Search

Pipeline pressure drops can be decreased by various methods. Utilizing small amounts of additives that named drag reducing agent (DRA) in pipelines with crude oil may reduce the friction caused by fluid. It highlights the importance of accurate approximation of drag reduction (DR). In this work, the performance of artificial neural network (ANN) in forecasting DR in crude oil pipelines was enhanced using artificial bee colony (ABC) and particle swarm optimization (PSO) algorithms. To this end, we considered Reynolds number, concentration of DRA, type of DRA, temperature, and kind of pipe as the DR influential factors. Using 80:20 ratios for determining the training and testing data, each model performed with its optimal parameters. Three accuracy criteria of coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) were used to evaluate their efficiency. Based on the results, applying ABC and PSO evolutionary algorithm leads to increasing R2 from 0.9487 to 0.9743 and 0.9806 in the training phase, and from 0.9584 to 0.9795 and 0.9835 in the testing phase. Moreover, a considerable decrease was observed for the RMSE (30% and 36%) and MAE (31% and 38%) in the testing stage. [ABSTRACT FROM AUTHOR]

Balancing the exploration and exploitation in any nature-inspired optimization algorithm is an essential task, while solving the real-world global optimization problems. Therefore, the search agents of an algorithm always try to explore the unvisited domains of a search space in a balanced manner. The sine cosine algorithm (SCA) is a recent addition to the field of metaheuristics that finds the solution of an optimization problem using the behavior of sine and cosine functions. However, in some cases, the SCA skips the true solutions and trapped at sub-optimal solutions. These problems lead to the premature convergence, which is harmful in determining the global optima. Therefore, in order to alleviate the above-mentioned issues, the present study aims to establish a comparatively better synergy between exploration and exploitation in the SCA. In this direction, firstly, the exploration ability of the SCA is improved by integrating the social and cognitive component, and secondly, the balance between exploration and exploitation is maintained through the grey wolf optimizer (GWO). The proposed algorithm is named as SC-GWO. For the performance evaluation, a well-known set of benchmark problems and engineering test problems are taken. The dimension of benchmark test problems is varied from 30 to 100 to observe the robustness of the SC-GWO on scalability of problems. In the paper, the SC-GWO is also used to determine the optimal setting for overcurrent relays. The analysis of obtained numerical results and its comparison with other metaheuristic algorithms demonstrate the superior ability of the proposed SC-GWO. [ABSTRACT FROM AUTHOR]

Early assessment of the energy performance of buildings (EPB) is focused in this study. This task is carried out by predicting the cooling load (CL) in a residential building. To this end, due to the drawbacks of neural computing approaches (e.g., local minima), a novel metaheuristic technique, namely teaching–learning-based optimization (TLBO) is employed to modify a multi-layer perceptron neural network (MLPNN). The complexity of the proposed model is also optimized by a trial and error process. Evaluating the results revealed a high efficiency for this scheme. In this sense, the prediction error of the MLPNN was reduced by around 20%, and the correlation between the measured and forecasted CLs rose from 0.8875 to 0.9207. It was also deduced that the TLBO outperforms two benchmark optimizers of cuckoo optimization algorithm (COA) and league championship algorithm (LCA) in terms of both modeling accuracy and network complexity. Moreover, the TLBO-MLP emerged as the most time-effective hybrid as it required considerably lower computation time than COA-MLP and LCA-MLP. Regarding these advantages, the proposed model can be promisingly used for early assessment of EPB in practice. [ABSTRACT FROM AUTHOR]

The present work aimed to evaluate and optimize the design of an artificial neural network (ANN) combined with an optimization algorithm of genetic algorithm (GA) for the calculation of slope stability safety factors (SF) in a pure cohesive slope. To make datasets of training and testing for the developed predictive models, 630 finite element limit equilibrium (FELE) analyses were performed. Similar to many artificial intelligence-based solutions, the database was involved in 189 testing datasets (e.g., 30% of the entire database) and 441 training datasets; for example, a range of 70% of the total database. Moreover, variables of multilayer perceptron (MLP) algorithm (for example, number of nodes in any hidden layer) and the algorithm of GA like population size was optimized by utilizing a series of trial and error process. The parameters in input, which were used in the analysis, consist of slope angle (β), setback distance ratio (b/B), applied stresses on the slope (Fy) and undrained shear strength of the cohesive soil (Cu) where the output was taken SF. The obtained network outputs for both datasets from MLP and GA-MLP models are evaluated according to many statistical indices. A total of 72 MLP trial and error (e.g., parameter study) the optimal architecture of 4 × 8 × 1 were determined for the MLP structure. Both proposed techniques result in a proper performance; however, according to the statistical indices, the GA–MLP model can somewhat accomplish the least mean square error (MSE) when compared to MLP. In an optimized GA–MLP network, coefficient of determination (R2) and root mean square error (RMSE) values of (0.975, and 0.097) and (0.969, and 0.107) were found, respectively, to both of the normalized training and testing datasets. [ABSTRACT FROM AUTHOR]

