Global Genetic Algorithm Research Articles

Intelligent computing framework to analyze the transmission risk of COVID-19: Meyer wavelet artificial neural networks

The optimum control methods for the epidemiology of the COVID-19 model are acknowledged using a novel advanced intelligent computing infrastructure that joins artificial neural networks with unsupervised learning-based optimizers i.e., Genetic Algorithms (GA) and sequential quadratic programming (SQP). Unsupervised learning strategy is provided which depends on the wavelet basis's sequential deconstruction of stochastic data. The weights or selection values of neural networks are utilizing cumulative algorithms of Meyer wavelet artificial neural networks (MWANNs) optimized with global search Genetic Algorithms (GAs) and Sequential Quadratic Programming (SQP), referred to as MWANNs-GA-SQP and the design technique is utilized to determine the COVID-19 model for five different scenarios employing different step sizes and input intervals. The findings of this research article examined that in order to minimize the total disease transmission at the lowest cost and complexity, safety, focused medical care, and exterior sterilization methods applicability. The provided data is validated through various graphical simulations, which surely authenticate the effectiveness and robustness of the proposed solver. The suggested solver, MWANNs-GA-SQP, is tested in a variety of circumstances to examine that how reliable, safe, and tolerant. Using the proposed MWANNs hubristic intelligent approach, an objective optimization function is created in feed forward neural networking to minimize the mean square error. An investigation of the hybrid GA-SQP is used to confirm the accuracy and dependability of the MWANNs model results. Mean absolute graphs have been constructed to assess the integrity and efficiency of the proposed methodology. The accuracy and reliability of the suggested method are demonstrated by constantly achieving maximum variables of analytical assessment criteria computed for a large appropriate variety of distinct trials.

Reliability based optimisation of composite plates under aeroelastic constraints via adapted surrogate modelling and genetic algorithms

Composite materials are vital in aerospace for their exceptional strength-to-weight ratio. This study delves into reliability-based optimisation of composite plates within aeroelastic constraints, employing an efficient global optimisation method and genetic algorithms. Initial analysis focuses on aeroelastic responses such as limit flutter speed, gust response, and static loads, emphasising maximum strain assessment. To tackle optimisation challenges of composite stacking sequences, a homogenisation technique with lamination parameters is applied. We then formulate a constrained optimisation problem to minimise gust response while meeting flutter and maximum strain constraints. Surrogate models based on conditioned Gaussian Processes are developed for each aeroelastic response, facilitating optimisation within the composite design space. These models, with potential for local refinement, expedite optimal solution identification. Further, we integrate reliability-based optimisation into the framework to determine a robust stacking sequence using genetic algorithms, accounting for random fibre orientation variations. This holistic approach integrates aeroelastic analysis, constrained optimisation, surrogate modelling, and reliability-based optimisation, proving effective in designing reliable, efficient composite structures for aerospace, thus enhancing performance and safety.

Design of evolutionary computational intelligent solver for nonlinear corneal shape model by Mexican Hat and Gaussian wavelet neural networks

In this study, an integrated computational intelligence algorithm is implemented for the numerical treatment of the two-point boundary value problems that arise in the nonlinear corneal shape (NCS) model through the exploitation of wavelet neural networks including Mexican-Hat (MHWNNs) and Gaussian-wavelet (GWNNs) through global genetic algorithms (GAs) then hybridization with local sequential quadratic programming (SQP) solvers, i.e. MHWNNs-GAs, GWNNs-GAs, MHWNNs-GA-SQP, and GWNNs-GA-SQP respectively. The GWNNs and MHWNNs are applied to calculate the mean squared error of mathematical modeling of the proposed problem through objective functions while optimization of the fitness functions is initially conducted with an efficiency of global search GAs and then the efficacy of local search technique SQP for fine-tuning. A comparison of the proposed solutions of MHWNNs-GAs, GWNNs-GAs, MHWNNs-GA-SQP, and GWNNs-GA-SQP solvers with a reference solution of Adam’s method shows that the proposed schemes have better accuracy, stability, efficiency consistency on an independent number of runs analyzed through complexity analysis and different statistical operators.

