Metaheuristic Bat Algorithm Research Articles

Exploring Fault Plane Geometry through Metaheuristic Bat Algorithm (MBA) Analysis of Potential Field Data: Environmental and Engineering Applications

Exploring Fault Plane Geometry through Metaheuristic Bat Algorithm (MBA) Analysis of Potential Field Data: Environmental and Engineering Applications

Monthly streamflow prediction using hybrid extreme learning machine optimized by bat algorithm: a case study of Cheliff watershed, Algeria

ABSTRACT In the present paper, we propose a new approach for monthly streamflow prediction based on the extreme learning machine (ELM) and the metaheuristic bat algorithm (Bat-ELM). The performance of the Bat-ELM was compared to that of ELM, support vector regression (SVR), Gaussian process regression (GPR), multilayer perceptron neural network (MLPNN), and generalized regression neural network (GRNN). The proposed models were applied using data from three hydrometric stations located in the Cheliff Basin, Algeria. The results showed that the Bat-ELM was more satisfactory than the standalone models. The Bat-ELM achieved the highest numerical performance with correlation coefficient and Nash-Sutcliffe efficiency ranging from 0.927 to 0.973 and from 0.846 to 0.944, respectively, much higher than the respective values obtained using the MLPNN, GRNN, SVR, GPR and ELM approaches. The obtained results demonstrate that the Bat-ELM is an interesting alternative algorithm for predicting high and extreme streamflow.

Gravity data inversion applying a metaheuristic Bat algorithm for various ore and mineral models

Geophysical methods, especially the gravity method, are very helpful in ore and mineral explorations. Here, gravity modeling and interpretation for the subsurface geologic structures generally assumes either homogenous or spatially varying densities within target source rocks and surrounding structures. Therefore, the use of simple-geometric bodies helps in the validation of the subsurface ore and mineral targets. A Bat optimization algorithm is a recently developed metaheuristic algorithm that is used in various geophysical applications to explore and explain the parameters of buried ore and mineral targets. Using the Bat optimization algorithm, we were elucidating gravity anomaly profiles for ore and mineral cases. To perform global optimization, the Bat optimization algorithm is based on the echolocation behavior of bats. The global optimum solution in the Bat optimization algorithm reached the suggested minimum value of the objective function. The Bat optimization algorithm is applied to gravity data to estimate the target parameters (e.g., amplitude coefficient, depth, origin location, and geometric shape). The stability and efficiency of the introduced optimizing algorithm have been checked on two synthetic models represented in a spherical model and an infinitely horizontal cylinder model using two different kinds of noise. Furthermore, successful applications of the proposed algorithm for discovering the ore and minerals in Canada, Cuba, and India were presented. The results match well with the available geological and borehole information and other results from the published literature.

Magnetic data interpretation for 2D dikes by the metaheuristic bat algorithm: sustainable development cases

Metaheuristic algorithms are increasingly being utilized as a global optimal method in the inversion and modeling of magnetic data. We proposed the Bat Algorithm Optimization (BAO) technique that is based on bat echolocation performance to find the global optimum solution. The best-estimated source parameters that correspond to the objective function minimum value are obtained after achieving the global optimum (best) solution. The suggested BAO technique does not require any prior knowledge; rather, it is a global search method that provides an effective tool for scanning the space of data to appraise sources parameters. The BAO technique is applied to magnetic data in the class of dipping and vertical dikes along 2D profiles to estimate the dimensional source parameters that include the depth to top, origin location, amplitude coefficient, index angle of magnetization, and width of the dipping dikes. The BAO technique has been used for single and multiple dikes structures. The accuracy and stability of the BAO technique are achieved on different synthetic examples of free and noisy data for single and multiple cases. Furthermore, the presented BAO technique was effectively utilized in three field examples from China and Egypt for iron ore deposits and metavolcanics basalt rock investigations. Overall, the BAO technique recovered inversion outcomes are in good agreement with borehole, geology, and published literature results.