Recycled aggregate concrete is used as an alternative material in construction engineering, aiming to environmental protection and sustainable development. However, the compressive strength of this concrete material is considered as a crucial parameter and an important concern for construction engineers regarding its application. In the present work, the 28-days compressive strength of recycled aggregate concrete is investigated through four artificial intelligence techniques based on a meta-heuristic search of sociopolitical algorithm (i.e. ICA) and XGBoost, called the ICA-XGBoost model. Based on performance indices, the optimum among these developed models proved to be ICA-XGBoost model. Namely, findings demonstrated that the proposed ICA-XGBoost model performed better than the other models (i.e. ICA-ANN, ICA-SVR, and ICA-ANFIS models) in estimating compressive strength of recycled aggregate concrete. The suggested model can be used in construction engineering in order to ensure adequate mechanical performance of the recycled aggregate concrete and allow its safe use for building purposes. [ABSTRACT FROM AUTHOR]

In this article, thermal buckling and frequency analysis of a size-dependent laminated composite cylindrical nanoshell in thermal environment using nonlocal strain–stress gradient theory are presented. The thermodynamic equations of the laminated cylindrical nanoshell are based on first-order shear deformation theory, and generalized differential quadrature element method is implemented to solve these equations and obtain natural frequency and critical temperature of the presented model. The results show that by considering C–F boundary conditions and every even layers' number, in lower value of length scale parameter, by increasing the length scale parameter, the frequency of the structure decreases but in higher value of length scale parameter this matter is inverse. Finally, influences of temperature difference, ply angle, length scale and nonlocal parameters on the critical temperature and frequency of the laminated composite nanostructure are investigated. [ABSTRACT FROM AUTHOR]

Recent studies have demonstrated the high efficiency of metaheuristic algorithms for various optimization engineering problems. The main focus of the present study is to apply a novel notion of stochastic search methods, namely evaporation rate-based water cycle algorithm (ER-WCA) to the problem of soil shear strength (SSS) prediction. The ER-WCA, as the name indicates, is a modified version of the water cycle algorithm that is used to computationally modify an artificial neural network (ANN) for the mentioned purpose. The sensitivity analysis showed that the most proper values for the number of rivers + sea and the population size are 5 and 300, respectively. The performance of the ER-WCA–ANN hybrid is compared to an ANN typically trained by the Levenberg–Marquardt algorithm to evaluate the effectiveness of the proposed metaheuristic technique. The findings showed that incorporation of the ER-WCA results in reducing the root-mean-square error by 5.87% and 4.92% in the training and testing phases, respectively. Meanwhile, the coefficient of determination rose from 84.27 to 86.11% and from 78.80 to 80.83% in these phases. It indicates that the weights and biases suggested by the ER-WCA can construct a considerably more reliable ANN. Therefore, the introduced method is recommended for practical uses in the early prediction of the SSS in civil engineering projects. [ABSTRACT FROM AUTHOR]

