Evolutionary Algorithm Research Articles

A multistrategy differential evolution algorithm combined with Latin hypercube sampling applied to a brain–computer interface to improve the effect of node displacement

Injection molding is a common plastic processing technique that allows melted plastic to be injected into a mold through pressure to form differently shaped plastic parts. In injection molding, in-mold electronics (IME) can include various circuit components, such as sensors, amplifiers, and filters. These components can be injected into the mold to form a whole within the melted plastic and can therefore be very easily integrated into the molded part. The brain–computer interface (BCI) is a direct connection pathway between a human or animal brain and an external device. Through BCIs, individuals can use their own brain signals to control these components, enabling more natural and intuitive interactions. In addition, brain–computer interfaces can also be used to assist in medical treatments, such as controlling prosthetic limbs or helping paralyzed patients regain mobility. Brain–computer interfaces can be realized in two ways: invasively and noninvasively, and in this paper, we adopt a noninvasive approach. First, a helmet model is designed according to head shape, and second, a printed circuit film is made to receive EEG signals and an IME injection mold for the helmet plastic parts. In the electronic film, conductive ink is printed to connect each component. However, improper parameterization during the injection molding process can lead to node displacements and residual stress changes in the molded part, which can damage the circuits in the electronic film and affect its performance. Therefore, in this paper, the use of the BCI molding process to ensure that the node displacement reaches the optimal value is studied. Second, the multistrategy differential evolutionary algorithm is used to optimize the injection molding parameters in the process of brain–computer interface formation. The relationship between the injection molding parameters and the actual target value is investigated through Latin hypercubic sampling, and the optimized parameters are compared with the target parameters to obtain the optimal parameter combination. Under the optimal parameters, the node displacement can be optimized from 0.585 to 0.027 mm, and the optimization rate can reach 95.38%. Ultimately, by detecting whether the voltage difference between the output inputs is within the permissible range, the reliability of the brain–computer interface after node displacement optimization can be evaluated.

A novel differential evolution algorithm based on periodic intervention and systematic regulation mechanisms

A novel differential evolution algorithm based on periodic intervention and systematic regulation mechanisms

Task scheduling in cloud computing based on grey wolf optimization with a new encoding mechanism

Task scheduling in the cloud computing still remains challenging in terms of performance. Several evolutionary-derived algorithms have been proposed to solve or alleviate this problem. However, evolutionary algorithms have good exploration ability, but the performance drops significantly in high dimensions. To address this issue, considering the characteristic of task scheduling in cloud computing (i.e. all task-VM mappings are 1-dimensional and have the same search range), we propose a task scheduling algorithm based on grey wolf optimization using a new encoding mechanism (GWOEM) in this work. Through this new encoding mechanism, greedy and evolutionary algorithms are rationally integrated in GWOEM. Besides, based on the new mechanism, the dimension of search space is reduced to 1 and the key parameter (i.e., the population size) is eliminated. We apply the proposed GWOEM to the Google Cloud Jobs dataset (GoCJ) and demonstrate better performance than the prior state of the art in terms of makespan.

Optimizing pulmonary carcinoma detection through image segmentation using evolutionary algorithms

<span lang="EN-US">This paper’s goal is to suggest an image segmentation technique for use with medical images, specifically computer tomography scan images, to aid doctors in understanding the images. To address a variety of picture segmentation issues, it is necessary to investigate and apply novel evolutionary algorithms. The study focuses on pulmonary carcinoma, which is the cancer that affects males the most frequently across the globe. For proper treatment and life-saving measures, early identification of lung cancer is essential. To identify lung cancer, doctors frequently employ the computed tomography imaging technique. In order to extract tumours from lung scans, the study analyses the effectiveness of three optimization algorithms: k-means clustering, particle swarm optimization, and modified guaranteed convergence particle swarm optimization. The study also examines the pre-processing performance of four filters, namely the mean, bilateral, gaussian, and laplacian filters, shows that the bilateral filter is best suited for CT scans of the body. To test the proposed technique on 30 examples of lung scans. The proposed algorithm is tested on 30 sample lung images. The results show that the modified guaranteed convergence particle swarm optimization algorithm has the highest accuracy of 96.01%.</span>

Evaluation of cardiovascular disease in diabetic patients using machine learning techniques

