Search

In this paper, different modeling approaches to the drain current, including analytical and artificial neural network (ANN) modeling, are investigated. The adopted models address the inherent self-heating and kink effects, especially in high-power GaN-based high electron mobility transistors (HEMTs). Different optimization algorithms were demonstrated for extracting the model parameters, including genetic algorithm optimization (GAO), gray wolf optimization (GWO), growth optimization (GO), and particle swarm optimization (PSO). The modeling approaches are applied to DC IV measurements of 1-mm, 4-mm, and 2-mm GaN HEMTs on SiC and Si substrates. An improved optimization procedure was applied to the analytical models to find the main parameters responsible for fitting the general nonlinear behavior of the device. Then, the thermal or self-heating parameters are tuned for best fitting in the high-power dissipation region. The kink effect has been counted by adding another factor to the analytical formula to characterize the voltage dependency of this effect. The ANN modeling provides an efficient and cost-effective solution to accurately simulate the IV characteristics with less effort. In this technique, there is no need for a predefined closed formula or a complicated fitting parameter extraction process. Also, the model training was enhanced by using a genetic algorithm augmented backpropagation technique. The investigated analytical and ANN techniques were demonstrated by modeling the IV characteristics of the considered GaN HEMTs. The results obtained confirm the advantages of using ANN modeling for solving such problems and large-signal modeling applications. [ABSTRACT FROM AUTHOR]

Purpose: Accurate assessment of soil moisture content (SMC) is crucial for applications in climate science, hydrology, ecology, and agriculture. However, conventional SMC characterization and measurement are expensive, time-consuming, and have negative effects on soil. Recently, the application of multispectral technology provides a new idea for SMC accurate detection. The objective of this study was to develop and compare regression and machine learning algorithms to estimate SMC from multispectral images. Materials and methods: A multispectral sensor was used to collect spectral images of 125 soil samples from five distinct soil textures in Shanxi province at varying degrees of soil moisture, ranging from arid to fully saturated. A set of seven spectral parameters was derived from images, and predictive relationships were developed against laboratory-measured SMC. A linear regression (LR) model and a backpropagation neural network model based on genetic algorithm optimization (GA-BP) were compared in this study to predict SMC. Results and discussion: The results showed that (1) the spectral reflectance and SMC exhibit a clear negative correlation, and the lower the SMC, the larger the spectral reflectance is. (2) The GA-BP neural network model exhibits higher prediction accuracy and performance (R2 = 0.978 ~ 0.990, RMSE = 0.366 ~ 0.799%, MAE = 0.360 ~ 0.890%). (3) The GA-BP model exhibits the excellent inversion precision for the fine sand soil (R2 = 0.990, RMSE = 0.518%, MAE = 0.360%). Conclusions: This study introduces an effective methodology for accurate estimation of SMC using multispectral remote sensing technology. It further underscores the significant effectiveness of employing backpropagation neural networks and genetic algorithms in SMC prediction, providing a rapid, precise, non-intrusive, and practical approach towards precision agriculture. [ABSTRACT FROM AUTHOR]

To reduce the amount of energy consumed in wastewater treatment plants, nine methods were used to select the key operation parameters that affected energy consumption according to daily operation records, and an intelligent operation management system based on a genetic algorithm was constructed by mapping the relationships between energy consumption and the key operation parameters. The results showed that the prediction and management of energy consumption could be achieved by incorporating the strengthened elastic genetic algorithm into the extreme gradient boosting model. The main parameters affecting energy consumption were the influent flow rate, effluent total nitrogen, NH4+–N loading rate, etc., and the energy consumption could be reduced by 13–27% (with an average of 22%). The parameters were all selected from the daily operation records of the wastewater treatment plant, and no additional complex data acquisition system was needed to collect specific parameters. This study provided a cost-effective strategy to reduce energy consumption in wastewater treatment plants. [ABSTRACT FROM AUTHOR]

Evolutionary algorithms (EAs) have been used extensively for the optimal design of water distribution networks (WDNs). There is evidence in the literature that search space reduction is highly effective. However, practical methods that do not introduce extra computational requirements are lacking. A dynamic search space reduction methodology is proposed to search the entire solution space without eliminating any part of the search space beforehand. The proposed methodology works on the information explored during the execution of the algorithm. Further, a self-adaptive penalty is suggested which is based on both flow and pressure deficits instead of only pressure deficit and is obtained using pressure dependent analysis. In this study, the methodology is demonstrated using a Genetic Algorithm (GA). The effectiveness of the methodology is demonstrated on the Ramnagar Network of Nagpur City, India and two benchmark problems from the literature. The proposed methodology resulted in a substantial reduction in the computational efforts and provided nine improved solutions as compared to the best solution available in the literature for one of the networks. The techniques proposed are generic and can be incorporated in other EAs. [ABSTRACT FROM AUTHOR]

