Search

The shear behaviour of fibre-reinforced polymer reinforced concrete (FRP-RC) beams without web reinforcement suffers from low strength, low stiffness, more brittleness and wide and quick propagated cracks. Fortunately, the addition of various types of fibres could improve most of these weaknesses. On the other hand, the shear strength prediction of FRP-RC beams with various types of fibres is one of the most complex cases in structural engineering applications. Developing generalised, precise and consistent prediction models are necessary and very limited. This paper investigates the impacts of various types of fibres on shear strength and presents proposing four new prediction models, utilising artificial neural networks and empirical nonlinear regression analysis, and modifying the combination of available models based on a collected database of 49 shear test results of FRP-RC members with various types of fibres. The comparison of the developed models with the available equations from the literature indicates that the developed models yielded excellent performance, great efficiency and a high level of accuracy over all other existing models. Additionally, the parametric study confirmed that all the developed models have great abilities to accurately predict the actual response of each parameter, in spite of its complexity, on the shear strength of FRP-reinforced fibrous concrete beams without stirrups. [ABSTRACT FROM AUTHOR]

The reliability of thimble tubes plays a critical role for maintaining the safety of a nuclear power plant. The defect depth needs to be quantified and predicted to support the operational decision-making. This paper presents a method to quantify the defects on thimble tube wall based on the analyzation of eddy current testing (ECT) data. Then, a method using artificial neural network (ANN) to predict the detect depth is studied. The tubes are divided into 2 shapes and four regions according to their positions and the data of each region and each shape is expanded by mean interpolation. A prediction model based on ANN is constructed for each shape in each region. The experimental results show that the model can predict the signal of the next year according to the signal of the previous three years with mean absolute percentage error less than 16%. [ABSTRACT FROM AUTHOR]

Aims: The purpose of this study was to identify risk factors for cognitive impairment in advanced cancer patients and to develop predictive models based on these risk factors. Background: Cancer‐related cognitive impairment seriously affects the quality of life of advanced cancer patients. However, neural network models of cognitive impairment in patients with advanced cancer have not yet been identified. Design: A cross‐sectional design was used. Methods: This study collected 494 questionnaires between January and June 2022. Statistically significant clinical indicators were selected by univariate analysis, and the artificial neural network model and logistic regression model were used for multivariate analysis. The predicted value of the model was estimated using the area under the subject's working characteristic curve. Result: The artificial neural network and the logistic regression models suggested that cancer course, anxiety and age were the major risk factors for cognitive impairment in advanced cancer patients. All the indexes of artificial neural network model constructed in this study are better than those of the logistic model. Conclusion: The artificial neural network model can better predict the risk factors of cognitive impairment in patients with advanced cancer. Better prediction will enable nurses and other healthcare professionals to provide better targeted and timely support. Summary statement: What is already known about this topic?: Cancer‐related cognitive impairment has significantly affected the quality of life of patients with advanced cancer.Risk factors associated with cognitive impairment in patients with advanced cancer have not been adequately documented, and neural network models have not been identified. What this paper adds?: This study found that long a cancer course, anxiety and ageing were the most important risk factors for cognitive impairment in patients with advanced cancer.The artificial neural network showed good predictive indicators, indicating that it can be used to predict cognitive impairment in patients with advanced cancer. The implications of this paper: Neural network models can help nurses and other clinicians predict cognitive impairment in advanced cancer patients early which will allow provision of timely intervention. [ABSTRACT FROM AUTHOR]

BACKGROUND: Milling operations of laminae in spinal surgery generate high temperatures, which can lead to thermal injury and osteonecrosis and affect the biomechanical effects of implants, ultimately leading to surgical failure. OBJECTIVE: In this paper, a backpropagation artificial neural network (Bp-ANN) temperature prediction model was developed based on full factorial experimental data of laminae milling to optimize the milling motion parameters and to improve the safety of robot-assisted spine surgery. METHODS: A full factorial experiment design were used to analyze the parameters affecting the milling temperature of laminae. The experimental matrixes were established by collecting the corresponding cutter temperature T c and bone surface temperature T b for the milling depth, feed speed and different bone densities. The Bp-ANN lamina milling temperature prediction model was constructed from experiment data. RESULTS: Increasing milling depth increases bone surface and cutter temperature. Increasing feed speed had little effect on cutter temperature, but decreased bone surface temperature. Increasing bone density of laminae increased cutter temperature. The Bp-ANN temperature prediction model had best training results in the 10th epoch, and there is no overfitting (training set R = 0.99661, validation set R = 0.85003, testing set R = 0.90421, all temperature data set R = 0.93807). The goodness of fit R of Bp-ANN was close to 1, indicating that the predicted temperature was in good agreement with the experiment measurements. CONCLUSION: This study can help spinal surgery-assisted robot to select appropriate motion parameters at different density bones to improve lamina milling safety. [ABSTRACT FROM AUTHOR]

Rock mechanical properties are complex but essential for reservoir stimulation. Both experimental and empirical equation method have inevitable defects, and artificial neural network model (ANN) shows great potential in rock mechanics. This paper established a preliminary rock database from the Keshen block in Tarim Basin and improved clustering algorithm to assess the similarity between wells, creating sub-databases and realizing data sharing among similar wells. 18 parameters are used to predict ten rock mechanical properties and corresponding model inputs are optimized by correlation and sensitivity analysis separately. The results show that more accurate predictions can be obtained using optimized sample data and model inputs. The average predicted loss value using all 31 wells (221 samples) was 7.28%, while the value was reduced to 5.4% after clustering analysis using seven wells (95 samples). The average loss value can be further reduced to 4.3% using the optimized model inputs. As for rock peak stress, the predicted loss value is 2.5%, the determination coefficient (R2) is 0.983, and the root mean square error (RMSE) is 0.03. By optimizing training method, improving training sample quality, and optimizing model inputs, the problem of overfitting can be alleviated and a more reliable ANN model can be obtained. Highlights: Defined homogeneity coefficient based on computed tomography and image recognition, which is important for predicting rock mechanical properties. A preliminary database was established based on the rock samples from 31 wells for the training of the artificial neural network model. Improved clustering algorithm and performed similarity analysis between wells, created sub-databases, and improved data quantity and quality. 18 parameters are used to predict 10 rock mechanical properties, and model inputs are optimized by correlation and sensitivity analysis. [ABSTRACT FROM AUTHOR]

Miscanthus is a perennial energy crop that produces high yields and has the potential to be converted into energy. The ultimate analysis determines the composition of the biomass and the energy value in terms of the higher heating value (HHV), which is the most important parameter in determining the quality of the fuel. In this study, an artificial neural network (ANN) model based on the principle of supervised learning was developed to predict the HHV of miscanthus biomass. The developed ANN model was compared with the models of predictive regression models (suggested from the literature) and the accuracy of the developed model was determined by the coefficient of determination. The paper presents data from 192 miscanthus biomass samples based on ultimate analysis and HHV. The developed model showed good properties and the possibility of prediction with high accuracy (R2 = 0.77). The paper proves the possibility of using ANN models in practical application in determining fuel properties of biomass energy crops and greater accuracy in predicting HHV than the regression models offered in the literature. [ABSTRACT FROM AUTHOR]