Novel informational bat-ANN model for predicting punching shear of RC flat slabs without shear reinforcement

While design codes provide guidelines to prevent brittle punching shear failures in flat reinforced concrete (RC) slabs, they are associated with high inaccuracy. This study scrutinizes existing design provisions, highlighting its features and limitations. Sensitivity analysis is then used to identify the influential mechanical and geometric parameters. Subsequently, an artificial neural network coupled with a metaheuristic Bat algorithm (Bat-ANN) is used to develop a hybrid model for estimating punching shear strength. Several statistical metrics revealed that the Bat-ANN model achieved superior predictive accuracy. The novel hybrid model was deployed to assess the influence of key parameters affecting punching shear strength, including the slab effective depth, concrete strength, reinforcement ratio, reinforcement yield strength, and width of the square loaded area. The analysis identified the importance of the flexural reinforcement, which is not typically considered in estimating punching shear strength. Subsequently, using the supervised machine learning method through the EUREQA software, a new regression expression was proposed to estimate the punching shear resistance of flat slabs. This hybrid computational intelligence model could be integrated in future automated design platforms of RC structures.

A spatial multi-resolution multi-objective data-driven ensemble model for multi-step air quality index forecasting based on real-time decomposition

In recent years, the problem of urban air pollution has become more serious. Effective Air Quality Index (AQI) forecasting can provide a reliable guarantee for pollution control and air quality warnings. In this research background, a spatial multi-resolution data-driven ensemble AQI forecasting model based on real-time decomposition is proposed. The model uses spatial correlation analysis to screen out the auxiliary sites that are most relevant to the target site. Wavelet Packet Decomposition (WPD) decomposes the original AQI data into multiple subseries. The iterative refresh mechanism of real-time decomposition makes the decomposition method more valuable in engineering applications. The classic averaging method and deep learning-based Stacked Auto-Encoder (SAE) are used to obtain low-resolution data and high-resolution data, respectively. Subseries containing fluctuation information and depth features are input into Outlier Robust Extreme Learning Machine (ORELM) for forecasting. Multi-Objective Wolf Colony Algorithm (MOWCA) is utilized for the ensemble of multiple resolution predictors. Then, the high-correlation auxiliary sites tested by the Pearson method are input into the model where the target site is located. After the optimized ensemble of the new meta-heuristic bat algorithm, the final AQI forecasting result is produced. To comprehensively evaluate the proposed model, historical air quality data from 26 city monitoring stations in China is used for experimental comparison. Experimental results show that each component of the proposed model has a positive effect on the forecasting performance of the model. The proposed model has excellent forecasting performance, and its performance is superior to other comparative models. Reasonable consideration of multi-resolution and space-time data provides more ideas for the enrichment of the air pollution forecasting model library.

Adaptive optimized DTC‐SVM using metaheuristic Bat algorithm for DSIM fed by IMC based on robust synergetic speed controller

Adaptive optimized <scp>DTC‐SVM</scp> using metaheuristic Bat algorithm for <scp>DSIM</scp> fed by <scp>IMC</scp> based on robust synergetic speed controller

A rigorous approach to uncertain production optimization using a hybrid algorithm: Combination of a meta-heuristic and a Quasi-Newton method

Integrated production optimization from a typical large scale hydrocarbon field is a very complicated task because of geological and economic uncertainty, existence of several linear and nonlinear constraints, and time consuming nature of reservoir simulation. Therefore, it is crucial to develop an efficient framework to perform full field optimization under uncertainty to maximize the returns.This paper, first tries to bridge the gap between reservoir and wells with the surface facilities such as pipelines, separators, injection manifolds. This integrated modeling maximizes the reliability of simulation output. Then, the Broyden–Fletcher–Goldfarb–Shanno (BFGS) coupled with meta-heuristic bat algorithm (BA) is applied for production optimization under geological and economic uncertainty. Cholesky decomposition is used to construct reservoir realizations. The bi-objective function is expected net-present-value (NPV) and its standard deviation.Results reveal that the expected NPV increases over the base case NPV between 2.35% and 9.27% for various time steps. Also, the uncertainty assessment shows that the most likely cumulative oil production (P50%) could be improved over the current value at least by 2.23% under geological and economic uncertainty. Therefore, the optimization framework based on integrated modeling, and combining gradient-based with meta-heuristic algorithms could efficiently solve the full-field worldwide problem.