In this novel bench-top experimental and statistical investigation, the effects of influencing parameters on cellulose extraction have been studied and optimized. Chemically isolated cellulose was used at the optimum condition for the purpose of cellulose nanofiber preparation by deep eutectic solvent (DES) application. For this purpose, the Taguchi method was applied for experimental design. Six parameters which have more signal-to-noise ratio were selected as influencing parameters. These parameters consist of solvent ratio for dewaxing, depectinization pH and time, delignification pH and time, and pH of hemicellulose removal. The effect of these parameters on the cellulose extraction was modeled and optimized by the application of artificial neural network (ANN), coupled with genetic algorithm (GA). The ANN model, by establishing of feedforward backpropagation network with topologies 6, 13, and 1, was applied to model the relation between the extraction condition and cellulose extraction. The results confirmed that the best neural network structure has the ability of cellulose extraction yield prediction with an acceptable level of accuracy. The optimization results show the maximum cellulose extraction would be achieved at the following conditions: pectin extraction time of 1.62 h, delignification time of 2.19 h, the solvent ratio for dewaxing of 0.89 (V/V%), depectinization pH of 2.06, delignification pH of 5.48, and hemicellulose removal pH of 11.36. Under these conditions, the experimental extraction condition yield was 91.7% for cellulose extraction, which matched with the predictive extraction yield of 92.3%. Chemically extracted cellulose at the above condition was applied to prepare cellulose nanofibers. For this purpose, choline chloride–lactic acid–based DES pretreatment was used. The structure of the extracted cellulose and prepared cellulose nanofibers by the application of FTIR, XRD, Fe-SEM, and TEM methods was characterized. The XRD diffractograms alongside with FTIR analyses show that in the extraction process by impurity elimination, the crystallinity index increases. Also, as the characterization results show, by the DES application, glyosidic bonds were cleaved, enhancing the crystallinity and nanofibrilization. [ABSTRACT FROM AUTHOR]

This paper proposes a methodology to detect metals using a drone equipped with a metal detector and programmed by machine learning (ML) models. Our proposed research process could be considered a safe and efficient unmanned mine detection technology for the eventual removal of landmines. Users of this methodology can remotely control the drones without entering the minefield to detect the metal buried and to distinguish whether the metal is mine or not. To realize this idea, we have first stabilized and improved the attitude control of a drone with an attached metal detector by using the micro genetic algorithm-based optimization of proportional–integral–differential control gains. Next, for metal detection, ML models such as a support vector machine and a back-propagation neural network were trained using the annotated dataset. Finally, we have built a controlled drone equipped with a metal detector and trained ML models and experimentally validated our methodology. According to the experimental results, the present study secured the flight stability of the unmanned metal detection drones and the high detection success rate. [ABSTRACT FROM AUTHOR]

Currently, the manufacture of composite structures often requires material removal operations using a cutting tool. Indeed, since biocomposites are generally materials that do not conduct electricity, electro-erosion cannot be utilized. As a result, the processes that can be used not only the unconventional method of abrasive water jet but also conventional machining, such as drilling. Delamination factors (Fd) are widely recognized for controlling the damaged area (delamination) induced by drilling in industry. As discussed in the literature, several approaches are available to evaluate and quantify the delamination surrounding a hole. In this context, the objective of this study is to compare the three Fd evaluation methods that have been most frequently used in previous investigations. To this end, three spindle and feed speeds and three Brad and Spur drills (BSD) tool diameters were selected (L27) for drilling 155-g/m2 density jute fabric–reinforced polyester biocomposites. The desirability function (DF) was further made to optimize the drilling parameters. The response surface methodology (RSM) and artificial neural networks (ANNs) were applied to validate the results obtained experimentally as well as to predict the behavior of the structure depending on the cutting conditions. [ABSTRACT FROM AUTHOR]

Water scarcity is a worldwide concern for Earth citizens. Finding new methods for water concentration is essential for the extension of life. The water issue is more intense in the regions with a warm to the tropical environment. Considering the cooling demand of these regions, which consequently requires excess energy to satisfy the cooling load, having a thermal system to support three concerns of the water, cooling, and power would be the key for the warm/hot weather areas. In the present study, a novel model by integration of gas turbine power cycle with a solar parabolic collector, a steam turbine, heat recovery, steam generator, multi-effect desalination, and absorption chiller is proposed. The suggested model is optimized through developing a comprehensive multi-objective function to maximize the exergy efficiency and minimize the cost. Using the genetic algorithm method, the model is optimized based on six design parameters such as condenser pressure, number of solar parabolic through collector rows, gas turbine and steam turbine inlet temperature, high and low pressure, high- and low-pressure pinch points. The final optimal design point of this cycle enables the overall exergy efficiency of 36.16 % and 188.43 $ h - 1 of the total cost rate value; also, this integrated energy system provides the net electrical generation of 5.18 MW and the cooling load rate of 406.18 KW and generates 2.57 kg s - 1 of desalinated water. In this novel cycle solar energy is used for preheating the inflow of the combustion chamber. A dual pressure heat recovery exploits thermal energy of flue gas, which runs both desalination and multi-effect absorption system and circulates in simultaneous water and cooling load generation. Finally, by utilizing the genetic 1 algorithm, the optimal system is developed. [ABSTRACT FROM AUTHOR]

