Showing papers in "Engineering With Computers in 2020"

A novel hybrid extreme learning machine–grey wolf optimizer (ELM-GWO) model to predict compressive strength of concrete with partial replacements for cement

Abstract: Compressive strength of concrete is one of the most determinant parameters in the design of engineering structures. This parameter is generally determined by conducting several tests at different ages of concrete in spite of the fact that such tests are not only costly but also time-consuming. As an alternative to these tests, machine learning (ML) techniques can be used to estimate experimental results. However, the dependence of compressive strength on different parameters in the fabrication of concrete makes the prediction problem challenging, especially in the case of concrete with partial replacements for cement. In this investigation, an extreme learning machine (ELM) is combined with a metaheuristic algorithm known as grey wolf optimizer (GWO) and a novel hybrid ELM-GWO model is proposed to predict the compressive strength of concrete with partial replacements for cement. To evaluate the performance of the ELM-GWO model, five of the most well-known ML models including an artificial neural network (ANN), an adaptive neuro-fuzzy inference system (ANFIS), an extreme learning machine, a support vector regression with radial basis function (RBF) kernel (SVR-RBF), and another SVR with a polynomial function (Poly) kernel (SVR-Poly) are developed. Finally, the performance of the models is compared with each other. The results of the paper show that combining the ELM model with GWO can efficiently improve the performance of this model. Also, it is deducted that the ELM-GWO model is capable of reaching superior performance indices in comparison with those of the other models.

Application of Chebyshev–Ritz method for static stability and vibration analysis of nonlocal microstructure-dependent nanostructures

Abstract: This research develops a nonlocal couple stress theory to investigate static stability and free vibration characteristics of functionally graded (FG) nanobeams. The theory introduces two parameters based on nonlocal elasticity theory and modified couple stress theory to capture the size effects much accurately. Therefore, a nonlocal stress field parameter and a material length scale parameter are used to involve both stiffness-softening and stiffness-hardening effects on responses of FG nanobeams. The FG nanobeam is modeled via a higher order refined beam theory in which shear deformation effect is verified needless of shear correction factor. A power-law distribution is used to describe the graded material properties. The governing equations and the related boundary conditions are derived by Hamilton’s principle and they are solved applying Chebyshev–Ritz method which satisfies various boundary conditions. A comparison study is performed to verify the present formulation with the provided data in the literature and a good agreement is observed. The parametric study covered in this paper includes several parameters such as nonlocal and length scale parameters, power-law exponent, slenderness ratio, shear deformation and various boundary conditions on natural frequencies and buckling loads of FG nanobeams in detail.

A comprehensive computational approach for nonlinear thermal instability of the electrically FG-GPLRC disk based on GDQ method

Abstract: This is a fundamental study on the buckling temperature and post-buckling analysis of functionally graded graphene nanoplatelet-reinforced composite (FG-GPLRC) disk covered with a piezoelectric actuator and surrounded by the nonlinear elastic foundation. The matrix material is reinforced with graphene nanoplatelets (GPLs) at the nanoscale. The displacement–strain of thermal post-buckling of the FG-GPLRC disk via third-order shear deformation theory and using Von Karman nonlinear plate theory is obtained. The equations of the model are derived from Hamilton’s principle and solved by the generalized differential quadrature method. The direct iterative approach is presented for solving the set of equations that includes highly nonlinear parameters. Finally, the results show that the radius ratio of outer to the inner (Ro/Ri), the geometrical parameter of GPLs, nonlinear elastic foundation, externally applied voltage, and piezoelectric thickness play an essential impact on the thermal post-buckling response of the piezoelectrically FG-GPLRC disk surrounded by the nonlinear elastic foundation. Another important consequence is that, when the effect of the elastic foundation is considered, there is a sinusoidal effect from the Ro/Ri parameter on the thermal post-buckling of the disk and this matter is true for both boundary conditions.

Free vibration and buckling analyses of CNT reinforced laminated non-rectangular plates by discrete singular convolution method

Abstract: This paper presents the free vibration and buckling analyses of functionally graded carbon nanotube-reinforced (FG-CNTR) laminated non-rectangular plates, i.e., quadrilateral and skew plates, using a four-nodded straight-sided transformation method. At first, the related equations of motion and buckling of quadrilateral plate have been given, and then, these equations are transformed from the irregular physical domain into a square computational domain using the geometric transformation formulation via discrete singular convolution (DSC). The discretization of these equations is obtained via two-different regularized kernel, i.e., regularized Shannon’s delta (RSD) and Lagrange-delta sequence (LDS) kernels in conjunctions with the discrete singular convolution numerical integration. Convergence and accuracy of the present DSC transformation are verified via existing literature results for different cases. Detailed numerical solutions are performed, and obtained parametric results are presented to show the effects of carbon nanotube (CNT) volume fraction, CNT distribution pattern, geometry of skew and quadrilateral plate, lamination layup, skew and corner angle, thickness-to-length ratio on the vibration, and buckling analyses of FG-CNTR-laminated composite non-rectangular plates with different boundary conditions. Some detailed results related to critical buckling and frequency of FG-CNTR non-rectangular plates have been reported which can serve as benchmark solutions for future investigations.