Due to the rapid development of process manufacturing, composite materials with graphene-reinforcement have obtained commercially notices in promoted engineering applications. For this regard, vibrational characteristics of a cylindrical nanoshell reinforced by graphene nanoplatelets (GPL) and coupled with piezoelectric actuator (PIAC) is investigated. Also, the nanostructure is embedded in a viscoelastic medium. The material properties of piece-wise graphene-reinforced composite (GPLRC) are assumed to be graded in the thickness direction of a cylindrical nanoshell and estimated through a nanomechanical model. For the first time in the current study is considering the effects of piezoelectric layer, viscoelastic foundation, GPLRC, and size-effects on the frequency responses of the GPLRC cylindrical nanoshell coupled with PIAC and by assuming perfect bonding between the core (GPLRC cylindrical shell) and the piezoelectric layer. The governing equations and boundary conditions have been developed using minimum potential energy and solved with the aid of the generalized differential quadrature method. In addition, because of piezoelectric layer, Maxwell's equation is derived. The results show that viscoelastic foundation, piezoelectric layer, GPL distribution pattern, length scale parameter and GPL weight function have important role in the frequency characteristics of the GPLRC cylindrical nanoshell coupled with PIAC and surrounded by viscoelastic foundation. The results of the current study are useful suggestions for design of materials science, micro-electro-mechanical systems, and nanoelectromechanical systems such as nanoactuators and nanosensors. Communicated by Francesco Tornabene. [ABSTRACT FROM AUTHOR]

In developing countries, evaluating irrigation water quality using conventional methods can be costly and time-consuming. To overcome these challenges, this study explores the potential of utilizing physical parameters and artificial intelligence (AI) models for predicting and evaluating the quality indicators of irrigation water in aquifer systems. To achieve this goal, novel hybrid methods, namely the Whale Optimization Algorithm (WOA) and Wind-Driven Optimization (WDO), are employed in conjunction with Artificial Neural Network (ANN) models. The specific objective of this study is to forecast the Sodium Adsorption Ratio (SAR) by considering independent variables such as Na+, Mg2+, Ca2+, Na percent, K+, SO42−, Cl−, pH, and HCO3−. A dataset of 540 samples from the Shiraz plain, collected over a statistical period of 16 years (2002–2018), is used to estimate the groundwater quality variables. A pre-processing technique is applied in the AI approach to enhance the model's efficiency. The results indicate that the WDO-ANN model exhibits higher accuracy (R2 = 0.9983 and RMSE = 0.10618) than the WOA-ANN model (R2 = 0.9957 and RMSE = 0.16957). The optimization of computational parameters and comparison of AI model structures demonstrate that the WDO-ANN model outperforms the WOA-ANN model in predictive ability. In general, using AI models as a tool for low-cost and timely prediction of underground water quality using physical parameters as input variables has a high potential. [ABSTRACT FROM AUTHOR]

Landslides, the most significant geohazards in Iran, adversely affect the region's socioeconomic conditions and the environment. Landslide susceptibility mapping is crucial for proactive risk management, sustainable development, and protecting human lives, infrastructure, and the environment. It enables decision-makers to make informed choices, implement appropriate mitigation measures, and plan for potential landslide events, leading to safer and more resilient communities. Using a recommended subdivision methodology, this research has developed a landslide susceptibility map for a significant Gilan, Iran region. The production of the map involved utilizing an artificial neural network (ANN) model. This model incorporated sixteen causal components from several characteristics, including topographic and geomorphologic features, geological factors, land use patterns, hydrological aspects, and hydrogeological properties. Three hundred seventy instances were identified using multiple verified sources and analyzing aerial photographs to create the landslide inventory map. Examining and verifying the weights assigned to the causal elements were conducted per accepted mathematical standards, incorporating sensitivity analysis, earlier research, and empirical data on landslides. The area under the receiver operating characteristic curve (AUROC) was used to compare the various models. The study's findings indicated that the best swarm size value for COA-MLP 1 1 Cuckoo Optimization Algorithm (COA). is equal to 450, and the accuracy indices for this algorithm were 0.998 and 0.995 in training and testing datasets, respectively. Similarly, the AUC 2 2 Area under the curve (AUC). for the HS-MLP, 3 3 Harmony Search Algorithm (HS). SFS-MLP, 4 4 Stochastic Fractal Search (SFS). and TLBO-MLP 5 5 Teaching- Learning-Based Optiization (TLBO). were 0.997, 0.999, and 0.999 in training and 0.995, 0.996, and 0.995 in the testing dataset, respectively. Therefore, the use of optimization algorithms leads to an increase in the performance and accuracy of the neural network, and the high accuracy of the SFS-MLP model demonstrates the existence of a dependable criterion for delineating the susceptibility zones about forthcoming landslide occurrences. The model is a cost-effective and potentially indispensable tool for urban planners in growing cities and municipalities. Its effectiveness is demonstrated by comparisons with previous susceptibility analyses conducted in the region. [ABSTRACT FROM AUTHOR]