A design optimization of a slider-crank mechanism (SCM) based upon multiobjective concurrent engineering is presented in this paper. The proposed generalized mathematical model includes geometric equations, kinetic–dynamic expressions, fatigue strength and stability requirements and allows to take into consideration the manufacturing capabilities available. The model also allows for describing the actual mechanism characteristics and can be used directly for the detailed design stage of SCMs, in contrast to the simplified physical models available for preliminary design. Based on this approach, the multiobjective model of SCM which includes 11 variables, seven constrained expressions and the three most important objective functions (total mass, required power and maximum dynamic reaction) was developed. The closed-form analytical expressions were established to the relationship between objective functions, constraints and variables. The correctness of the model was checked by using the finite element method. By using the developed model, the optimization design of the main transmission of a fruit/vegetable washer was carried out. The genetic algorithm optimization has yielded 73 Pareto optimal solutions, and the three most suitable solutions according to the specific manufacturing capability were determined by employing a decision-making process based on the method of successive concessions. Further, a comparative study showed that the solutions obtained by the developed model have excelled the one obtained by means of the experience-based approach. It is noteworthy that the generalized mathematical model and the problem-solving approach adopted in this work can also be used for the SCM synthesis of other mechanical systems. [ABSTRACT FROM AUTHOR]

This article proposes an optimization framework, based on genetic algorithms (GA), to calibrate the constitutive law of von Wolffersdorff. This constitutive law, known as Sand Hypoplasticity (SH), allows for robust and accurate modelling of the soil behaviour but requires a complex calibration involving eight parameters. The proposed optimization can automatically fit these parameters from the results of an oedometric and a triaxial drained compression test, by combining the GA with a numerical solver that integrates the SH in the test conditions. By repeating the same calibration several times, the stochastic nature of the optimizer enables the uncertainty quantification of the calibration parameters and allows studying their relative importance on the model prediction. After validating the numerical solver on the ExCalibre-Laboratory software from the SoilModels' website, the GA calibration is tested on a synthetic dataset to analyse the convergence and the statistics of the results. In particular, a correlation analysis reveals that two couples of the eight model parameters are strongly correlated. Finally, the calibration procedure is tested on the results from von Wolffersdorff, 1996, and Herle and Gudehus, 1999, on the Hochstetten sand. The model parameters identified by the GA optimization improves the matching with the experimental data and hence lead to a better calibration. [ABSTRACT FROM AUTHOR]

This study attempts to develop a high-performance wood plastic composite (WPC) in terms of impact strength, tensile strength, and tensile modulus. For this purpose, a new methodology is offered to find the optimum parameters of WPC including the content of wood flour, compatibilizer (MAPE), and recycled polyethylene terephthalate (RP) for optimizing the impact strength. The WPC samples with different contents of wood flour (30–40 mass%), MAPE (4–12 phr), and RP (0–35 phr) were prepared by melting technique in corotating twin screw extruder. To determine the tensile strength, tensile modulus, and impact strength, the tensile and impact tests were conducted. The significance of each input factor on the outputs was estimated by analysis of variance. The maximization of impact strength considering the tensile strength and modulus as constrains was done by genetic algorithm coupled with the response surface method. The optimum content of wood flour, MAPE, and RP were obtained as 30 mass%, 10 phr, and 25 phr, respectively. [ABSTRACT FROM AUTHOR]