Time-space four-dimensional motion target localization is a fundamental and challenging task in the field of intelligent driving, and an important part of achieving the upgrade in existing target localization technologies. In order to solve the problem of the lack of localization of moving targets in a spatio-temporal four-dimensional environment in the existing spatio-temporal data model, this paper proposes an optical imaging model in the four-dimensional time-space system and a mathematical model of the object-image point mapping relationship in the four-dimensional time-space system based on the central perspective projection model, combined with the one-dimensional "time" and three-dimensional "space". After adding the temporal dimension, the imaging system parameters are extended. In order to solve the nonlinear mapping problem of complex systems, this paper proposes to construct a time-space four-dimensional object-image mapping relationship model based on a BP artificial neural network and demonstrates the feasibility of the joint time-space four-dimensional imaging model theory. In addition, indoor time-space four-dimensional localization prediction experiments verify the performance of the model in this paper. The maximum relative error rates of the predicted motion depth values, time values, and velocity values of this localization method compared with the real values do not exceed 0.23%, 2.03%, and 1.51%, respectively [ABSTRACT FROM AUTHOR]

This paper investigates the possibility for implementing machine learning-aided prediction in analyzing the buckling phenomena of ballasted railway tracks induced by extreme temperature. In this study, artificial neural networks (ANNs) have been developed to identify the relationship between various ballasted track conditions and outputs, namely safe temperature and buckling temperature. The variables included in the objective function of the optimization problems are the lateral resistance of ballasted track provided by ballast-sleeper interaction, torsional resistance provided by fastening systems, and misalignment of the track. Due to its complexity in parameter combinations, the objective of this study is to create predictive models with the aim of minimizing the usage of scarce resources. Thus, this paper is the first to develop a novel machine learning-aided prediction of railway track buckling due to extreme temperature. Comprehensively, all 353 datasets of the safe and buckling temperatures derived from previous finite element (FE) simulation results have been collected and trained. Note that the mean squared error (MSE) and the coefficient of determination ( R 2) are considered to quantify the performance of the ANN architectures. The optimal ANN architecture with a very high rate of accuracy has been determined and highlighted. Thus, the suggested neural network model can be applied conveniently to help estimate safe and buckling temperatures of the complex track models in order to improve track conditions and thus prevent track buckling in summer. [ABSTRACT FROM AUTHOR]

Predicting the penetration depth during electron beam welding (EBW) is important, but the accuracy of current predictive models is highly varied, depending on the type and number of data used. This paper develops and compares several penetration depth prediction models for EBW and uniquely compares the influence of the number and type of data used, as well as the measurement and modelling methods. Although accelerating voltage, beam current and welding speed data are essential modelling inputs, additional data for beam focal position and beam shape, measured using a novel 4-slit beam probing method, greatly improve the accuracy of predictions for models based on an empirical equation, a second-order regression and an artificial neural network (ANN). Optimised models predict weld depths that deviate, on average, by less than 5% from measured depths, are valid for very broad linear electron beam power density ranges (86–324 J/mm) and are close to the estimated 4% inherent variability in the process and its measurement. Within this linear electron beam power density range, the ANN yields accurate and reliable depth predictions, demanding as few as 36 welding trials, decreasing the number required for models that do not consider beam focal position and shape, for the same targeted accuracy, by more than 60%. Adding large volumes of virtual data generated by less reliable analytical or regression models did not improve the predictive capability for the ANN developed in this study. [ABSTRACT FROM AUTHOR]

Al-50wt% Si alloy is considered as a difficult-to-machine material and is lack of precision machining research. In this paper, the response surface methodology (RSM), artificial neural network (ANN) and genetic algorithm (GA) are coupled to determine the optimum cutting conditions leading to the minimum surface roughness Ra and feed force Ft in Al-50wt% Si alloy precision milling. The purpose is to address the problem of machining parameters optimization in precision milling high Si-Al alloy. The Ra and Ft were considered as two process responses and cutting speed (vc), feed per tooth (fz), radial cutting depth (ae) and axial cutting depth (ap) were the process parameters. Using the rotatable orthogonal central composite design, 31 experiments were conducted. Based on RSM and analysis of variance (ANOVA), the influence of milling parameters on Ra and Ft was studied. The ANN was also employed for developing Ra and Ft predictive models, and its predictive capability was more accurate compared with RSM. Parameter optimizations were performed for minimizing Ra and Ft in single-objective and multi-objective cases using GA. In multi-objective optimization, the entropy weight method (EWM) was also implemented. Finally, the optimal parameter combination for precision milling Al-50wt% Si alloy was obtained as vc = 105 m/min, fz = 0.013 mm/z, ae = 3.909 mm and ap = 0.14 mm. The prediction errors were found as 3.27% and 4.65% for Ra and Ft, respectively. The results showed the effectiveness of the predictive model and the optimization method. [ABSTRACT FROM AUTHOR]

Analysis of the extraction modelling for natural compounds is essential for industrial application. In the present paper, ohmic-assisted extraction was investigated for the extraction of Falcaria vulgaris extract. This study was performed in order to express the effect of some pecific parameters (as: voltage gradiant, ethanol to water ratio, extraction time and temperature) on the extraction yield and total phenolic content (TPC). Kinetics models (first-order, second's-order and pelleg models) and artificial neural network were used for modeling ohmic-assisted extraction process. Kinetic study plays a very important role in evaluating the extraction process because it allows estimation of the cost-effectiveness of the process in saving time, money and energy. The results showed that the second-order and plleg's kinetic models respectively, were successfully predicted the value of the total phenol content of the extract and extraction yield in all experiments. The correlation coefficient between experimentally obtained extraction yield and total phenolic content and values predicted by artificial neural network (4-16-2) were 0.995 for training, 0.963 for validation, and 0.979 for testing, indicating the good predictive ability of the model. The artificial neural network model had a higher prediction efficiency than the kinetic models. Artificial neural network can reliably model the process with better predictive and estimation capabilities than the kinetic’s models. [ABSTRACT FROM AUTHOR]

This paper aimed to compare the multi-layer perceptron as an artificial neural network and the decision tree model for predicting OPEC crude oil production. Machine learning is about designing algorithms that automatically extract valuable information from data, and it has seen many success stories. The accuracy of these two models was assessed using symmetric mean absolute percentage errors, mean absolute scaled errors, and mean absolute percentage errors. Achieved were the OPEC crude oil production's maximum projected figures. The OPEC crude oil output was also represented by certain descriptive scales and graphs; A comparison was made between the results and the earlier results acquired by the others after the study of the association between the variables revealed statistical significance. [ABSTRACT FROM AUTHOR]

Coordinate measuring machines (CMMs) are massively exploited as measuring tools in the modern manufacturing industry. The performance of these machines, in terms of accuracy, has been considerably improved in recent years by using quasi-static errors compensation. Considering the shorter cycle times required during measurement tasks, CMMs are to be operated at high measuring velocity. In such measuring conditions, dynamic errors have a critical impact on measuring accuracy. Consequently, dynamic errors assessment, modeling, and compensation are needed to improve the overall CMM metrological performances. In this paper, a comprehensive predictive modeling strategy for dynamic error compensation is developed and applied successfully. The main measuring parameters that influence CMM dynamic performance are identified and used in a systematic experimental investigation. The positioning accuracy is then evaluated concerning dynamic conditions using a high-precision laser interferometer. Based on the experimental results, neural network models are built according to a structured modeling procedure inspired by the Taguchi method. Improved statistical analysis tools and performance measurement criteria are used to extract the most appropriate variables and conditions leading to well-founded predictive modeling. The resulting models are implemented on a bridge-type CMM to compensate for both geometric and dynamic errors. The results demonstrate a reduction of more than 80% of dynamic errors. This demonstrates that the compensation of dynamic-induced errors using high-speed measurement is achieved leading to shorter cycle times of measurement tasks while maintaining high accuracy measurements. [ABSTRACT FROM AUTHOR]