Global Genetic Algorithm for Automating and Optimizing Petroleum Well Deployment in Complex Reservoirs

Locating petroleum-productive wells using informed geological data, a conventional means, has proven to be tedious and undesirable by reservoir engineers. The former numerical simulator required a lengthy trial-and-error process to manipulate the variables and uncertainties that lie on the reservoir to determine the best placement of the well. Hence, this paper examines the use of a global genetic algorithm (GA) to optimize the placement of wells in complex reservoirs, rather than relying on gradient-based (GB) methods. This is because GB approaches are influenced by the solution’s surface gradient and may only reach local optima, as opposed to global optima. Complex reservoirs have rough surfaces with high uncertainties, which hinders the traditional gradient-based method from converging to global optima. The explicit focus of this study was to examine the impact of various initial well placement distributions, the number of random solution sizes and the crossover rate on cumulative oil production, the optimization of the synthetic reservoir model created by CMG Builder, CMOST, and IMEX indicated that using a greater number of random solutions led to an increase in cumulative oil production. Despite the successful optimization, more generations are required to reach the optimal solution, while the application of GA on our synthetic model has proven efficient for well placement; however, different optimization algorithms such as the improved particle swarm (PSO) and grey wolf optimization (GWO) algorithms could be used to redefine well-placement optimization in CMG.

A novel heuristic Morlet wavelet neural network procedure to solve the delay differential perturbed singular model

This study designs the Morlet wavelet neural network (MWNN) for the numerical performance of the second-order delay differential perturbed singular model (DD-PSM). These stiff singular models are always challenging for the research community to numerically present their results. The DD-PSM is used as an objective function, and its boundary conditions are assembled and then optimised using the computing hybrid proficiency of the global genetic algorithm (GA) and local active-set approach (ASA). Details of the singularity, shape factor, perturbed and delay terms based on the DD-PSM are also provided. Three problems of the DD-PSM are presented and numerically solved using the MWNN–GA–ASA. The precision of the MWNN–GA–ASA is studied by comparing the proposed solution-based DD-PSM and exact solutions. Moreover, a comparison of the MWNN with the Meyer wavelet neural network is presented. The reliability, convergence, correctness and constancy of the numerical scheme are observed by different statistical performances.

A framework for the analysis of skin sores disease using evolutionary intelligent computing approach

The most common and contagious bacterial skin disease i.e. skin sores (impetigo) mostly affects newborns and young children. On the face, particularly around the mouth and nose area, as well as on the hands and feet, it typically manifests as reddish sores. In this study, a neuro-evolutionary global algorithm is introduced to solve the dynamics of nonlinear skin sores disease model (SSDM) with the help of an artificial neural network. The global genetic algorithm is integrated with local sequential quadratic programming (GA-LSQP) to obtain the optimal solution for the proposed model. The designed differential model of skin sores disease is comprised of susceptible (S), infected (I), and recovered (R) categories. An activation function based neural network modeling is exploited for skin sores system through mean square error to achieve best trained weights. The integrated approach is validated and verified through the comparison of results of reference Adam strategy with absolute error analysis. The absolute error results give accuracy of around 10 − 11 to 10 − 5 , demonstrating the worthiness and efficacy of proposed algorithm. Additionally, statistical investigations in form of mean absolute deviation, root mean square error, and Theil’s inequality coefficient are exhibited to prove the consistency, stability, and convergence criteria of the integrated technique. The accuracy of the proposed solver has been examined from the smaller values of minimum, median, maximum, mean, semi-interquartile range, and standard deviation, which lie around 10 − 12 to 10 − 2 .

A global heat flow topology for revealing the synergistic effects of heat transfer and thermal power conversion in large scale systems: Methodology and case study