The increase in hydrocarbon production from problematic production zones having high fluid loss and formation damage has led to the emergence of non-damaging drilling fluids (NDDF). Recently, nanotechnology has found a wide array of applications in the oil and gas industry. Most applications of nanotechnology and enhancement in properties of drilling fluids are restricted to bentonite, xanthan gum and a few oil-based mud. In this study, the effects of silica and copper oxide nanoparticles on polyamine-based NDDF and conventional bentonite-based drilling fluids (BDF) were investigated. Silica nanoparticles were prepared using sol–gel method, and copper oxide nanoparticles were synthesized using co-precipitation method. Nano-based drilling fluids were prepared by dispersing nanoparticles in concentrations of 0.5%, 0.8% and 1% by weight. Furthermore, testing of these nano-based drilling fluids was conducted by measuring specific gravity, pH, rheological properties and filtrate loss at surface temperature (room temperature) and then aging it at bottom-hole temperature (80 °C). The addition of silica and copper oxide nanoparticles to both the drilling fluids did not show much effect on pH and specific gravity. Addition of 0.5% concentration of silica nanoparticles in NDDF showed least degradation in rheological properties compared to other fluids. It showed reduction in filtrate loss by 31%. Moreover, silica nanoparticles in conjunction with BDF acted as a mud thinner showing a decrease in viscosity and yield point. On the contrary, when used with NDDFs, silica nanoparticles acted as a mud thickener. Copper oxide nanoparticles behaved as a thinner in both the drilling fluids with a highest reduction in plastic viscosity of 24% for 0.8% of copper oxide nanoparticle in BDF. Thinning properties were enhanced as the doping concentrations of copper oxide nanoparticles increased; however, the fluid loss controlling ability decreased except for 0.5% concentration by 31% and 24% when used with both the drilling fluids. Additionally, optimal Herschel–Bulkley parameters have been determined by using genetic algorithm to minimize the function of sum of squared errors between observed values and model equation. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) is essential for engineers to effectively evaluate structural performance. The accelerometers and strain gauges are commonly used for monitoring and testing structural performance. Placing both types of sensors is the key step for SHM and structural testing. This paper presents the development and application of the sensor placement optimization methods, which have been integrated and implemented in a versatile software tool for maximizing the sensor coverage capacity for structural performance assessment. The sensor placement solutions are optimized using a parallel optimization framework based on the competent genetic algorithm, leading to a number of features that enrich the application flexibility. The developed methods and software tool provide a generic approach for multi-type sensor placement. The integrated tool has been applied to the Indian River Inlet Bridge a large-span cable-stayed bridge to demonstrate and validate the effectiveness of the proposed solution methods for facilitating real world SHM practice. [ABSTRACT FROM AUTHOR]

The replacement of existing pipes is a strategy for the rehabilitation of water distribution networks that is frequently adopted by water companies. Usually, the optimal choice of the pipes diameter is a difficult optimization task, because limited budgets are available. In order to support the selection of a rehabilitation strategy, surrogate reliability measures are often used as an indirect measure of the water distribution system hydraulic performance. Among others, the resilience and entropy indices have attracted considerable interest because they both represent a measure of the network robustness. In the present work, a comparison between these indices is provided in the framework of the optimal rehabilitation of an existing network under limited budget constraint. The resilience and entropy indices are applied to the case of a realistic water distribution network in an extended period simulation framework. Several values of the maximum budget allocable for rehabilitation are considered, and hydraulic calculations are undertaken by means of a pressure driven approach within a modified EPANET 2 environment. The effectiveness of the two surrogate reliability measures is demonstrated by an a-posteriori reliability assessment. [ABSTRACT FROM AUTHOR]

In this comprehensive investigation, we evaluate the mechanical properties and the effect of drilling parameters (spindle speed, 355, 710 and 1400 rev/min; feed rate, 50, 108 and 190 mm/min; and the tool diameter, 5, 7 and 10 mm) as a function of the cutting process on the delamination factor when drilling jute fabrics reinforced epoxy matrix biocomposites. The study is carried out using different drill geometries and material (HSS_TiN, HSS and brad and spur drill bits). The design of experiment is developed by the application analysis of variance (ANOVA). The response surface methodology (RSM) and artificial neural networks (ANN) are applied to validate the results obtained during the experiment and to predict the behaviour of the structure under any cutting condition. Result analysis showed the superiority of the ANN model over the RSM model, while the feed rate had a significant contribution on spindle speed and diameter. The optimum conditions obtained for the Fd factor were a feed rate of 51 mm/min, a spindle speed of 1160 rev/min and a drilling diameter of 5 mm. [ABSTRACT FROM AUTHOR]

In this study, surface structures of two zinc oxide (ZnO) thin films, prepared by sol–gel spin and dip‐coating methods, were investigated. Ex situ Atomic Force Microscopy (AFM), X‐ray diffraction (XRD), and X‐ray reflectivity measurements were carried out in order to study the surface structure. XRD measurements showed nanostructured ZnO thin films with well‐defined orientations. Fractal analysis was applied on the AFM data to illustrate the surface morphology of thin films. Fractal analysis provided a precious depiction of irregularities found in ZnO thin films and revealed that both interface width W and lateral correlation length ξ are strongly affected by coating method. Calculations showed that the film that was prepared by dip‐coating had correlation length, interface width and fractal dimension of 56.2, 2.3, and 2.2 nm, respectively. These parameters for spin‐coated sample were 354.8, 8.5, and 2.64 nm, respectively. Optimization of X‐ray reflectivity by Genetic Algorithm optimization revealed structural parameters of thin films such as surface and interface roughness and thickness of the films. These calculations showed that dip‐coated thin film has a smooth surface, whereas spin‐coated thin film has a rough surface. [ABSTRACT FROM AUTHOR]