• Developing optimized neural network-based models for trapdoor stability prediction. • New FELA solutions for 3D rectangular trapdoors in anisotropic clays. • Developing hybrid machine learning models based on ANNs with various optimization algorithms. • Examining several performance metrics, regression plots, and rank analysis. The problem of trapdoor stability is a crucial problem in geotechnical engineering. This study is the first to introduce novel neural network-based metaheuristic models for the stability prediction of 3D rectangular trapdoors in anisotropic and nonhomogeneous clays. However, no researcher has considered such trapdoor problems in the past. In this study, the dataset is obtained by using finite element limit analysis (FELA). The proposed hybrid machine learning models based on artificial neural networks (ANNs) and various types of optimization algorithms (OAs), namely, ant colony optimization (ACO), artificial lion optimization (ALO), the imperialist competition algorithm (ICA), and shuffled complex evolution (SCE), are also proposed in this paper by undergoing rigorous optimization to ensure accuracy and efficiency in capturing the intricate dynamics of the stability investigations from the models. The performance of the proposed ANN-based models is assessed using several performance metrics, regression plots, and rank analysis. The proposed ANN-SCE model outperforms the other proposed models in predicting trapdoor stability, where the ANN-SCE model achieved the highest rank, with a score of 58, followed by the ANN-ALO (47), ANN-ICA (33), and ANN-ACO (22) models. The proposed neural network-based metaheuristic models deliver precise and effective forecasts of trapdoor stability to make informed decisions concerning road design and mitigation tactics, ultimately improving the robustness of infrastructure facing geotechnical challenges. [ABSTRACT FROM AUTHOR]

The problem addressed in this work is the enhancement of energy efficiency in buildings, primarily focused on heating control. The paper highlights the importance of addressing this challenge, given that HVAC systems are responsible for over 60% of total energy consumption in buildings, making them the largest energy consumers in both the residential and nonresidential sectors. This paper presents a methodology for developing a model predictive control (MPC) system based on artificial neural network (ANN) models, with the aim of improving the energy efficiency of buildings. This approach involves the creation of a training dataset using dynamic thermal simulation tools, enabling the learning of the ANN model that is responsible for predicting future states within an MPC optimization loop. Additionally, the implementation leverages advanced technologies such as Field-Programmable Gate Arrays (FPGAs), specifically the PYNQ board, Wi-Fi modules, and MQTT communication to enhance scalability, deployment, and adaptability. The study evaluates the proposed Neural Network Model Predictive Control (NNMPC) strategy implemented on the PYNQ, reporting a substantial reduction of 38.53% in heating energy consumption in buildings compared to a basic On/Off control approach for 24-hour simulation. This outcome underscores the solutions significant potential for energy savings in building heating systems. [ABSTRACT FROM AUTHOR]

Wind power, as a potential new energy generation technology, is gradually developing towards to the mainstream energy in the world. However, the inherent random volatility of wind brings severe challenges to the safe operation of the grid and the reliability of power supply, one of the effective ways to solve the problem is to improve the accuracy of wind speed prediction. However, most of wind speed prediction model cannot well mine the inherent regularity of wind speed data. Therefore, this paper introduces variational mode decomposition (VMD) algorithm. And the Short-term Wind Speed Prediction Model based on GA-ANN improved by VMD is proposed, which can effectively improve the accuracy of wind speed prediction. Firstly, hierarchical cluster method in this paper is employed to extract the historical data with high similarity to the predicted day. And then the appropriate number of decompositions K is selected by judging the value of sample entropy, so that the extracted historical data is decomposed into K subsequences by the variational mode decomposition. Next, with the global optimization ability of genetic algorithm, the artificial neural network is optimized to improve the forecasting performance. Finally, the short-term wind speed forecasting model based on GA-ANN improved by VMD is employed to predict the wind speed of each subsequence and superimposed them to obtain the final wind speed prediction sequence. The results in this paper show that (1) the model can find the periodic fluctuation of wind speed through historical data by hierarchical cluster method, so that significantly improving the accuracy of short-term wind speed prediction; (2) for the wind speed prediction, the error value of GA-ANN model is smaller than that of BP neural network; (3) in view of the inherent nature of the wind, the model proposed in this paper can use VMD to decompose the wind speed signal to obtain different scale fluctuations or trends, so as to fully exploit the potential information of wind speed, and obtain more accurate prediction results. The research work can help the relevant departments of the power system to accurately assess the risk of power grid operation, make a reasonable generation plan, effectively reduce the cost of power operation, and then greatly promote the development of green energy. • Proposing a new windspeedprediction model named HC-VMD-GA-BPmodel. • Using hierarchical cluster methodtoselect the historical wind speed data. • VMD is introduced to decomposethe original wind speed sequence. • Artificial neural networkisoptimized by GA to improve the prediction performance. • The HC-VMD-GA-BP model is comparedwith other models to verify itseffectiveness and high prediction accuracy. [ABSTRACT FROM AUTHOR]

Viscoelastic characterization of asphalt binders is critical for selecting suitable binders for a given climatic region and for improving long-term performance prediction using mechanistic-empirical pavement analysis and design methods, such as the Mechanistic-Empirical-Pavement-Design-Guide (MEPDG). A-VTS information (viscosity data) was used in the past and existing databases have this type of information. Nowadays, Dynamic Shear Modulus (|G*|) and Phase Angle (δ) determination using the Dynamic Shear Rheometer (DSR) is common practice. This resulted in the existence of old and new databases in highway agencies. The goal is to find a way to combine these separate data sets and merge them into a unified national database based on |G*| and δ. The work discussed in this paper is critical to make this merger possible and to use this in future binder to mixture predictive model developments and in MEPDG. In this study, |G*| and δ prediction models were developed. A machine learning technique named Artificial Neural Network (ANN) was employed in this process. 8940 data points from 41 binders were utilized in the model development process. After robust training, validation, and testing process, a |G*| prediction model with seven neurons and a δ prediction model with three neurons were reported. The models were compared with previous Bari-Witczak and Onifade-Birgisson models. ANN-based models performed better in every statistical parameter. Two equations were also extracted from the ANN models, which can be used reliably to predict |G*| and δ from A-VTS data. These two models with closed-form equations can be incorporated into the MEPDG for |G*| and δ predictions. • New models for Binder dynamic shear modulus and phase angle using binder viscosity data with temperature and frequency. • Artificial Neural Network (ANN) is utilized in the model development process. • An equation is extracted from each ANN-based model. • The prediction performance of new models is better than existing models in every statistical parameter. [ABSTRACT FROM AUTHOR]