Machine learning (ML) improves operations in many industries, including medicine. It affects the prognosis of several disorders, including heart disease. If predicted, it may provide doctors with new insights and allow them to treat each patient individually. If anticipated, it may provide medical practitioners with valuable information. Our team uses machine learning algorithms to study heart disease risk. This research will compare decision trees, AdaBoost, support vector machines, artificial neural networks (ANN), and customized ANN. The study will include this analysis. The given model will leverage the dataset of general information and medical test results. Our model uses particle swarm optimization (PSO) and k-nearest neighbors (KNN). Algorithm for feature selection. The model reduces dimensionality using evolutionary algorithms and neural networks. We compared the numerous assessment criteria to the current models, our model, and earlier models. Because of this, the suggested model's suitability was rated with the highest accuracy.

Discovery of novel silicon allotropes with optimized band gaps to enhance solar cell efficiency through evolutionary algorithms and machine learning

In the pursuit of advancing solar energy technologies, this study presents 20 direct and quasi-direct band gap silicon crystalline semiconductors that satisfy the Shockley-Queisser limit, a benchmark for solar cell efficiency. Employing two evolutionary algorithm-based searches, we optimize structures and calculate fitness function using the DFTB method and Gaussian approximation potential. Following the preselection of structures based on energy considerations, we further optimize them using PBEsol DFT. Subsequently, we screen the structures based on their band gap, employing a DFTB method tailored for band gap calculation of silicon crystals. To ensure accurate band gap determination, we employ HSE and GW methods. To validate the structural stability, we employ phonon analysis via linear regression algorithm applied to PBEsol DFT data. Significantly, the structures unveiled in this study are of great importance due to their proven stability from both mechanical and dynamic perspectives. Furthermore, the ductility and low density of certain structures enhance their potential application. We examine the optical properties by studying the imaginary part of the dielectric function by solving the Bethe–Salpeter Equation on top of GW approximation. By calculating the SLME, we achieve an efficiency of 32.7% for Si22 at a thickness of 500 nm. Moreover, the study harnesses various machine learning algorithms to develop a predictive model for the band gap energy of these silicon structures. Input data for machine learning models are derived from structural MBTR and SOAP descriptors, as well as DFT outputs. Notably, the results reveal that features extracted from DFT outperform the MBTR and SOAP descriptors.

An improved permeability estimation model using integrated approach of hybrid machine learning technique and shapley additive explanation

Accurate reservoir permeability determination is crucial in hydrocarbon exploration and production. Conventional methods relying on empirical correlations and assumptions often result in high costs, time consumption, inaccuracies, and uncertainties. This study introduces a novel hybrid machine learning approach to predict the permeability of the Wangkwar formation in the Gunya oilfield, Northwestern Uganda. The group method of data handling with differential evolution (GMDH-DE) algorithm was used to predict permeability due to its capability to manage complex, nonlinear relationships between variables, reduced computation time, and parameter optimization through evolutionary algorithms. Using 1953 samples from Gunya-1 and Gunya-2 wells for training and 1563 samples from Gunya-3 for testing, the GMDH-DE outperformed the group method of data handling (GMDH) and random forest (RF) in predicting permeability with higher accuracy and lower computation time. The GMDH-DE achieved an R2 of 0.9985, RMSE of 3.157, MAE of 2.366, and ME of 0.001 during training, and for testing, the ME, MAE, RMSE, and R2 were 1.3508, 12.503, 21.3898, and 0.9534, respectively. Additionally, the GMDH-DE demonstrated a 41% reduction in processing time compared to GMDH and RF. The model was also used to predict the permeability of the Mita Gamma well in the Mandawa basin, Tanzania, which lacks core data. Shapley additive explanations (SHAP) analysis identified thermal neutron porosity (TNPH), effective porosity (PHIE), and spectral gamma-ray (SGR) as the most critical parameters in permeability prediction. Therefore, the GMDH-DE model offers a novel, efficient, and accurate approach for fast permeability prediction, enhancing hydrocarbon exploration and production.