Developed comparative analysis of metaheuristic optimization algorithms for optimal active control of structures

Abstract: A developed comparative analysis of metaheuristic optimization algorithms has been used for optimal active control of structures. The linear quadratic regulator (LQR) has ignored the external excitation in solving the Riccati equation with no sufficient optimal results. To enhance the efficiency of LQR and overcome the non-optimality problem, six intelligent optimization methods including BAT, BEE, differential evolution, firefly, harmony search and imperialist competitive algorithm have been discretely added to wavelet-based LQR to seek the attained optimum feedback gains. The proposed approach has not required the solution of Riccati equation enabling the excitation effect in controlling process. Employing this advantage by each of six mentioned algorithms to three-story and eight-story structures under different earthquakes led to define (1) the best solution, (2) convergence rate and (3) computational effort of all methods. The purpose of this research is to study the aforementioned methods besides the superiority of ICA in finding the optimal responses for active control problem. Numerical simulations have confirmed that the proposed controller is enabling to significantly reduce the structural responses using less control energy compared to LQR.

Optimization of ANFIS with GA and PSO estimating α ratio in driven piles

Abstract: This study aimed to optimize Adaptive Neuro-Fuzzy Inferences System (ANFIS) with two optimization algorithms, namely, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) for the calculation friction capacity ratio (α) in driven shafts. Various studies are shown that both ANFIS are valuable methods for prediction of engineering problems. However, optimizing ANFIS with GA and PSO has not been used in the area of pile engineering. The training data set was collected from available full-scale results of the driven piles. The input parameters used in this study were pile diameter (m), pile length (m), relative density (Id), embedment ratio (L/D), both of the pile end resistance (qc) and base resistance at relatively 10% base settlement (qb0.1) from CPT result, whereas the output was α. A learning fuzzy-based algorithm was used to train the ANFIS model in the MATLAB software. The system was optimized by changing the number of clusters in the FIS and then the output was used for the GA and PSO optimization algorithm. The prediction was compared with the real-monitoring field data. As a result, good agreement was attained representing reliability of all proposed models. The estimated results for the collected database were assessed based on several statistical indices such as R2, RMSE, and VAF. According to R2, RMSE, and VAF, values of (0.9439, 0.0123 and 99.91), (0.9872, 0.0117 and 99.99), and (0.9605, 0.0119 and 99.97) were obtained for testing data sets of the optimized ANFIS, GA–ANFIS, and PSO–ANFIS predictive models, respectively. This indicates higher reliability of the optimized GA–ANFIS model in estimating α ratio in driven shafts.

Development of a new hybrid ANN for solving a geotechnical problem related to tunnel boring machine performance

Abstract: Prediction of tunnel boring machine (TBM) performance parameters can be caused to reduce the risks associated with tunneling projects. This study is aimed to introduce a new hybrid model namely Firefly algorithm (FA) combined by artificial neural network (ANN) for solving problems in the field of geotechnical engineering particularly for estimation of penetration rate (PR) of TBM. For this purpose, the results obtained from the field observations and laboratory tests were considered as model inputs to estimate PR of TBMs operated in a water transfer tunnel in Malaysia. Five rock mass and material properties (rock strength, tensile strength of rock, rock quality designation, rock mass rating and weathering zone) and two machine factors (trust force and revolution per minute) were used in the new model for predicting PA. FA algorithm was used to optimize weight and bias of ANN to obtain a higher level of accuracy. A series of hybrid FA-ANN models using the most influential parameters on FA were constructed to estimate PR. For comparison, a simple ANN model was built to predict PR of TBM. This ANN model was improved on the basis of new ways. By doing this, the best ANN model was chosen for comparison purposes. After implementing the best models for two methods, the data were divided into five separate categories. This will minimize the chance of randomness. Then the best models were applied for these new categories. The results demonstrated that new hybrid intelligent model is able to provide higher performance capacity for predicting. Based on the coefficient of determination 0.948 and 0.936 and 0.885 and 0.889 for training and testing datasets of FA-ANN and ANN models, respectively, it was found that the new hybrid model can be introduced as a superior model for solving geotechnical engineering problems.