This paper presents an empirical model for predicting the uniaxial compressive strength (UCS) of rocks using gene expression programming (GEP). A total of 44 datasets collected from the literature was used to construct the GEP model. The GEP model developed is evaluated using four conventional regression models and an artificial neural network (ANN) model in terms of three statistical indices. The comparison results confirmed that the proposed GEP model has the lowest root mean square error (RMSE) and the highest coefficient of determination (R 2 ) and correlation coefficient (R) values compared to the four conventional regression models and the ANN model in the literature. It is concluded that the proposed GEP model can be applied to predict the UCS of rocks [ABSTRACT FROM AUTHOR]

Automotive aftermarket industry is possessed of a wide product portfolio range which is in the 4th rank by its worldwide trade volume. The demand characteristic of automotive aftermarket parts is volatile and uncertain. Nevertheless, the cause-and-effect relationship of automotive aftermarket industry has not been defined obviously heretofore. These conditions bring automotive aftermarket sales forecasting into a challenging process. This paper is composed to determine the relevant external factors for automotive aftermarket sales based on expert reviews and to propose a sales forecasting model for automotive aftermarket industry. Since computational intelligence techniques yield a framework to focus on predictive analytics and prescriptive analytics, an artificial neural network model constructed for Turkey automotive aftermarket industry. Artificial intelligence is a subset of computational intelligence that focused on problems which have complex and nonlinear relationships. The data which have complex and nonlinear relationships could be modelled successfully even though incomplete data in case of implementation of appropriate model. The proposed ANN model for sales forecast is compared with multiple linear regression and revealed a higher prediction performance. [ABSTRACT FROM AUTHOR]

Due to a lack of solar radiation measurement instruments in various regions across the world, particularly in Ethiopia, many empirical models have been developed to estimate global solar radiation. Reliable global solar radiation infor- mation is essential for the design and development of solar energy systems.Thus, the aim of this paper is to investigate the feasibility of using Artificial Neural Network (ANN) to predict mean daily global solar radiation (GSR) and to compare the performance of ANN and empirical models based on sunshine in estimating mean daily global solar irradiation on a horizontal surface.For the ANN model, network inputs were daily data for a number of days, average daily data (sunshine hours, maximum temperature, minimum temperature, wind speed, relative humidity, and pressure), and while daily averaged global solar radiation was the network output.After training, the model had R values of 0.891 for training, 0.932 for validation, 0.920 for testing, and 0.903 for all, with validation performance of 0.0797.The results of the ANN model were compared to the empirical equations using statistical error evaluation (MBEANN = 0.0005, RMSEANN = 0.3310, and R2ANN = 0.7998).The agreement between the values of NASA and estimated values reveals that the ANN exhibits good performance in studying daily GSR. The result also shows that the mean daily GSR is varying between 3.675KWh/m² (August-1) and 6.935 KWh/m² (April-19) in the study site. [ABSTRACT FROM AUTHOR]

This paper is motivated by searching for the perfect pattern for the spectroscopy spectra using artificial neural networks (ANN) using python programming coding. The pattern from the spectroscopy is based on the absorption and emission of light and other radiation by materials in relation to the wavelength dependence of these processes. Spectral equipment such as spectrometers, spectral analysers, spectrographs, or spectrophotometers is utilised to determine spectrum values. The problem in this spectroscopy is to identify the sample or analyte, which can be solved by a prediction model for spectroscopy using Python. These problems occur when finding the best algorithm of pre-processing techniques that can predict any model accurately into an understandable format for prediction models. Various types of pre-processing techniques have been used, such as Multiplicative Scatter Correction (MSC), Inverse MSC, Extended MSC (EMSC), Extended Inverse MSC, de-trending, Standard Normal Variate (SNV) and normalisation in order to get a better r2 value. In this project, we find the r2 and the root mean square error (RMSE) to evaluate the prediction values and the actual values. First, choosing pre-processing techniques and then finding the best statistical method for constructing predictive models that produce high accuracy. We used ANN in this project as a prediction model. Based on the results, we managed to achieve our objective, which is that the prediction model has more than 90% of accuracy. Furthermore, the results show that our prediction model has 1.0 accuracy at 100 Epoch with a 0.3 learning rate. Finally, we can conclude that our prediction model can be used to predict the spectroscopybased data format. [ABSTRACT FROM AUTHOR]

This paper aimed to explore the non‐destructive detection of apple firmness based on portable acoustic signals for consumers. The acoustic eigenvalues processed by Time‐domain, Fourier Transform (FT), and Hilbert Huang Transform (HHT) are used to analyse the correlations with apple firmness. The apple firmness prediction models are established through Multiple Linear Regression (MLR) and Artificial Neural Network (ANN). The results proved that the acoustic eigenvalues of wave index form and total energy of 8–9 kHz correlated with apple firmness (P < 0.05), the significant acoustic eigenvalues of sound intensity, amplitude difference, max frame energy, maximum power spectral density, power spectral density characteristics and total energy of 0–1 kHz significantly correlated with apple firmness (P < 0.01). The average relative error of ANN model was significantly lower than that of MLR model (P < 0.05). Compared with Time‐FT, the acoustic eigenvalues processed by a combination of Time‐FT‐HHT possessed a superior effect on the prediction model established by ANN of apple firmness. [ABSTRACT FROM AUTHOR]

This paper presents a new artificial neural network (ANN)-based system model that concatenates an optimized artificial neural network (OANN) and a neural network compensator (NNC) in series to capture temporally varying system dynamics caused by slow-paced degradation/anomaly. The OANN comprises a complex, fully connected multilayer perceptron, trained offline using nominal, anomaly free data, and remains unchanged during online operation. Its hyperparameters are selected using genetic algorithm-based meta-optimization. The compact NNC is updated continuously online using collected sensor data to capture the variations in system dynamics, rectify the OANN prediction, and eventually minimize the discrepancy between the OANN-predicted and actual response. The combined OANN-NNC model then reconfigures the model predictive control (MPC) online to alleviate disturbances. Through numerical simulation using an unmanned quadrotor as an example, the proposed model demonstrates salient capabilities to mitigate anomalies introduced to the system while maintaining control performance. We compare the OANN-NNC with other online modeling techniques (adaptive ANN and multinetwork model), showing it outperforms them in reference tracking of altitude control by at least 0.5m and yaw control by 1 deg. Moreover, its robustness is confirmed by the MPC consistency regardless of anomaly presence, eliminating the need for additional model management during online operation. [ABSTRACT FROM AUTHOR]

This paper proposes an artificial neural network (ANN) to predict the solar energy generation produced by photovoltaic generators. The intermittent nature of solar power creates two main issues. Firstly, power production and demand have to be balanced to ensure the control of the whole system, and the inherent variability of clean energies makes this difficult. Secondly, energy generation companies need a highly accurate day-ahead or intra-day estimation of the energy to be sold in the electricity pool. For the tool developed in this paper, we address the issue of the complexity of control in systems that are based on solar energies. The tool's ability to predict the parameters that are involved in solar energy production will allow us to estimate the future power production in order to optimise grid control. Our tool uses an ANN which we developed using MATLAB ® software. The results were validated by analysing the root mean square error of the prediction for days outside the database used for training the ANN. The difference between the actually produced and predicted energy is about 0.5–9%, meaning that the accuracy of our tool is sufficient enough to be installed in systems which have integrated solar generators. [ABSTRACT FROM AUTHOR]