The cooperative algorithm with auxiliary objectives for the truck and trailer routing problem

<p>In this paper, a cooperative algorithm with auxiliary objectives is proposed to resolve the truck and trailer routing problem. In this proposal, each member of the population does not represent a complete solution as in almost any evolutionary algorithm. In addition, for each member, an aptitude is not possible to compute based only on its codification, because the member has only partial information of the solution. All the members of the population have partial information of the solution. Therefore, these members need to cooperate to obtain an aptitude for the entire population. This way of computing fitness is clearly a gap in the literature, and must be investigated. Moreover, the multi-objectivization approach incorporates an important feature to the proposed algorithm in order to improve its performance, i.e., the multi-objectivization approach permits to identify the best trips using the auxiliary objectives. Enough experimental results are shown that the cooperative algorithm is competitive against other current evolutionary algorithms. There no exist statistically significant difference between the cooperative algorithm and the others.</p>

Using Evolutionary Algorithms and Ab Initio Calculations to Study the Crystal Structure of Intercalated Fe1/3TiS2 Compound

Using Evolutionary Algorithms and Ab Initio Calculations to Study the Crystal Structure of Intercalated Fe1/3TiS2 Compound

Grinding process optimization considering carbon emissions, cost and time based on an improved dung beetle algorithm

During the machining phase, carbon emissions produced by grinding machines account for a significant proportion of the total emissions. Optimizing grinding process parameters is an effective energy-saving measure, which can notably reduce carbon emissions. However, most of the research on parameter optimization related to carbon emissions and energy saving is focused on turning and milling processes, with limited studies on the grinding process. To address this gap, this paper introduces an optimization method for grinding process parameters that considers carbon emissions and seeks to balance emissions, time, and cost in the grinding process. Initially, we quantify the relationship between grinding parameters and optimization objectives and a corresponding multi-objective optimization model is established subsequently. Then an improved multi-objective dung beetle optimization algorithm (INSDBO) is proposed to solve this model. As a case study, we conduct experiments on the machining of a plunger. Simulation results indicate that after optimization, carbon emissions, grinding costs and time have decreased by 11.7%,7.7%, and 6.7% respectively, validating the effectiveness of the proposed optimization method. When compared with the Adaptive Weighted Evolutionary Algorithm (AdaW)、the traditional dung beetle algorithm (NSDBO), and Multi-Stage Multi-Objective Evolutionary Algorithm (MSEA), the improved dung beetle optimization algorithm(INSDBO) showed superior performance. This refined algorithm can suggest optimal parameters in the grinding process, thereby reducing carbon emissions, machining time, and costs.

A fixed point evolution algorithm based on expanded Aitken rapid iteration method for global numeric optimization

Evolution algorithms based on mathematical models whose reproduction operators are derived from mathematical models are a promising branch of metaheuristic algorithms. Aitken rapid iteration method, as a fixed point iteration technique for solving nonlinear equations, performs a procedure of progressive display of a root and generates an iterative sequence that exhibits a convergent trend. Inspired by the idea that an iterative sequence gradually converges to the optimal point during the progressive display procedure of a fixed point of an equation, a fixed point evolution algorithm based on the expanded Aitken rapid iteration method (FPEea) is proposed. To develop FPEea, an expanded Aitken rapid model is first constructed. Then, three polynomials which are derived from the expanded Aitken rapid model are used as the reproduction operator of FPEea to produce offspring. The performance of FPEea is investigated on CEC2019 and CEC2020 benchmark function sets, as well as four engineering design problems. Experimental results show that FPEea is an effective and competitive algorithm compared with several classical evolution algorithms and state-of-the-art algorithms.

Optimization of high-speed angular contact ball bearing for aircraft gearbox utilizing an evolutionary multi-objective algorithm, NSGA-III

We develop a program for predicting bearing performance, including the maximum contact stress, bearing power loss, minimum lubricating film thickness, static safety factor, and dynamic life, and an optimal design for high-speed angular contact ball bearings in aircraft gearboxes using optimization algorithms. A program is developed to predict bearing performance by calculating the loads and displacements of individual balls based on the bearing’s kinematic and static equilibrium equations. Next, an optimization program is developed with non-dominated sorting genetic algorithm III (NSGA-III), wherein calculated bearing performance indicators serve as constraints or objective functions. The performance of individuals within the final Pareto front is evaluated using the inter-criteria correlation (CRITIC) and weighted product methods. The optimization performances of NSGA-III and NSGA-II are compared based on their hypervolume indicators. A solution of the kinematic and static equilibrium equations under the load cases and duty cycles of real aircraft gearboxes is obtained, enhancing the prediction accuracy. Furthermore, optimization, including bearing performance metrics rarely considered in previous studies, is performed. Optimal specifications superior to reference bearings employed in aircraft gearboxes are obtained, enhancing all three objective functions or specific objective functions. The optimization performance of NSGA-III is confirmed to surpass that of conventional NSGA-II.