A computational framework for propagated waves in a sandwich doubly curved nanocomposite panel

Abstract: In the current report, characteristics of the propagated wave in a sandwich structure with a soft core and multi-hybrid nanocomposite (MHC) face sheets are investigated. The higher-order shear deformable theory (HSDT) is applied to formulate the stresses and strains. Rule of the mixture and modified Halpin–Tsai model are engaged to provide the effective material constant of the multi-hybrid nanocomposite face sheets of the sandwich panel. By employing Hamilton’s principle, the governing equations of the structure are derived. Via the compatibility rule, the bonding between the composite layers and a soft core is modeled. Afterward, a parametric study is carried out to investigate the effects of the CNTs' weight fraction, core to total thickness ratio, various FG face sheet patterns, small radius to total thickness ratio, and carbon fiber angel on the phase velocity of the FML panel. The results show that the sensitivity of the phase velocity of the FML panel to the $${W}_{\rm{CNT}}$$ and different FG face sheet patterns can decrease when we consider the core of the panel more much thicker. It is also observed that the effects of fiber angel and core to total thickness ratio on the phase velocity of the FML panel are hardly dependent on the wavenumber. The presented study outputs can be used in ultrasonic inspection techniques and structural health monitoring.

Chaotic simulation of the multi-phase reinforced thermo-elastic disk using GDQM

Abstract: In this research, a mathematical derivation is made to develop a nonlinear dynamic model for the nonlinear frequency and chaotic responses of the multi-scale hybrid nano-composite reinforced disk in the thermal environment and subject to a harmonic external load. Using Hamilton’s principle and the von Karman nonlinear theory, the nonlinear governing equation is derived. For developing an accurate solution approach, generalized differential quadrature method (GDQM) and perturbation approach (PA) are finally employed. Various geometrically parameters are taken into account to investigate the chaotic motion of the viscoelastic disk subject to harmonic excitation. The fundamental and golden results of this paper could be that in the lower value of the external harmonic force, different FG patterns do not have any effects on the motion response of the structure. But, for the higher value of external harmonic force and all FG patterns, the chaos motion could be seen and for the FG-X pattern, the chaosity is more significant than other patterns of the FG. As a practical designing tip, it is recommended to choose plates with lower thickness relative to the outer radius to achieve better vibration performance.

Optimizing ANN models with PSO for predicting short building seismic response

Abstract: The present study aimed to optimize the artificial neural network (ANN) with one of the well-established optimization algorithms called particle swarm optimization (PSO) for the problem of ground response approximation in short structures. Various studies showed that ANN-based solutions are a reliable method for complex engineering problems. Predicting the ground surface respond to seismic loading is one of the engineering problems that still has not received any ANN solution. Therefore, this paper aimed to assess the application of hybrid PSO-based ANN models to the calculation of horizontal deflection of columns in short building after being subjected to a significant seismic loading (e.g., The Chi-Chi earthquake used as one of the input databases). To prepare both of the training and testing datasets, for the ANN and PSO-ANN network models, a series of finite element (FE) modeling were performed. The used FEM simulation database consists of 8324 training datasets and 2081 testing datasets that is equal to 80% and 20% of the whole database, respectively. The input includes Chi-Chi earthquake dynamic time (s), friction angle (φ), dilation angle (ψ), unit weight (γ), soil elastic modulus (E), Poisson’s ratio (v), structure axial stiffness (EA), and bending stiffness (EI) where the output was taken horizontal deflection of the columns at their highest level (Ux). The result indicates higher reliability of the PSO-ANN model in estimating the ground response and horizontal deflection of structural columns in short structures after being subjected to earthquake loading.

A new hybrid grey wolf optimizer-feature weighted-multiple kernel-support vector regression technique to predict TBM performance

Abstract: Full-face tunnel boring machine (TBM) is a modern and efficient tunnel construction equipment. A reliable and accurate TBM performance (like penetration rate, PR) prediction can reduce the cost and help to select the appropriate construction method. Therefore, this study introduces a new hybrid intelligence technique, i.e., grey wolf optimizer-feature weighted-multiple kernel-support vector regression (GWO-FW-MKL-SVR) to predict TBM PR. For this purpose, a tunnel in China was selected as a case study and the most important parameters on TBM performance, i.e., chamber earth pressure, total thrust, cutterhead torque, cutterhead speed, cohesion, internal friction angle, compression modulus, the ratio of boulder, uniaxial compressive strength and rock quality designation, were measured and considered as model inputs. To show the capability of the GWO-FW-MKL-SVR model, three models including biogeography-based optimization (BBO)-FW-MKL-SVR, MKL-SVR, and SVR were also proposed to predict the TBM PR. To select the best predictive models, some performance indices, i.e., coefficient of determination (R2), root mean square error (RMSE) and variance accounted for (VAF) were considered and calculated. The obtained results showed that the GWO-FW-MKL-SVR model receives the highest accuracy in predicting the TBM PR for both train and test stages. R2 values of 0.946 and 0.894, for train and test stages of the GWO-FW-MKL-SVR model, respectively, confirmed that this new hybrid model is considered as a powerful, applicable and simple technique in predicting the TBM PR. By performing feature weight analysis, it was found that the effects of the uniaxial compressive strength, rock quality designation and cutterhead speed features were higher than the other input parameters on the TBM PR.