Due to heterogeneity in municipal solid waste (MSW) characteristics and composition, the already available heating value estimation methods cannot be accurately applied for the cities of developing countries. In this study, both linear and non-linear approaches have been used for the development of lower heating value (LHV) prediction models. The models have been developed based on the physical composition, proximate analysis, and ultimate analysis of both mixed MSW and combustible components (food waste, yard waste, plastic, paper & cardboard, textile & rubber) separately. In total, six multiple linear regression (MLR) models and six artificial neural network (ANN) models have been developed. All of them can be used for the timely decision making as per the availability of data and requirements with a sufficient level of accuracy. The physical composition based LHV prediction models (both MLR and ANN) showed highest prediction performance. The models developed using combustible components showed slightly better prediction capabilities than mixed MSW based models. Further, in this study, an appropriate refuse-derived fuel (RDF) mix has been determined based on the ease of recovery of the individual waste components from the mixed MSW stream. Finally, the energy recovery potential from mass-burn incineration and RDF incineration has been evaluated. The energy recovery potential of proposed RDF (combination of plastic, paper & cardboard, textile & rubber and yard waste) and mixed MSW was found to be 1310 kWh/tonne and 837 kWh/tonne of dry weight respectively. • Lower heating value prediction models are developed using linear regression & ANN. • Models are based on physical composition, proximate and ultimate analysis of MSW. • The developed models can be used for both mixed MSW and combustible components. • Models based on physical composition of MSW showed highest prediction accuracy. • The proposed RDF has energy recovery potential of 1310 kWh/tonne of dry RDF. [ABSTRACT FROM AUTHOR]

The Newmark-type predictive models are extensively used to estimate earthquake-induced sliding displacements (D) of slopes. Most existing models are designed for shallow slope failure using polynomial regression. Based on a large amount of decoupled sliding-block analyses, this paper proposes an artificial neural network (ANN)-aided model to predict D for both shallow and deep slope failures using peak ground acceleration and spectral acceleration at the 2 s period (SA (2 s)). Three sub-models are included for estimating shallow sliding displacement, representing dynamic response of sliding mass, and modifying the displacement for deep failure, respectively. The key features achieved are as follows: (1) the inputted SA is more easily accessible than the mean period (T m) required by the existing models; (2) impedance ratio (IR) is utilized to account for stiffness conditions of geo-materials underlying slip surfaces; (3) powerful ANN is introduced for the first time as a surrogate of the decoupled analysis. The SA -based model generally yields lower biases and uncertainty than the existing models. Since larger D is produced for smaller IR , the existing models with a single IR value would be unconservative for relatively stiff underlying soils and/or soft overlying soils. Coefficients of the proposed model are provided for practical applications. [ABSTRACT FROM AUTHOR]

• An artificial neural network-parallel connected (ANN-PL) model is proposed to predict vehicle running attitude under the single-vehicle impact condition. • The 3D multibody dynamics model of the single-vehicle impact on the rigid wall is established to generate the datasets and validated by the experimental full-scale test. • The predictive capacity of the proposed network model is validated in the test datasets. • The key factors affecting vehicle running attitude are studied by the change of MSE method (COM) in the ANN-PL. Artificial neural networks have drawn growing attention for their outstanding predictive capability combined with traditional research methods. This paper aims to propose a vehicle running attitude prediction model based on Artificial Neural Network-Parallel Connected (ANN-PL), predicting the longitudinal displacement (S vx) and vertical displacement (S vz) of the vehicle body, the vehicle head-up angle (α), and the overriding risk (C d). The 3D multibody dynamics model (MBD) of the single-vehicle impact on the rigid wall, namely 3D-MBD-SV, was established and validated by the experimental full-scale vehicle collision test. Based on the reliable 3D-MBD-SV, the design of experiment (DOE) approach was carried out to obtain the datasets for training the ANN-PL. The ANN-PL exhibited excellent computational efficiency and satisfactory prediction accuracy compared to the multibody dynamics and finite element simulation calculation methods. However, the different network hyperparameters of the ANN-PL network are essential to prediction accuracy, considering the number of hidden layers and neurons in this paper. In terms of the variables factor analysis, the change of Mean Square Error (MSE) method (COM) in the ANN-PL was used to explore the relationship between the eleven essential input variables and vehicle running attitude. It was found that the maximum relative contribution in ANN-PL (S vx , S vz , α, C d) is vehicle body mass (M c) at 70.65%, impact velocity (V x) at 43.39%, vertical offset of the vehicle body center mass (CM z) at 30.14%, and primary suspension axle box spring vertical travel (D pz) at 13.63%, respectively. The outcome of this study is expected to provide a research method to solve the complicated engineering issue by building a new artificial neural network algorithmic framework combined with the multibody dynamics and finite element simulation calculation methods. [ABSTRACT FROM AUTHOR]

Future building energy management systems will have to be capable of adapting to variation in the rate of production of energy from renewable sources. Controllers employing a model predictive control (MPC) framework can optimise and schedule energy usage based on the availability of renewably generated energy. In this paper, an MPC using artificial neural networks (ANNs) was implemented in a residential building. The ANN-MPC was successfully tested and demonstrated good performance predicting the building's energy consumption. The controller was then modified to function as an economic MPC (EMPC) to optimise demand flexibility (i.e., the ability to adapt energy demands to fluctuations in supply). The operational costs of energy usage were associated with this demand flexibility, which was represented by three flexibility indicators: flexibility factor, supply cover factor, and load cover factor. The results from a day-long test showed that these flexibility indicators were maximised (flexibility factor ranged from −0.88 to 0.67, supply cover factor from 0.04 to 0.13, and load cover factor from 0.07 to 0.16) when the EMPC controller's demand flexibility was compared to that of a conventional proportional-integral (PI) controller. The EMPC framework for demand flexibility can be used to regulate on-site energy generation, grid consumption, and grid feed-in and can thus serve as a basis for overall optimisation of the operation of heating systems to achieve greater demand flexibility. • An ANN-MPC was developed and tested in a residential building. • ANN models and an MPC framework were validated against measurements in buildings. • An EMPC to maximise the demand flexibility of residential buildings was developed and tested. [ABSTRACT FROM AUTHOR]

Abstract The prediction of interval-valued data is a challenging task as the predicted lower bounds of intervals should not cross over the corresponding upper bounds. In this paper, a regularized artificial neural network (RANN) is proposed to address this difficult problem. It provides a flexible trade-off between prediction accuracy and interval crossing. Compared to existing hard-constrained methods, the RANN has the advantage that it does not necessarily reduce the prediction accuracy while preventing interval crossing. Extensive experiments are conducted based on both simulation and real-life datasets, with comparison to multiple traditional models, including the linear constrained center and range method, the least absolute shrinkage and selection operator-based interval-valued regression, the nonlinear interval kernel regression, the interval multi-layer perceptron and the multi-output support vector regression. Experimental results show that the proposed RANN model is an effective tool for interval-valued data prediction tasks with high prediction accuracy. [ABSTRACT FROM AUTHOR]

Thousands of investigations on quantitative structure-activity/property relationships (QSARs/QSPRs) have been reported. However, few publications can be found that deal with QSARs for aptamers, because calculating two-dimensional and three-dimensional descriptors directly from aptamers (typically with 15-45 nucleotides) is difficult. This paper describes calculating molecular descriptors from amino acid sequences that are translated from DNA aptamer sequences with DNAMAN software, and developing QSAR models for the aptamers' binding affinity to the influenza virus. General regression neural network (GRNN) based on Parzen windows estimation was used to build the QSAR model by applying six molecular descriptors. The optimal spreading factor σ of Gaussian function of 0.3 was obtained with the circulation method. The correlation coefficients r from the GRNN model were 0.889 for the training set and 0.892 for the test set. Compared with the existing model for aptamers' binding affinity to the influenza virus, our model is accurate and competes favourably. The feasibility of calculating molecular descriptors from an amino acid sequence translated from DNA aptamer sequences to develop a QSAR model for the anti-influenza aptamers was demonstrated. [ABSTRACT FROM AUTHOR]