In the processes of modeling, optimization, heat transfer analysis, and thermal power conversion analysis in large-scale complex systems, challenges are encountered regarding intricate design and optimization. In this paper, a global heat flow topology is proposed that reveals the synergistic effect of heat transfer and thermal power conversion in large-scale systems. The approach involves the construction of a heat flow topology, mathematical model development, analysis of specific parameters, and multi-objective optimization. It integrates various methods and tools, including heat flow topology, numerical simulation tool, entransy transfer analysis, global thermal resistances visualization, genetic algorithm (GA), and technique for order preference by similarity to ideal solution (TOPSIS). By using the LNG cold energy recovery and regasification process in floating storage and regasification units (FSRU) as a case study, the methodology provides a comprehensive understanding of the interactions and conversions between heat transfer and thermal power within the system. The results demonstrate that the optimal configuration achieves a maximum thermal efficiency of 21.73 % and a maximum cold recovery efficiency of 58.48 %. Additionally, the interaction between LNG pressure and seawater temperature exhibits limited synergistic impact on both LNG cold exergy efficiency and entransy transfer efficiency. Similarly, the combined influence of LNG pressure and evaporator temperature shows weak synergistic effects on parameters such as supply/demand ratio, thermal efficiency, and entransy transfer efficiency. The analysis of the global thermal resistance bubble chart reveals the significant impact of evaporator temperature and seawater temperature on the evaporator resistance, as well as the notable impact of LNG pressure on the condenser resistance.

Designing a heuristic computing structure to solve the human balancing model

The current study provides numerical solutions to the human balancing system using novel framework-based artificial neural networks and the hybrid competency of global heuristic genetic algorithm and local search sequential quadratic programming. These networks tend to handle complicated tasks and perform contemporary performance in different areas. The neural networks performances based on the hybridization schemes are presented using the discretization of the model to express the fitness function in the sense of mean square error. The numerical representations are presented for three cases of the delay terms-based human balancing model in order to validate the consistency and efficacy of the proposed stochastic scheme. The acceptability of the proposed solver is oppressed through the overlapping of obtained and reference results. The negligible values of absolute error also provide the accuracy of the scheme. Additionally, the graphs based on the statistical interpretations provide the precision, and convergence of stochastic computing solver.

Novel quartic spline method for boundary layer fluid flow problem of Falkner-Skan model with wall stretching and transfer of mass effects

The non-linear ordinary differential equations (NODEs) in this article are estimated and analyzed numerically using the capability of the Quartic Splines Method (QSM) for mathematical modeling of the Falkner-Skan fluidic system and its optimization through global search Genetic Algorithms (GAs) and local search Active-Set (AS) techniques. The concept of hybridization is used to optimize the obtained results and provide a boost to the suggested method, QSM, which allows for rapid iteration. Falkner-Skan fluid model (FSFM) is solved by the proposed technique QSM-GAs-AS. The FSFM is solved for three, seven, and twelve splines successfully. The problem is analyzed for three scenarios, in which each scenario is based on the variation of a parameter out of the three involved parameters, namely the wall mass transfer parameter (γ), the wall movement parameter (λ), and the stream-wise pressure gradient parameter (β), appearing in FSFM. The QSM-GAs-AS produces an interpolated function that is continuous up to its fourth derivative. The solution outcomes of FSFM, treated by the designed scheme QSM-GAs-AS, are presented graphically. The evaluation of the planned solution is done with a deterministic numerical solver, the Homotopy Analysis Method (HAM). Statistical analysis for multiple runs is used to examine the proposed scheme's convergence, exactness, and accuracy.

Heuristic computing with active set method for the nonlinear Rabinovich–Fabrikant model

The current study shows a reliable stochastic computing heuristic approach for solving the nonlinear Rabinovich-Fabrikant model. This nonlinear model contains three ordinary differential equations. The process of stochastic computing artificial neural networks (ANNs) has been applied along with the competences of global heuristic genetic algorithm (GA) and local search active set (AS) methodologies, i.e., ANNs-GAAS. The construction of merit function is performed through the differential Rabinovich-Fabrikant model. The results obtained through this scheme are simple, reliable, and accurate, which have been calculated to optimize the merit function by using the GAAS method. The comparison of the obtained results through this scheme and the conventional reference solutions strengthens the correctness of the proposed method. Ten numbers of neurons along with the log-sigmoid transfer function in the neural network structure have been used to solve the model. The values of the absolute error are performed around 10−07 and 10−08 for each class of the Rabinovich-Fabrikant model. Moreover, the reliability of the ANNs-GAAS approach is observed by using different statistical approaches for solving the Rabinovich-Fabrikant model.