Analytical modeling of bending and vibration of thick advanced composite plates using a four-variable quasi 3D HSDT

Abstract: This work presents an efficient and original high-order shear and normal deformation theory for the static and free vibration analysis of functionally graded plates. The Hamilton’s principle is used herein to derive the equations of motion. The number of unknowns and governing equations of the present theory is reduced, and hence makes it simple to use. The present plate theory approach accounts for both transverse shear and normal deformations and satisfies the zero traction boundary conditions on the surfaces of the plate without using shear correction factor. Unlike any other theory, the number of unknown functions involved in displacement field is only four, as against five or more in the case of other shear and normal deformation theories. The accuracy of the proposed solution is checked by comparing it with other closed form solutions available in the literature.

Frequency simulation of viscoelastic multi-phase reinforced fully symmetric systems

Abstract: Honeycomb structures have the geometry of the lattice network to allow the minimization of the amount of used material to reach minimal material cost and minimal weight. In this regard, this article deals with the frequency analysis of imperfect honeycomb core sandwich disk with multiscale hybrid nanocomposite (MHC) face sheets rested on an elastic foundation. The honeycomb core is made of aluminum due to its low weight and high stiffness. The rule of the mixture and modified Halpin–Tsai model are engaged to provide the effective material constant of the composite layers. By employing Hamilton’s principle, the governing equations of the structure are derived and solved with the aid of the generalized differential quadrature method (GDQM). Afterward, a parametric study is done to present the effects of the orientation of fibers ( $$\theta_{{\text{f}}} /\pi$$ ) in the epoxy matrix, Winkler–Pasternak constants ( $$K_{{\text{w}}}$$ and $$K_{{\text{p}}}$$ ), thickness to length ratio of the honeycomb network ( $$t_{{\text{h}}} /l_{{\text{h}}}$$ ), the weight fraction of CNTs, value fraction of carbon fibers, angle of honeycomb networks, and inner to outer radius ratio on the frequency of the sandwich disk. The results show that it is true that the roles of $$K_{{\text{w}}}$$ and $$K_{{\text{p}}}$$ are the same as an enhancement, but the impact of $$K_{{\text{w}}}$$ could be much more considerable than the effect of $$K_{{\text{p}}}$$ on the stability of the structure. Additionally, when the angle of the fibers is close to the horizon, the frequency of the system improves.

A Monte Carlo simulation approach for effective assessment of flyrock based on intelligent system of neural network

Abstract: One of the undesirable phenomena in the surface mines, which results in various hazards for human and facilities, is flyrock. It seems that the careful study of the subject and its effects on the environment can affect the control of flyrock hazards in the studied area. Therefore, the use of intelligent models and methods which are capable of predicting and simulating the risk of flyrock can be considered as an appropriate solution in this regard. The current research was conducted using nonlinear models and Monte Carlo (MC) simulation. The data used in this study consist of 260 samples of rock thrown from a mine in Malaysia. The parameters used in these models include hole’s diameter (D), hole’s depth (HD), burden to spacing (BS), stemming (ST), maximum charge per delay (MC), and powder factor (PF). At first, multiple regression analysis (MRA) and artificial neural network (ANN) models were used in order to develop a non-linear relationship between dependent and independent parameters. The ANN model was an appropriate predictor of flyrock in the mine. Then using the best implemented model of ANN, the flyrock environmental phenomenon was simulated using MC technique. MC simulation showed a proper level of accuracy of flyrock ranges in the mine. Using this simulation, it can be concluded with 90% accuracy that the Flyrock phenomenon does not exceed 331 m. Under these conditions, this simulation can be used for various areas requiring risk assessment. Finally, a sensitive analysis was carried out on data. This analysis showed MC has the greatest effect on flyrock.