A full methodology of short-term traffic prediction is proposed for urban road traffic network via Artificial Neural Network (ANN). The goal of the forecasting is to provide speed estimation forward by 5, 15 and 30 min. Unlike similar research results in this field, the investigated method aims to predict traffic speed for signalized urban road links and not for highway or arterial roads. The methodology contains an efficient feature selection algorithm in order to determine the appropriate input parameters required for neural network training. As another contribution of the paper, a built-in incomplete data handling is provided as input data (originating from traffic sensors or Floating Car Data (FCD)) might be absent or biased in practice. Therefore, input data handling can assure a robust operation of speed forecasting also in case of missing data. The proposed algorithm is trained, tested and analysed in a test network built-up in a microscopic traffic simulator by using daily course of real-world traffic. [ABSTRACT FROM AUTHOR]

Abstract Desalting brines from Reverse Osmosis (RO) plants is one of the most promising applications of Membrane Distillation (MD) systems. The development of accurate models to predict MD system performances plays a significant role in the design of this kind of industrial applications. In this paper, a commercial-scale Permeate-Gap Membrane Distillation (PGMD) module was modelled by means of two different approaches: Response Surface Methodology (RSM) and Artificial Neural Networks (ANN). Condenser inlet temperature, evaporator inlet temperature, feed flow rate and feed water salt concentration were selected as inputs of the model, while permeate flux and Specific Thermal Energy Consumption (STEC) were chosen as responses. The prediction abilities of both RSM and ANN models were compared with further experimental data by using the Analysis of Variance (ANOVA) and the Root Mean Squared Error (RMSE). The results show that the ANN model is able to predict in a more precise way the behaviour of the module for the whole range of input variables. Thus, ANN model was used to find the optimal operating conditions, for the module operating at feed water salinity of 70 and 105 g/L, concentrations that can be reached when desalting RO brines. Highlights • Commercial-scale permeate-gap membrane distillation evaluated for high salinity • Prediction models based on RSM and ANN have been developed from the experimental data. • A comparison between the two modelling tools is provided. • 3D response surfaces showing the influence of the feed salinity are presented. • The operation of MD pilot unit for desalting RO brines is optimized. [ABSTRACT FROM AUTHOR]

Highlights • High variation in starch content of cassava roots significantly affect yield of starch production. • Regression, ANN, and HDBN were used to predict and identify key factors affecting starch contents. • Observational data in five categories are collected from 242 farmers at a manufacturing plant. • HDBN performs the best in starch prediction with MAPE of 6.226% and RMSE of 2.35 percent of starch. • Key factors include harvest age, planting density, growing season, farm location, among others. Abstract This paper involves an application of prediction models to study quality of incoming raw materials of a tapioca starch manufacturer in Thailand. The objectives are to estimate starch content of fresh cassava roots and to identify significant factors that affect starch content in cassava roots. Three prediction models, including multiple regression, artificial neural network (ANN), and hybrid deep belief network (HDBN), are implemented. Input data were collected from 242 farmers from 49 different sub-districts in Nakhon Ratchasima province in the Northeast of Thailand, who supply fresh cassava roots to the manufacturing plant. Potential factors are classified into four categories: farmers' demographics, cultivation activities, harvesting activities, and logistics activities, a total of 38 variables. Regression models, ANNs with one hidden layer, and HDBNs were constructed for starch content prediction. Prediction performances were evaluated using the root mean square error (RMSE) and mean absolute percentage errors (MAPE), which were 2.44 percent of starch content and 7.283% for the best regression model; 2.41 and 7.055% for the best ANN, and 2.35 and 6.226% for the best HDBN, respectively. The results indicate that HDBN outperforms the other two models in terms of prediction performance. The final regression model and the best ANN are primarily used to identify seven important factors that can potentially describe starch content. These include harvest age, planting density, growing season, farm location, type of soil, cassava variety, and weed control method. [ABSTRACT FROM AUTHOR]

Abstract Near wellbore failure during the exploration of hydrocarbon reservoirs presents a serious concern to the oil and gas industry. To predict the probability of these undesirable phenomena, engineers study the mechanical rock properties of the formation such as Young's modulus, Bulk modulus, shear modulus and Poisson's ratio. Conventionally, these are measured indirectly using the established petro physical relationships from sonic wave velocities which can be obtained from sonic well logs. Unfortunately, reliable sonic well logs are not always available, due to poor borehole conditions (wash out), damaged tools and offset well data. Most offset well log data are not acquired with dipole sonic tools; they are acquired with a borehole compensated logging tool. This limits the application of acoustic measurements to estimate the mechanical rock properties. In this study, a three-layer feedforward multilayered perceptron artificial neural network model is presented. This model aims to estimate compressional wave transit time and shear wave transit time using real gamma ray and formation density logs. The validation of the model is confirmed by using an oil and gas offshore shaley sandstone reservoir located in West Africa. The results of the validation show that the model presented in this study can be used to determine the sanding potential of the formation without performing a compressive geoscientific analysis in the absence of sonic well logs. The developed model's effectiveness is tested by comparing the predicted results with results obtained from the measured well log. The paper provides a tool to give preliminary recommendations of the likelihood of the formation to produce sand. Implementation of the proposed model can serve as a cost-effective and reliable alternative for the oil and gas industry. Highlights • A new a multilayered perceptron artificial neural network (ANN) model is presented to model transit time and shear wave transit time. • The proposed ANN model assists in estimating rock mechanical properties and sanding criterion of a formation. • The proposed ANN model also assists in estimating formation failure along the wellbore formation. • The proposed model is tested and validated using a real life case study. [ABSTRACT FROM AUTHOR]

The cloud shading on the photovoltaic (PV) power station is one of the main factors that cause random changes in the PV output power, and thereby greatly influences an ultra-short-term photovoltaic power prediction. This paper presents an ultra-short-term prediction model for photovoltaic power generation based on dynamic characteristics of the cloud that is sheltering the sun. The proposed prediction model consists of three stages. In the first stage, the moving trajectory of the cloud is predicted using the motion vector and the cloud that shelters the sun is selected. In the second stage, the dynamic characteristics of target cloud, which have a great influence on the photovoltaic power generation, are extracted using the digital image processing. In the third stage, a prediction model based on the radial basis function (RBF) neural network, which is trained with processed sample data, is designed. Finally, the performance of RBF prediction model is compared with the performance of auto regressive (AR) model. The comparison shows that the power prediction accuracy of RBF model is 7.4% and the power prediction accuracy of AR model is 13.6%. The proposed ultra-short-term PV power prediction model can significantly improve the power prediction performance, especially in cloudy weather. [ABSTRACT FROM AUTHOR]