A design of novel Gudermannian neural networks for the nonlinear multi-pantograph delay differential singular model

In this paper, a new stochastic numerical platform through the Gudermannian neural network (GNN) based intelligent computing solver (GNNICS) is accessible for solving the nonlinear singular multi-pantograph delay differential (MP-DD) systems. In GNNICS, Gudermannian kernel is exploited to construct the neural network models of differential operators with different neurons for the nonlinear system along with the hybrid computing via global genetic algorithm (GA) and local refinements based active set (AS), i.e., GNN-GAAS method. A fitness function with GNN models is formulated for solving the MP-DD equation along with the optimization of design variables of the network using GAAS. To investigate the performance of the designed GNNICS based GNN-GAAS algorithm, three different variants of the MP-DD systems are used to assess the correctness, effectiveness, and robustness. The statistical investigations based on different performance are presented to authenticate the consistent accuracy, convergence, and stability of the designed GNN-GAAS algorithm. Furthermore, the negligible absolute error that are performed as 10−06 to 10−08 for solving the GNNICS based on GNN-GAAS algorithm.

A Bibliometric Analysis of Metaheuristic Research and Its Applications

Metaheuristic algorithms are generic optimization tools to solve complex problems with extensive search spaces. This algorithm minimizes the size of the search space by using effective search strategies. Research on metaheuristic algorithms continues to grow and is widely applied to solve big data problems. This study aims to provide an analysis of the performance of metaheuristic research and to map a description of the themes of the metaheuristic research method. Using bibliometric analysis, we examined the performance of scientific articles and described the available opportunities for metaheuristic research methods. This study presents the performance analysis and bibliometric review of metaheuristic research documents indexed in the Scopus database between the period of 2016-2021. The overall number of papers published at the global level was 3846. At global optimization, heuristic methods, scheduling, genetic algorithms, evolutionary algorithms, and benchmarking dominate metaheuristic research. Meanwhile, the discussion on adaptive neuro-fuzzy inference, forecasting, feature selection, biomimetics, exploration, and exploitation, are growing hot issues for research in this field. The current research reveals a unique overview of metaheuristic research at the global level from 2016-2021, and this could be valuable for conducting future research.

COMPUTATIONAL PERFORMANCES OF MORLET WAVELET NEURAL NETWORK FOR SOLVING A NONLINEAR DYNAMIC BASED ON THE MATHEMATICAL MODEL OF THE AFFECTION OF LAYLA AND MAJNUN

The aim of this study is to design a novel stochastic solver through the Morlet wavelet neural networks (MWNNs) for solving the mathematical Layla and Majnun (LM) system. The numerical representations of the mathematical LM system have been presented by using the MWNNs along with the optimization is performed through the hybridization of the global and local search schemes. The local active-set (AS) and global genetic algorithm (GA) operators have been used to optimize an error-based merit function using the differential LM model and its initial conditions. The correctness of the MWNNs using the local and global operators is observed through the comparison of the obtained solutions and the Adams scheme, which is used as a reference solution. For the stability of the MWNNs using the global and local operators, the statistical performances with different operators have been provided using the multiple executions to solve the nonlinear LM system.

Neural networks and genetic algorithm as robust optimization tools for modeling the microbial production of poly-β-hydroxybutyrate (PHB) from Brewers' spent grain.

This research work has been carried out to establish the combinatorial impact of various fermentation medium constituents, used for poly-β hydroxybutyrate (PHB) biosynthesis. Model development was performed with an optimized medium composition that enhanced the biosynthesis of PHB from the biowaste material Brewers' spent grain (BSG). The latter was used as a carbon substrate in submerged fermentation with Bacillus sphaericus NCIM 2478. Three independent variables: BSG, yeast extract (YE), and salt solution concentration (SS) and one dependent variable (amount of PHB produced) were assigned. A total of 35 microbial fermentation trials were conducted by which a nonlinear mathematical relationship was established in terms of neural network model between independent and dependent variables. The resulting artificial neural networks (ANNs) model for this process was further optimized using a global genetic algorithm optimization technique, which predicted the maximum production of PHB (916.31mg/L) at a concentration of BSG (50.12g/L), concentration of YE (0.22g/L), and concentration of SS (24.06%, v/v). The experimental value of the quantity of PHB (concentration ∼916mg/L) was found to be very close to the value predicted by the ANN-GA model approach.