Dynamic Gaussian bare-bones fruit fly optimizers with abandonment mechanism: method and analysis

Abstract: The Fruit Fly Optimization Algorithm (FOA) is a recent algorithm inspired by the foraging behavior of fruit fly populations. However, the original FOA easily falls into the local optimum in the process of solving practical problems, and has a high probability of escaping from the optimal solution. In order to improve the global search capability and the quality of solutions, a dynamic step length mechanism, abandonment mechanism and Gaussian bare-bones mechanism are introduced into FOA, termed as BareFOA. Firstly, the random and ambiguous behavior of fruit flies during the olfactory phase is described using the abandonment mechanism. The search range of fruit fly populations is automatically adjusted using an update strategy with dynamic step length. As a result, the convergence speed and convergence accuracy of FOA have been greatly improved. Secondly, the Gaussian bare-bones mechanism that overcomes local optimal constraints is introduced, which greatly improves the global search capability of the FOA. Finally, 30 benchmark functions for CEC2017 and seven engineering optimization problems are experimented with and compared to the best-known solutions reported in the literature. The computational results show that the BareFOA not only significantly achieved the superior results on the benchmark problems than other competitive counterparts, but also can offer better results on the engineering optimization design problems.

A sequential constraints updating approach for Kriging surrogate model-assisted engineering optimization design problem

Abstract: Kriging surrogate model has been widely used in engineering design optimization problems to replace computational cost simulations. To facilitate the usage of the Kriging surrogate model-assisted engineering optimization design, there are still challenging issues on the updating of Kriging surrogate model for the constraints, since there exists prediction error between the Kriging surrogate model and the real constraints. Ignoring the interpolation uncertainties from the Kriging surrogate model of constraints may lead to infeasible optimal solutions. In this paper, general sequential constraints updating approach based on the confidence intervals from the Kriging surrogate model (SCU-CI) are proposed. In the proposed SCU-CI approach, an objective switching and sequential updating strategy is introduced based on whether the feasibility status of the design alternatives would be changed because of the interpolation uncertainty from the Kriging surrogate model or not. To demonstrate the effectiveness of the proposed SCU-CI approach, nine numerical examples and two practical engineering cases are used. The comparisons between the proposed approach and five existing approaches considering the quality of the obtained optimum and computational efficiency are made. Results illustrate that the proposed SCU-CI approach can generally ensure the feasibility of the optimal solution under a reasonable computational cost.

Shear strength of SFRCB without stirrups simulation: implementation of hybrid artificial intelligence model

Abstract: Recent developments on shear strength (Vf) of steel fiber-reinforced concrete beam (SFRCB) simulation have been shifted to the implementation of the computer aid advancements. The current study is attempted to explore new hybrid artificial intelligence (AI) model called integrative support vector regression with firefly optimization algorithm (SVR-FFA) for shear strength prediction of SFRCB. The developed hybrid predictive model is constructed using laboratory experimental data set gathered from the literature and belongs to the shear failure capacity. The related beam dimensional and concrete properties are utilized as input attributes to predict Vf. The proposed SVR-FFA model is validated against classical SVR model and eight empirical formulations obtained from published researches. The attained results of the proposed hybrid AI model exhibited a reliable resultant performance in terms of prediction accuracy. Based on the examined root-mean-square error (RMSE) and the correlation coefficient (R2) over the testing phase, SVR-FFA achieved (RMSE ≈ 0.25 MPa) and (R2 ≈ 0.96).

A new fusion of salp swarm with sine cosine for optimization of non-linear functions

Abstract: The foremost objective of this article is to develop a novel hybrid powerful meta-heuristic that integrates the salp swarm algorithm with sine cosine algorithm (called HSSASCA) for improving the convergence performance with the exploration and exploitation being superior to other comparative standard algorithms. In this method, the position of salp swarm in the search space is updated using the position equations of sine cosine; hence the best and possible optimal solutions are obtained based on the sine or cosine function. During this process, each salp adopts the information sharing strategy of sine and cosine functions to improve their exploration and exploitation ability. The inspiration behind incorporating changes in salp swarm optimizer algorithm is to assist the basic approach to avoid premature convergence and to rapidly guide the search towards the probable search space. The algorithm is validated on 22 standard mathematical optimization functions and 3 applications namely the 3-bar truss, tension/compression spring and cantilever beam design problems. The aim is to examine and confirm the valuable behaviors of HSSASCA in searching the best solutions for optimization functions. The experimental results reveal that HSSASCA algorithm achieves the highest accuracies with least runtime in comparison with the others.