This paper proposes a machining performance prediction approach on multiple performances of wire electrical discharge machining (WEDM) on Inconel 718. Artificial neural network (ANN) is emphasized to predict the machining performances. Many efforts have been made to model the performances of WEDM using ANN. However, to obtain the best ANN model, generally the network parameters are not consistent and so far, the selection has been made in a random manner and resulted in an excessive experimental trial. Taguchi design orthogonal array L256 is implemented in the process of network parameter selection to search for the potential machining model. This approach, prescribed as OrthoANN, is simplified to avoid as much as unnecessary experimentations. Material removal rate, surface roughness (Ra), cutting speed (Vc) and sparking gap (Sg) are the machining performances considered in this study. Five machining parameters considered; pulse on time, pulse off time, peak current, servo voltage and flushing pressure. Cascade forward back-propagation neural network (CFNN) is found to be the best network type of the selected data set. One hidden layer 5-14-4 CFNN showed the most precise and generalized network architecture with very good prediction accuracy. An average of 5.16% error is generated which seems to be in superior concurrence with the actual experimental results. Confirmation test is carried out to verify the machining performances suggested by this approach. [ABSTRACT FROM AUTHOR]

The energy production analysis of a system based on renewable technology depends on the inputs estimation accuracy. The solar energy is a free resource characterized by high variability; hence, its correct evaluation is a strategic factor for the feasibility of a solar system. In this paper a new methodological approach is presented in order to evaluate more accurately the electric and thermal energy production of a point-focus concentrating photovoltaic and thermal system (CPV/T). Two Artificial Neural Network (ANN) models for predicting solar global radiation and direct normal solar irradiance (DNI) are developed adopting different parameters such as climatic, astronomic and radiometric variables. In particular, a new combination of parameters is proposed in this paper and adopted first of all for the global radiation evaluation whose ANN model can be easily compared with the literature; the data are trained and tested by a multi layer perceptron (MLP). Hence, the results validation for the global solar radiation evaluation has encouraged to design an ANN model for the DNI by means of a similar variables set. The MLP network is trained, tested and validated for the hourly DNI estimation obtaining the MAPE, RMSE and R 2 statistical indexes values respectively equal to 5.72%, 3.15% and 0.992. Finally, the electric and thermal outputs of a point-focus CPV/T system are evaluated varying the concentration factor and cells number, and adopting as input the DNI evaluation results obtained by the ANN model presented in this paper. The CPV/T system outputs are estimated referring to the city of Salerno (Italy) under different meteorological conditions. [ABSTRACT FROM AUTHOR]

In this paper four different Soft Computing (SC) models have been proposed which are able to predict AC breakdown voltage of the two solid insulating materials, namely Leatherite Paper and Manila Paper. The predicted voltage is a function of four input parameters, such as, the thickness of the insulating sample t, void depth t1, void diameter d and relative permittivity of the materials er. The requisite data on the breakdown voltages are obtained after statistical analysis of the experimental observations performed with a cylinder-plane electrode system by step-stress method. The voids are artificially created for initiation of Partial Discharge (PD) with different depths and diameters. The proposed SC models seem to be capable of predicting the breakdown voltages quiet efficiently and within a small value of mean absolute error. In order to get a better insight of the breakdown phenomenon, the two solid insulating materials have been observed using a Scanning Electron Microscope (SEM). The SEM images clearly show the degradation taking place in these materials leading ultimately to the breakdown. [ABSTRACT FROM AUTHOR]

Building cooling load prediction is critical to the success of energy-saving measures. While many of the computational models currently available in the industry have been developed for this purpose, most require extensive computer resources and involve lengthy computational processes. Artificial neural networks (ANNs) have recently been adopted for prediction, and pioneering works have confirmed the feasibility of this approach. However, users are required to predetermine an ANN model's parameters. This hinders the applicability of the ANN approach in actual engineering problems, as most engineers may be unfamiliar with soft computing. This paper proposes a fully autonomous kernel-based neural network (AKNN) model for noisy data regression prediction. No part of the model's mechanism requires human intervention; rather, it self-organises its structure according to the training samples presented. Unlike the other existing autonomous models, the AKNN model is an online learning model. It is particularly suitable for online steps-ahead prediction. In this paper, we benchmark the AKNN model's performance according to other ANN models. It is also successfully applied to predicting the cooling load of a commercial building in Hong Kong. The occupancy areas and concentration of carbon dioxide inside the building are successfully adopted to mimic the building's internal cooling load. Training data was adopted from actual measurements taken inside the building. Its results show reasonable agreement with actual cooling loads. [ABSTRACT FROM AUTHOR]

In this paper, group contribution (GC) property models for the estimation of acid dissociation constants ( K a ) of organic compounds are presented. Three GC models are developed to predict the negative logarithm of the acid dissociation constant pK a : (a) a linear GC model for amino acids using 180 data-points with average absolute error of 0.23; (b) a non-linear GC model for organic compounds using 1622 data-points with average absolute error of 1.18; (c) an artificial neural network (ANN) based GC model for the organic compounds with average absolute error of 0.17. For each of the developed model, uncertainty estimates for the predicted pK a values are also provided. The model details, regressed parameters and application examples are highlighted. [ABSTRACT FROM AUTHOR]

The Baltic Dry Index (BDI) is a robust indicator in the shipping sector in terms of global economic activities, future world trade, transport capacity, freight rates, ship demand, ship orders, etc. It is hard to forecast the BDI because of its high volatility and complexity. This paper proposes an artificial neural network (ANN) approach for BDI forecasting. Data from January 2010 to December 2016 are used to forecast the BDI. Three different ANN models are developed: (i) the past weekly observation of the BDI, (ii) the past two weekly observations of the BDI, and (iii) the past weekly observation of the BDI with crude oil price. While the performance parameters of these three models are close to each other, the most consistent model is found to be the second one. Results show that the ANN approach is a significant method for modeling and forecasting the BDI and proving its applicability. [ABSTRACT FROM AUTHOR]

The functional design of submerged breakwaters is still developing, particularly with respect to modelling of the nearshore wave field behind the structure. This paper describes a method for predicting the wave transmission coefficients behind submerged breakwaters using machine learning algorithms. An artificial neural network using the radial-basis function approach has been designed and trained using laboratory experimental data expressed in terms of non-dimensional parameters. A wave transmission coefficient calculator is presented, based on the proposed radial-basis function model. Predictions obtained by the radial-basis function model were verified by experimental measurements for a two dimensional breakwater. Comparisons reveal good agreement with the experimental results and encouraging performance from the proposed model. Applying the proposed neural network model for predictions, guidance is given to appropriately calculate wave transmission coefficient behind two dimensional submerged breakwaters. It is concluded that the proposed predictive model offers potential as a design tool to predict wave transmission coefficients behind submerged breakwaters. A step-by-step procedure for practical applications is outlined in a user-friendly form with the intention of providing a simplified tool for preliminary design purposes. Results demonstrate the model’s potential to be extended to three dimensional, rough, permeable structures. [ABSTRACT FROM AUTHOR]

Knowing the pressure coefficient on building surfaces is important for the evaluation of wind loads and natural ventilation. The main objective of this paper is to present and to validate a computational modeling approach to accurately predict the mean wind pressure coefficient on the surfaces of flat-, gable- and hip-roofed rectangular buildings. This approach makes use of artificial neural network (ANN) to estimate the surface-average pressure coefficient for each wall and roof according to the building geometry and the wind angle. Three separate ANN models were developed, one for each roof type, and trained using an experimental database. Applied to a wide variety of buildings, the current ANN models were proved to be considerably more accurate than the commonly used parametric equations for the estimation of pressure coefficients. The proposed ANN-based methodology is as general and versatile as to be easily expanded to buildings with different shapes as well as to be coupled to building performance simulation and airflow network programs. [ABSTRACT FROM AUTHOR]