An optimisation approach for uncertainty-based long-term production scheduling in open-pit mines using meta-heuristic algorithms

ABSTRACT In mines planning, the long-term production scheduling problem (LTPSP) in open-pit mines is considered as a significant issue. It also specifies the distribution of cash flow during the course of the mine-life. Actually, LTPSP is a large-scale optimisation problem including large data-sets, multiple constraints, and uncertainty in the input factors that, has to be solved in a reasonable time. LTPSP, despite the valuable efforts of researchers, has not yet been well resolved. In this paper, hybrid models have been offered by the Lagrangian relaxation (LR) method with meta-heuristic methods, bat algorithm and particle swarm optimisation for solving the LTPSP due to the deterministic assumption and concerning the grade uncertainty. To bring update the Lagrange multipliers, the meta-heuristic algorithms have been applied. In terms of cumulative net present value, average ore grade, and computational time in a 12-year production period, the consequences achieved from the case studies point out that a solution close to optimisation can be presented by the LR-bat algorithm hybrid strategy in comparison with other methods. The results analysis has shown that the proposed method produces a near-optimal solution with a rational time that can be a good suggestion for utilising in the mining industry.

Application of an improved Lagrangian relaxation approach in the constrained long-term production scheduling problem under grade uncertainty

In open-pit mines, the long-term production scheduling (LTPS) problem is a mixed-integer programming problem and is considered as a class of NP-hard problems that has to be solved in a reasonably small time owing to the operational requirements. The LTPS problem cannot be considered a well-solved problem. The current article presents hybrid models to elucidate the LTPS problem regarding grade uncertainty with the involvement of Lagrangian relaxation and augmented Lagrangian relaxation (ALR) with metaheuristic methods, firefly algorithm (FA) and bat algorithm. The results demonstrate that the ALR-FA has the best results in terms of net present value, average ore grade and computational time, and it is significantly better than the conventional method. Finally, analysis of the results shows that the proposed method generates a near-optimal solution within a reasonable time; thus, it could be a good proposition for use in the industry.

Meta heuristic-based task deployment mechanism for load balancing in IaaS cloud

An Infrastructure-as-a-service (IaaS) cloud is a new paradigm which offers computing and storage services in form of virtual machines to the cloud users. Due to increasing demand and diversity of the applications, most of the servers are become overloaded or imbalanced and affects the performance of the cloud system. Most of the existing strategies have developed a series of algorithms to pick out the optimal target server to achieve the immediate load balancing. However, it is proved in the literature that immediate load balancing does not meet the high execution efficiency and resource utilization of the servers. In this paper, we propose a new load balancing mechanism for a long-term process referred as LB-RC (load balancing resource clustering). The meta-heuristic Bat-algorithm is applied to obtain optimal resource clustering and their cluster centers for faster convergence. We also propose a new dynamic task assignment policy to achieve the minimum makespan and execution cost within the given constraints. The proposed algorithm is tested and compared with the existing algorithms over various synthetic datasets and performance matrices to prove its superiority.

Novel statistical forecasting models for crude oil price, gas price, and interest rate based on meta-heuristic bat algorithm