Prediction of ultimate bearing capacity through various novel evolutionary and neural network models

Abstract: In the current study, various evolutionary artificial intelligence and machine learning models namely, optimized artificial neural network (ANN), genetic algorithm optimized with ANN (GA-ANN) and particle swarm optimization optimized with ANN (PSO-ANN), differential evolution algorithm (DEA), adaptive neuro-fuzzy inference system (ANFIS), general regression neural network (GRNN), and feedforward neural network (FFNN) were optimized and applied to predict the ultimate bearing capacity (Fult) of shallow footing on two-layered soil condition. Due to a lot of input variables such as (upper layer thickness/foundation width (h/B) ratio, footing width (B), top and bottom soil layer properties) finding a reliable solution for such a complex engineering problem is difficult. Most of the available solutions are based on very limited experimental works. To assess the capability of proposed methods a new ranking system called CER (color intensity rating) based on their result of above indices was developed. As a result, although all provided methods, after being optimized, could successfully predict the bearing capacity of shallow footing in the two-layer subsoil and PSO-ANN could perform better compared to other techniques. Based on RMSE, R2 and VAF, values of (0.01, 0.99, and 99.90) and (0.01, 0.99, and 99.90) were found, respectively, for the training and testing datasets of PSO-ANN model. In this regard, the accuracy of other hybrid algorithm of GA-ANN model with RMSE, R2 and VAF of (0.05, 0.99, and 97.80) and (0.06, 0.99, and 97.57), respectively, for the training and testing datasets was slightly lower than the PSO-ANN model. This shows the superiority of the PSO-ANN model in the prediction of a highly complex real-world engineering problem.

Chaotic oppositional sine–cosine method for solving global optimization problems

Abstract: This study proposed an improved sine–cosine algorithm (SCA) for global optimization tasks. The SCA is a meta-heuristic method ground on sine and cosine functions. It has found its application in many fields. However, SCA still has some shortcomings such as weak global search ability and low solution quality. In this study, the chaotic local search strategy and the opposition-based learning strategy are utilized to strengthen the exploration and exploitation capability of the basic SCA, and the improved algorithm is called chaotic oppositional SCA (COSCA). The COSCA was validated on a comprehensive set of 22 benchmark functions from classical 23 functions and CEC2014. Simulation experiments suggest that COSCA’s global optimization ability is significantly improved and superior to other algorithms. Moreover, COSCA is evaluated on three complex engineering problems with constraints. Experimental results show that COSCA can solve such problems more effectively than different algorithms.

Optimizing an ANN model with genetic algorithm (GA) predicting load-settlement behaviours of eco-friendly raft-pile foundation (ERP) system

Abstract: Eco-friendly raft-pile foundation (ERP) system is one of the most recent developed types of pile foundations that the original materials can be provided from local Bakau. A precise prediction of its behaviour is of interest for many engineers. This paper presents three intelligent systems, namely, adaptive neuro-fuzzy inference system (ANFIS), conventional artificial neural network (ANN), and optimized ANN model with genetic algorithm (GA) for prediction of vertical settlement in ERP system. In this regard, a database compiled from 43 load-settlement results obtained from full-scale maintained load test (PLT). Note that, these floating raft-pile system piles were subjected to vertical axial loading. The ERP system was installed at the marine soft clay soil site at Rantau Panjang Kapar, Selangor, Malaysia. The values of subgrade modulus (Ks), Young’s modulus (Es), soil properties beneath the footing, and applied load were set as model input to predict vertical settlement (s). To evaluate the reliability of the network output, several well-known statistical indexes were used. The results show that the new proposed GA-ANN model could provide a better performance in estimating the maximum settlement of ERP system. In terms of statistical indexes (R2, and RMSE), the values of (0.998, 0.0259, and 99.99) and (0.997, 0.0324, and 99.998) were obtained for both data sets of training and testing, respectively. Besides, comparing the training and testing data sets, R2 values of (0.994, 0.9884, 0.995, and 0.9984) and (0.996, 0.985, 0.994, and 0.9973) were found for ANN–LMBP, ANFIS, GA, and GA-ANN models, respectively, which proves the superiority of the proposed GA-ANN model comparing to other methods.

The use of new intelligent techniques in designing retaining walls

Abstract: The stability of retaining walls against overturning is analyzed in this study using artificial intelligence methods. Five input parameters including wall height, wall thickness, soil friction angle, soil density, and stone cement mixture density were varied and 2000 cases were considered in developing the predictive models. Using the artificial neural network (ANN) method, eight prediction models were developed and evaluated based on the coefficient of determination (R2) and the root mean square error. R2 values of 0.9740 and 0.9824 for training and testing datasets, respectively (for the best model), indicate the level of ANN capability in predicting safety factor (SF) of retaining walls. After developing the ANN model, the ant colony optimization (ACO) algorithm was used to maximize the safety factor of the wall by varying the input parameters. In fact, the best ANN model was selected to be used as a modeling function in ACO algorithm. The SF result from optimization section was obtained as 3.057 which show a significant difference from the mean SF values used in the modeling. It can be concluded that ACO may be used as a powerful optimization algorithm in optimizing SF results of retaining walls.