Neural Optimizer for Inverse Design of Complex‐Modulated Hologram Implemented by Plasmonic Metasurfaces

Inverse design of a metasurface involves searching parameters in a high‐dimensional space, which needs huge computational power. To ease the computational burden, neural network, a well‐researched computer science stream, has demonstrated its potential usage in the inverse design of a photonic device. Many studies primarily focused on the nanostructure's configuration. However, the near field of a metasurface requires further optimization to achieve a desired holographic image at relieved computational power. Here, a convolutional neural network is developed to optimize the complex field of a computer‐generated hologram, which can be fabricated into a metasurface to generate the desired holographic image upon lensless image projection. The neural optimizer can accelerate the design speed 400 times faster than theoretical computation and reduce the time complexity from O(n 4) to O(n 2). The neural optimizer has been compared against three other methods, e.g., gradient‐based optimization, global genetic algorithm, and coupled‐mode theory, to demonstrate a lowered error rate from more than 10% to 1.38% for the benchmark testing and a reduced running time from hours to near 1 s. The neural optimizer is envisioned to play a key role in lensless image projection and real‐time metasurface pattern design.

Nonlinear Model Predictive Control-Based Optimal Energy Management for Hybrid Electric Aircraft Considering Aerodynamics-Propulsion Coupling Effects

Hybrid electric propulsion systems have been identified as feasible solutions for regional jets and narrow-body aircraft to reduce block fuel burn, emissions, and operating costs. In this article, a nonlinear model predictive control-based optimal energy management scheme (MPC-EMS) has been proposed to minimize the block fuel burn during flight. First, the artificial neural network (ANN) model is adopted to predict turbofan engine performance; meanwhile, gas turbine–electrical powertrain integration is investigated and analyzed for typical operating conditions. Then, by combining a point-mass aircraft dynamic model, nonlinear MPC with the cross-entropy method (CEM) is proposed to obtain optimal energy management based on a fully coupled aerodynamics-propulsion hybrid electric aircraft model. Besides, this state-constrained optimal control problem is reformulated as a state-unconstrained problem with a penalty function to reduce the computational load. Finally, the proposed MPC-EMS algorithm is applied to Boeing 737-800 aircraft with mechanically parallel hybrid electric propulsion configuration to minimize the block fuel burn and compared with the optimization results using global genetic algorithm (GA)-based EMS and equivalent consumption minimization strategy (ECMS). The simulation results indicate that the proposed MPC-EMS can effectively reduce the computational time compared with global GA-based EMS while achieving global optimization performance with only a minor difference of 1.71% of block fuel burn and emissions reductions.

Joint optimization of constrained well placement and control parameters with a quantum-inspired cell-based quality gate function

Well placement and parameter optimization (WPPO) is an essential step in hydrocarbon, geothermal and water resources development which has complexities and difficulties. In fact, high computational cost can be the most important obstacle in WPPO problems. Population-based metaheuristics algorithms (PBMAs) are the most widely utilized ones for WPPO problems. However, these methods suffer from the issue that at each iteration, the minimum number of simulation run is at least equal to the population size. Knowing this, in order to enhance the efficiency of these methods, in this study, we introduced a cell-based quality gate function (CBQGF) which is inspired from quantum gates in quantum computing. The CBQGF is incorporated in our previously introduced inter-distance algorithm (IDC) which we called CBQG-IDC. Since, CBQG sets a condition for each location during the optimization process, locations with poor cell properties will be filtered out to increase the rate of convergence considerably. We applied the CBQG-IDC to two universally popular global optimization methods, genetic algorithm (GA) and particle swarm optimization (PSO) and compared the results to the IDC limited algorithm. In all scenarios, net present value (NPV) was considered as the fitness value and all joint optimization of locations and well associated parameters were conducted simultaneously. The results showed CBQG-IDC with a much higher rate of convergence compared to IDC, while its performance is highly dependent on constant parameters. Ultimately, the proposed CBQG-IDC can be applied to any optimization algorithm for any placement optimization problem in Euclidian geometry to save the computational cost. • A cell-based quality gate function (CBQGF) has been introduced to optimization process. • The proposed CBQGF can be coupled with any arbitrary optimization and applied to any placement optimization problem. • The CBQGF has increased the rate of convergence significantly with substantial computation cost saving. • The threshold value of the cell property and its associated constant have great influence on the search flexibility.