Investment in the petroleum industry is usually faced with a high degree of risk due to uncertainty associated with economic factors. Typical factors include oil and gas price, interest rate, operational and capital expenditure. In addition, the investment risk increases as offshore exploration, drilling and production activities increase. Therefore, accurate prediction of economic factors is crucial in an upstream oil and gas sector in order to make better strategic decisions with minimized risk.In the present study, four methods of the least square support vector machine (LSSVM), genetic programming (GP), artificial neural network (ANN), and auto-regressive integrated moving average (ARIMA) were initially used to forecast monthly oil price (MOP), daily gas price (DGP), and annual interest rate (AIR). Next, the meta-heuristic bat algorithm (BA) was applied in order to optimally combine the four mentioned forecasting methods in an integrated equation as a novel approach. All required historical data to forecast oil price, gas price and interest rate were collected from the Central Bank of the Islamic Republic of Iran.Error analysis in terms of coefficient of determination (R2), average absolute relative error percentage (AAREP), root-mean square error (RMSE), and cumulative probability distribution versus absolute relative error percentage were used to compare the prediction performance of forecasting methods.Error analysis proves that the BA optimized method is superior over all other forecasting methods in terms of highest R2 and lowest RMSE. After the BA optimized method, construction of LSSVM, ARIMA, ANN, and GP has better prediction ability, respectively. The results indicate that the BA optimized method reduces RMSE at least by 6.61% in MOP forecast; by 18.33% in DGP forecast; and by 23.13% in AIR forecast over all other forecasting methods.

Application of DOE and metaheuristic bat algorithm for well placement and individual well controls optimization

The design of an optimal gas field development and production management is a complicating task because of influencing various factors on decision-making process. Typical factors include number and type of wells, well locations, and production constraints, economic factors of capital expenditure, operating costs, gas sale price, and different engineering and geological parameters. The situation is further complicated due to uncertainty associated with the nonlinear problem of field development optimization.In this study, first, design of experiment (DOE) techniques including uniform design (UD) and Box-Behnken design (BBD) are used for performance prediction of water drive gas reservoirs. Next, a new metaheuristic bat inspired algorithm (BA) will be applied in optimization process of objective function. Undiscounted net present value (UNPV) is used as an objective function for the determination of optimal number of wells (N), individual well locations (I and J), production rate (Qg), perforation thickness (Hp) and the limit of tubing head pressure (THP) for different average reservoir permeability (KG) and permeability anisotropy (Kv/Kh). In this regard, part of gas reservoir with an active bottom aquifer based on actual data is simulated in order to predict gas recovery factor and cumulative water production data that are necessary for performing production optimization.The results show that reducing gas production rate increases the UNPV. Reducing production rate increases ultimate recovery factor and decreases cumulative water production. However, considering time value of money, it is favorable to produce with high rates and consequently deplete the reservoir over short time scales in order to compensate the reduction of profit.

Energy optimization using metaheuristic bat algorithm assisted controller tuning for industrial and residential applications

The advent of model based control provides optimization and constrained control capabilities that can be tailored to specific goals. Metaheuristic algorithms are being researched in various fields owing to their efficiency in providing global optimization. In this paper, both model regression and energy efficiency based controller tuning are attempted using the chaotic bat algorithm (CBA). Two sets of plant data, one from an industrial precalciner temperature loop (PTL) and another from a domestic heating ventilation and air conditioning system (HVAC) are considered. Explicit model predictive control is designed. Minimizing the energy consumption (HVAC) and coal feed rate (PTL) by tuning the controllers is attempted. Results indicate that CBA can be successfully deployed in both regression and achieving control objectives as observed from the case studies.

PI controller optimization for a heat exchanger through metaheuristic Bat Algorithm, Particle Swarm Optimization, Flower Pollination Algorithm and Cuckoo Search Algorithm

This paper presents the modeling and computer simulation of a control system for a shell and tube heat exchanger, using Bat Algorithms, Particle Swarm Optimization, Flower Pollination Algorithm and Cuckoo Search Algorithm. The temperature control logic is managed by a Proportional Integral-controller whose parameters were initially tuned using two methods of keeping the state of the art. To evaluate the performance of different methods of tuning, we compared the values of the transient of the response to step in eight mesh settings generated. It has also established a comparison between these two types of mesh using the performance indices proposed in the literature, with optimized system by Bat Algorithms got the best values of transient in relation to the Particle Swarm Optimization, Cuckoo Search Algorithm and Flower Pollination Algorithm. Performance indices FPA and PSO obtained better results.