Due to the large scale of grid-connected photovoltaic (PV) power generation installations, accurate PV power forecasting is critical to the safe and economic operation of the electric power system. In the paper, by analyzing the influence of external ambient factors and the changing characteristics of PV modules with time, it is found that PV power generation is a nonlinear and time-varying process. This suggests that a certain single forecasting model is inadequate for representing actual generation characteristics, and it is difficult to obtain an accurate forecasting result. An adaptive back propagation (BP) neural network model adopting scrolling time window is proposed to solve the problem. Via an update of the training data of BP neural network with the scrolling time window, the forecasting model adapts to time and a changing external environment with the required modeling precision. Meanwhile, through evaluation of the forecasting performance in different time windows, an optimized time window can be determined to guarantee accuracy. Finally, using the actual operation data of a PV plant in Beijing, the approach is validated as being applicable for PV power forecasting and is able to effectively respond to the dynamic change of the PV power generation process. This improves the forecasting accuracy and also reduces computation complexity as compared with the conventional BP neural network algorithm. [ABSTRACT FROM AUTHOR]

In photovoltaic (PV) modules manufacturer provides rating under standard test conditions (STC). But STC hardly occur under outdoor conditions so it is important to investigate PV power by experimental analysis. In this study extensive literature survey of PV module electrical characteristics by conventional methods and ANN techniques are carried out. It is found that experimental analysis of PV modules maximum power under outdoor conditions remains a major research area. For this measurement of 75 Wp PV module are performed under outdoor conditions at Centre for Energy and Environmental Engineering, National Institute of Technology, Hamirpur, India. To find most influencing variables for PV power prediction, five different sets of parameters are served as inputs to establish five Artificial Neural Network (ANN) models and Multiple Linear Regression (MLR) Models which is novelty of this paper. The results shows that solar radiation and air temperature are found to be most influencing input variables for ANN based prediction of maximum power produced by PV module with mean absolute percentage (MAPE) of 2.15 %. The mean absolute percentage (MAPE) errors for ANN models are found to vary between 2.15 % to 2.55 % whereas for MLR models it varies from 13.04 % to 19.34 %, showing better prediction of ANN models. [ABSTRACT FROM AUTHOR]

This paper presents the results of model predictive control (MPC) using multiple deep neural network (DNN) models for the cooling system of a factory building. The target building accommodates a large space (80 m × 60 m × 9.7 m) and serves cooling via 45 diffusers connected to a direct expansion air handling unit that comprises two air supply fans and four condensing units. The authors developed 10 simulation models using a DNN: One predicts the supply air temperature of the HVAC system, while the others predict the indoor temperature of nine zones. The models can sufficiently predict the thermal behavior of the HVAC system (normalized mean bias error (NMBE): −1.2 %, coefficient of variation of the root mean square error (CVRMSE): 3.8 %) and indoor environment (NMBE: 1.1 %, CVRMSE: 1.3 %). The purpose of the MPC is to minimize the energy consumption of the condensing units while maintaining the cooling set-point temperature. The MPC was applied to the target building for a sampling time of 10 min, for four weeks, from August 23 to September 17, 2021. It was found that energy consumption decreased by 35.1 % compared with the baseline period, while satisfying the cooling set-point temperature maintenance condition. Finally, the authors highlight that the DNN-based MPC is a practical approach sufficient for predicting indoor thermal behavior and has significant potential for energy saving. [ABSTRACT FROM AUTHOR]

Dual fluidized bed steam gasification allows the production of high-value product gas from woody biomass or biogenic residuals. Advanced control concepts such as model predictive control are promising approaches to improve the process performance and efficiency. These control techniques require dynamic models of the process that can predict the plant's behavior as a function of the manipulated variables. This paper presents a gray-box modeling approach based on mass and energy balances to obtain a mathematical description of the temperatures inside the two reactors and the total mass flows leaving the reactors. The model incorporates data-driven components where first-principle modeling is hardly possible with reasonable effort. An artificial neural network is utilized to model the bed material circulation between the two reactors. Experiments were carried out at a 100 kW pilot plant to generate measurement data both for system identification and model validation. Simulations verify that the model achieves reliable predictions for the dual fluidized bed gasification process. [Display omitted] • A gray-box modeling method for dual fluidized bed steam gasification is presented. • A dynamic prediction model for control design is provided. • Data from a 100 kW pilot plant is used for parameter estimation and validation. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents the development of an Artificial Neural Network for the prediction of the wave reflection coefficient from a wide range of coastal and harbor structures. The Artificial Neural Network is trained and validated against an extensive database of about 6000 data, including smooth, rock and armor unit slopes, berm breakwaters, vertical walls, low crested structures, oblique wave attacks. The structure and data included in this database, as well as the approach used in this paper, follow the work done on wave overtopping within the CLASH project. In this new Artificial Neural Network 13 input elements are used to represent the physics of the reflection process taking into account the structure geometry (height, submergence, straight or non-straight slope, with or without berm or toe), the structure type (smooth or covered by an armor layer, with permeable or impermeable core) and the wave attack (water depth, wave height, wave length, wave obliquity, directional spreading). The selection of the input elements and of the algorithms used in the network is described based on an in-depth sensitivity analysis of the network performance. The accuracy of the network is quite satisfactory, being the average root mean squared error lower than 0.04. This value is consistent between the Artificial Neural Network calibrated on the original dataset and the one calibrated on boot-strapped datasets in which data reliability and structure complexity are considered. The performance of the network is compared for limited datasets with selected available literature formulae proving that this approach is able to estimate the experimental reflection coefficients with greater accuracy than the empirical formulae calibrated on these same datasets. [Copyright &y& Elsevier]

Abstract: Accurate predictions of oil production from wells are important for cost-effective operations in the petroleum industry. Such a prediction can assist petroleum engineers in project design, facilities construction scheduling, economic forecasting, and environment management. However, it is difficult to obtain accurate predictions of oil production due to the complex subsurface conditions of reservoirs. Reservoir engineers typically employ curve fitting techniques for predicting primary production of wells based on existing production data. Instead of using this approach, application of some artificial intelligence techniques for production prediction is explored in this paper. The artificial neural network (ANN) approach is a mathematical modeling technique inspired by biological neural networks. The ANN consists of an interconnected group of artificial neurons, which process information via a learning phase between inputs and outputs so as to find patterns in data. A decision tree learning algorithm such as C4.5 usually considers one variable at a time and ignores interdependencies among input attributes, which reduces its model accuracy. On the other hand, an enhanced decision tree learning approach called Neural Decision Tree (NDT) takes interdependencies among input attributes into consideration and generates a decision tree for prediction of petroleum production. This paper presents a comparison of prediction results produced from the three machine intelligence approaches of C4.5 model, NDT model and the ANN model. The results show that the NDT model can significantly improve upon the classification accuracy of the C4.5 algorithm. When compared to the ANN approach, the NDT model has a lower classification rate in general but is better able to describe classes with low number of instances. [Copyright &y& Elsevier]