Reinforced concrete deep beam shear strength capacity modelling using an integrative bio-inspired algorithm with an artificial intelligence model

Abstract: The design and sustainability of reinforced concrete deep beam are still the main issues in the sector of structural engineering despite the existence of modern advancements in this area. Proper understanding of shear stress characteristics can assist in providing safer design and prevent failure in deep beams which consequently lead to saving lives and properties. In this investigation, a new intelligent model depending on the hybridization of support vector regression with bio-inspired optimization approach called genetic algorithm (SVR-GA) is employed to predict the shear strength of reinforced concrete (RC) deep beams based on dimensional, mechanical and material parameters properties. The adopted SVR-GA modelling approach is validated against three different well established artificial intelligent (AI) models, including classical SVR, artificial neural network (ANN) and gradient boosted decision trees (GBDTs). The comparison assessments provide a clear impression of the superior capability of the proposed SVR-GA model in the prediction of shear strength capability of simply supported deep beams. The simulated results gained by SVR-GA model are very close to the experimental ones. In quantitative results, the coefficient of determination (R2) during the testing phase (R2 = 0.95), whereas the other comparable models generated relatively lower values of R2 ranging from 0.884 to 0.941. All in all, the proposed SVR-GA model showed an applicable and robust computer aid technology for modelling RC deep beam shear strength that contributes to the base knowledge of material and structural engineering perspective.

A multi-strategy enhanced salp swarm algorithm for global optimization

Abstract: As a typical nature-inspired swarm intelligence algorithm, because of the simple framework and good optimization performance, salp swarm algorithm (SSA) has been extensively applied to a lot of practical problems. Nevertheless, when facing a number of complicated optimization problems, particularly the high dimensionality and multi-dimensional problems, SSA will come to stagnation and decrease the optimal performance. To tackle this problem, this paper presents an enhanced SSA (ESSA) in which several strategies, including orthogonal learning, quadratic interpolation, and generalized oppositional learning are embedded to boost the global exploration and local exploitation performance of SSA. Orthogonal learning can help the worse salp break away from local optima, while quadratic interpolation is utilized to improve the accuracy of the global optimal through local search near the globally optimal solution. Also, generalized oppositional learning is used to improve the population quality through the initialization step and generation jumping. These strategies work together to assist SSA in promoting convergence performance. At the last CEC2017 benchmark suite and CEC2011, a real-world optimization benchmark is employed to estimate the property of ESSA in dealing with the high dimensionality and multi-dimensional problems. Three constrained engineering optimization problems are also used to assess the capability of ESSA in tackling practical engineering application problems. The experimental results and responding analysis make clear that the presented algorithm significantly outperforms the original SSA and other state-of-the-art methods.

Stochastic paint optimizer: theory and application in civil engineering

Abstract: This paper presents an art-inspired optimization algorithm, which is called Stochastic Paint Optimizer (SPO). The SPO is a population-based optimizer inspired by the art of painting and the beauty of colors plays the main role in this algorithm. The SPO, as an optimization algorithm, simulates the search space as a painting canvas and applies a different color combination for finding the best color. Four simple color combination rules without the need for any internal parameter provide a good exploration and exploitation for the SPO. The performance of the algorithm is evaluated by twenty-three mathematical well-known benchmark functions, and the results are verified by a comparative study with recent well-studied algorithms. In addition, a set of IEEE Congress of Evolutionary Computation benchmark test functions (CEC-C06 2019) are utilized. On the other hand, the Wilcoxon test, as a non-parametric statistical test, is used to determine the significance of the results. Finally, to prove the practicability of the SPO, this algorithm is applied to four different structural design problems, known as challenging problems in civil engineering. The results of all these problems indicate that the SPO algorithm is able to provide very competitive results compared to the other algorithms.

A new methodology for optimization and prediction of rate of penetration during drilling operations

Abstract: Predictive models have been widely used in different engineering fields, as well as in petroleum engineering. Due to the development of high-performance computer systems, the accuracy and complexity of predictive models have been increased significantly. One of the common methods for prediction is artificial neural network (ANN). ANN models in combination with optimization algorithms provide a powerful and fast tool for the prediction and optimization of processes which take a large amount of time if they are simulated using common simulation technics. In the present paper, to predict penetration rate during drilling process, several ANN models were developed based on the data obtained from drilling of a gas well located in south of Iran. Regarding the R2 and RMSE values of the developed models, the best model was selected for prediction of penetration rate. In the next step, artificial bee colony algorithm was used for optimization of the parameters which are effective on rate of penetration (ROP). Results showed that the model is accurate enough for being used in the prediction and optimization of ROP in drilling operations.