Optimal Design of Short Fiber Bragg Grating Using Bat Algorithm With Adaptive Position Update

We propose a new method to optimally design short triangular-spectrum fiber Bragg gratings (TS-FBGs), using the metaheuristic bat algorithm (BA). In addition, we propose a novel modification, i.e., adaptive position update (APU), to optimize the index modulation within a predetermined range. The discrete layer-peeling algorithm is used to efficiently initialize BA. The APU improves the search performance and accuracy of the BA algorithm in fiber Bragg grating (FBG) design application. Using the proposed method, a 0.2-nm-bandwidth TS-FBG, operating in the C-band, is designed. The short-length FBG with chirp-free structure prevents complex phase modulation for practical considerations. In addition, a dual-wavelength TS-FBG of 0.75-nm bandwidth operating in the eye-safe region has been designed and provided the most accurate optimum design length. The latter is well suited for FBGs inscribed in high-birefringent fibers, which are utilized in multiwavelength fiber laser systems. For both cases, the accuracy and search performance of APU-BA are shown to be better than those of previously reported algorithms in the literature.

BAT algorithm for model order reduction

Metaheuristic algorithms have made an unprecedented impact on model order reduction (MOR). Almost every year new algorithm emerges with an extended literature. These nature-based metaheuristic algorithms have attracted researchers to apply these algorithms for finding reduced order approximants of higher order system. This paper proposes a mixed approach for model order reduction based on metaheuristic BAT algorithm (BA) which is inspired by echolocation of microbats and Pade approximation based on matching of both time moments and Markov parameters. Further the efficiency of the method is investigated in terms of integral square error (ISE). This paper also draws a comparison of proposed method with existing techniques for models order reduction.

BAT algorithm for model order reduction

Metaheuristic algorithms have made an unprecedented impact on model order reduction (MOR). Almost every year new algorithm emerges with an extended literature. These nature-based metaheuristic algorithms have attracted researchers to apply these algorithms for finding reduced order approximants of higher order system. This paper proposes a mixed approach for model order reduction based on metaheuristic BAT algorithm (BA) which is inspired by echolocation of microbats and Padé approximation based on matching of both time moments and Markov parameters. Further the efficiency of the method is investigated in terms of integral square error (ISE). This paper also draws a comparison of proposed method with existing techniques for models order reduction.

Optimal design and tuning of novel fractional order PID power system stabilizer using a new metaheuristic Bat algorithm

Abstract This paper proposes a novel robust power system stabilizer (PSS), based on hybridization of fractional order PID controller (PIλDμ) and PSS for optimal stabilizer (FOPID-PSS) for the first time, using a new metaheuristic optimization Bat algorithm (BA) inspired by the echolocation behavior to improve power system stability. The problem of FOPID-PSS design is transformed as an optimization problem based on performance indices (PI), including Integral Absolute Error (IAE), Integral Squared Error (ISE), Integral of the Time-Weighted Absolute Error (ITAE) and Integral of Time multiplied by the Squared Error (ITSE), where, BA is employed to obtain the optimal stabilizer parameters. In order to examine the robustness of FOPID-PSS, it has been tested on a Single Machine Infinite Bus (SMIB) power system under different disturbances and operating conditions. The performance of the system with FOPID-PSS controller is compared with a PID-PSS and PSS. Further, the simulation results obtained with the proposed BA based FOPID-PSS are compared with those obtained with FireFly algorithm (FFA) based FOPID-PSS. Simulation results show the effectiveness of BA for FOPID-PSS design, and superior robust performance for enhancement power system stability compared to other with different cases.

Experimental Investigation and Multiobjective Optimization of Turning Duplex Stainless Steels

This paper addresses experimental investigations of turning EN 1.4462 and EN 1.4410 duplex stainless steel grades with multilayer coated carbide inserts. Single-point wet and dry longitudinal turning tests of cylindrical bars are conducted; cutting forces, effective cutting powers, and tool wear are measured. The parametric influences of cutting speed, feed rate, and process conditions on the cutting performances such as resultant cutting force, specific effective cutting power, and flank wear are analyzed and proper conclusions are drawn. Nature-inspired metaheuristic bat algorithm is employed to handle the multiobjective optimization of the conflicting performances. Finally, the optimum cutting condition for each process condition can be selected from calculated Pareto optimal fronts by the user according to the planning requirements.