Cole-Cole modeling of real-time capacitance data for estimation of cell physiological properties in recombinant Escherichia coli cultivation.

Real-time estimation of physiological properties of the cell during recombinant protein production would ensure enhanced process monitoring. In this study, we explored the application of dielectric spectroscopy to track the fed-batch phase of recombinant Escherichia coli cultivation for estimating the physiological properties, namely, cell diameter and viable cell concentration (VCC). The scanning capacitance data from the dielectric spectroscopy were pre-processed using moving average. Later, it was modeled through a nonlinear theoretical Cole-Cole model and further solved using a global evolutionary genetic algorithm (GA). The parameters obtained from the GA were further applied for the estimation of the aforementioned physiological properties. The offline cell diameter and cell viability data were obtained from particle size analyzer and flow cytometry measurements to validate the Cole-Cole model. The offline VCC was calculated from the cell viability % from flow cytometry data and dry cell weight concentration. The Cole-Cole model predicted the cell diameter and VCC with an error of 1.03% and 7.72%, respectively. The proposed approach can enable the operator to take real-time process decisions to achieve desired productivity and product quality.

A Neuro-Evolution Heuristic Using Active-Set Techniques to Solve a Novel Nonlinear Singular Prediction Differential Model

In this study, a novel design of a second kind of nonlinear Lane–Emden prediction differential singular model (NLE-PDSM) is presented. The numerical solutions of this model were investigated via a neuro-evolution computing intelligent solver using artificial neural networks (ANNs) optimized by global and local search genetic algorithms (GAs) and the active-set method (ASM), i.e., ANN-GAASM. The novel NLE-PDSM was derived from the standard LE and the PDSM along with the details of singular points, prediction terms and shape factors. The modeling strength of ANN was implemented to create a merit function based on the second kind of NLE-PDSM using the mean squared error, and optimization was performed through the GAASM. The corroboration, validation and excellence of the ANN-GAASM for three distinct problems were established through relative studies from exact solutions on the basis of stability, convergence and robustness. Furthermore, explanations through statistical investigations confirmed the worth of the proposed scheme.

A GA-based online real-time optimized energy management strategy for plug-in hybrid electric vehicles

The performance of plug-in hybrid electric vehicles (PHEVs) depends on the energy management strategy (EMS). An optimal EMS can maximize energy utilization by coordinating the battery energy and fuel consumption. However, the real-time EMS remains a challenge due to the multiple dynamic parameters. To this end, this paper proposed a real-time EMS based on the adaptive regulation of multiple parameters including the driving cycle, driving distance and battery state of charge (SOC). First, the rule-based EMS (RB-EMS) is designed, in which the operative threshold of the charge depleting mode (CD) and charge sustaining (CS) mode are initially determined through engineering experience considering the engine and battery SOC characteristics. Meanwhile, equivalent consumption minimization strategy (ECMS) is utilized to replace the traditional rules in the CD-CS region, which benefits to find the real-time optimal solution in a wider range and simultaneously addresses the fixed torque distribution between the engine and motor in the RB strategy. After then, to improve the adaptability of EMS in different driving cycles, the threshold in the RB strategy and equivalent factor (s(t)) in the ECMS strategy with different driving distances and initial SOC values are optimized with a global genetic algorithm (GA). Besides, a driving cycle recognition algorithm (DCR) based on fuzzy logic is online executed with GPS and onboard sensors, with which the optimal engine and motor torque distribution under the current conditions are adaptively determined according to the identified driving cycles and the above-mentioned offline results. Finally, the proposed adaptive hybrid energy management (HEM) approach was validated by the numerical simulation and hard-in-loop (HIL) experiments. Results show that the proposed HEM strategy can adaptively change the dynamic parameters to achieve the optimized CD stage in real-time; meanwhile, it can achieve a suboptimal result compared with DP which has reduced the fuel consumption by 14.82% for high power demand level.