Novel approach to predicting blast-induced ground vibration using Gaussian process regression

Abstract: An attempt has been made to propose a novel prediction model based on the Gaussian process regression (GPR) approach. The proposed GPR was used to predict blast-induced ground vibration using 210 blasting events from an open pit mine in Ghana. Out of the 210 blasting data, 130 were used in the model development (training), whereas the remaining 80 were used to independently assess the performance of the GPR model. The formulated GPR model was compared with the other standard predictive techniques such as the generalised regression neural network, radial basis function neural network, back-propagation neural network, and four conventional ground vibration predictors (United State Bureau of Mines model, Langefors and Kihlstrom model, Ambraseys–Hendron model, and Indian Standard model). Comparatively, the statistical results revealed that the proposed GPR approach can predict ground vibration more accurately than the standard techniques presented in this study. The GPR had the highest correlation coefficient (R), variance accounted for, and the lowest values of the statistical error indicators (mean absolute error and root-mean-square error) applied. The superiority of GPR to the other methods is explained by the ability of the GPR to quantitatively model the noise patterns in the blasting data events adequately. The study will serve as a foundation for future research works in the mining industry where artificial intelligence technology is yet to be fully explored.

Novel approach for forecasting the blast-induced AOp using a hybrid fuzzy system and firefly algorithm

Abstract: Air overpressure (AOp) produced by blasting is one of the environmental hazards of mining operations. Accordingly, the accurate prediction of AOp is very important, and this issue requires the application of appropriate prediction models. With this in view, this paper aims to propose a new data-driven model in the prediction of AOp using a hybrid model of fuzzy system (FS) and firefly algorithm (FA). This combination is abbreviated as FS-FA model. The used data-sets in the proposed FS-FA model were arranged in a format of three input parameters. In total, 86 sets of the mentioned parameters were prepared. To avoid over-fitting, the data-sets were divided into two parts of training (80%) and test sets (20%). Three quantitative standard statistical performance evaluation measures, variance account for (VAF), coefficient correlation (R2) and root mean squared error (RMSE), were used to check the accuracy of the FS-FA model. According to the results, the R2 and RMSE values obtained from the proposed FS-FA model were equal to 0.977 and 1.241 (for testing phase), respectively, which clearly demonstrate the merits of the proposed FS-FA model. In other words, the obtained R2 and RMSE show that FS-FA model has high prediction level in the modeling of blast-induced AOp.

Influence of axial load function and optimization on static stability of sandwich functionally graded beams with porous core

Abstract: Static stability of beams subjected to nonuniform axial compressive and shear loads is essential in many industrial applications, such as aircraft, automotive, mechanical, civil and naval. Thus, this article tends to investigate and optimize critical buckling loads of thin/thick sandwich functionally graded (FG) beam with porous core, for the first time. The proposed model is developed to consider a sandwich beam with three layers, which has top and bottom FG layers reinforced by single-walled carbon nanotubes (SWCNTs) and core porous layer with various porosity distributions. The variable in-plane compressive load is described by different distributed functions. Parabolic higher-order shear deformation theory of Reddy is adopted to describe kinematic displacement field and consider both thin and thick structures. The equilibrium governing variable-coefficient differential equations are obtained in detail by generalized variational principle. Equilibrium equations are solved numerically by differential quadrature method to get critical buckling loads. Numerical results are illustrated to examine influences of porosity function, porosity percentage, distribution gradation index, load types and boundary conditions on buckling loads of sandwich FG SWCNTs beam with porous core. Particle swarm optimization algorithm is adopted to get optimal axial load function.

Evaluation of rockburst occurrence and intensity in underground structures using decision tree approach

Abstract: Based on reported statistics, rockburst phenomenon is the main cause of many casualties and accidents occurred during the construction of deep underground structures. Therefore, its prediction in initial stages of design has a remarkable role on enhancement of safety. In this paper, two models have been developed for rockburst evaluation using the C5.0 decision tree classifier. The first model has been applied for prediction of rockburst occurrence and the second model for prediction of rockburst intensity. These models have been developed based on a database including 174 rockburst case histories. In both models, stress coefficient, rock brittleness coefficient, and the elastic strain energy index are the predictive variables. These models are easy to use and do not require extensive knowledge. Based on decision rules derived from these models, the rockburst occurrence and intensity can be evaluated easily. The results revealed that the proposed approach is a useful and robust technique for long-term prediction of rockburst.