Evolutionary Optimization for Unmanned Underwater Vehicle Navigation

Unmanned Underwater Vehicles (UUVs) play a vital role in various underwater exploration and surveillance tasks. However, the effective navigation of UUVs in complex underwater environments poses significant challenges due to factors such as limited communication, dynamic currents, and other difficulties. Evolutionary optimization techniques have developed as promising tools for enhancing UUV navigation abilities. This review provides a brief overview of the application of evolutionary optimization algorithms, including genetic algorithms, evolutionary approaches, and particle swarm optimization, in the context of UUV navigation. The fundamental principles of these algorithms and their applications in path planning, path optimization, localization, obstacle avoidance, and mission planning for UUVs are discussed in brief. Through an analysis of existing literature and case studies, the use of evolutionary optimization in improving the navigation efficiency, accuracy, and robustness of UUVs is highlighted. Additionally, current challenges were identified, and future research directions to advance the integration of evolutionary optimization techniques in UUV navigation systems are also discussed. Overall, this aims to provide insights into the potential of evolutionary optimization for addressing the navigation challenges faced by unmanned underwater vehicles and promoting advancements in underwater exploration and surveillance technologies.

Application of Metaheuristics for Multi-Trip Capacitated Vehicle Routing Problem with Time Window

Abstract This study focuses on the delivery routing problem faced by a transport company located in Phuket, Thailand. The goal of this study is to find a daily optimum route in order to minimize the total transportation cost, which comprises fixed costs associated with vehicle rental and variable costs calculated based on factors of travel distance, fuel prices, and fuel consumption. The complexity of this problem is compounded by the fact that customer demand often exceeds a vehicle capacity, in terms of weight and volume. In addition, delivery must be made within specific time windows. To tackle this issue, the delivery routing problem is classified as a multi-trip capacitated vehicle routing problem with time window (MTCVRPTW). Since the problem is NP-hard, an application of metaheuristic is more practical to determine the delivery routing of the company within a reasonable computing time. In this study, Particle Swarm Optimization (PSO) and Differential Evolution (DE) algorithm are applied to solve MTCVRPTW. The numerical results show that DE provides better solution quality compared to those obtained from PSO and company current practices.

Decomposition based multi-objective evolutionary algorithm for energy-saving design of homestay buildings

To improve the prediction accuracy of energy-saving design for homestay buildings, a multi-objective optimization model is studied. A model of multi-objective optimization algorithm for energy efficiency design of home stay buildings based on decomposition multi-objective evolutionary algorithm is proposed. Decomposition based multi-objective evolutionary algorithm is selected. To select the preliminary algorithm for achieving energy-saving design of homestay buildings, it divides the objectives into algorithm determination and model construction and uses multi-objective optimization algorithms to solve the proposed optimization model. The validation results show that the minimum discomfort time calculated using the non-dominated sorting genetic algorithm is 555.30 and the energy consumption is 7.68, while the minimum discomfort time calculated using the non-dominated sorting genetic algorithm method is 896 and the energy consumption is 8.92. With alternative model, the speed of multi-objective Evolutionary algorithm is the fastest, reaching 6105.44 seconds, which is 68.80% lower than the proposed method. With the help of substitutes, the computational speed of the multi-objective particle swarm optimization algorithm has been greatly improved. Its computational speed has reached 1217.231 seconds, while the fastest multi-objective particle swarm optimization algorithm among the four comparison methods is only 3868.591 seconds. Although the individual improvement is not significant, the overall optimization is still considerable and has strategic foresight in the decision-making plan of decision-makers.

Optimization strategies for enhancing diesel engine performance and emissions control with biofuel blends: A multi-objective approach

This study examines the effects of engine compression ratio, load, and biofuel composition on performance, combustion, and emissions. The experimental setup includes testing different compression ratios (16, 17, 18) and loads (25 %, 50 %, 75 % torque) at a fixed speed of 1500 rpm, using Thai standard diesel as the control fuel. Biofuel variations tested include neat biodiesel, neat biokerosene, and blends of 30 % biokerosene with 70 % biodiesel and 50 % biokerosene with 50 % biodiesel. The results show that an increased compression ratio enhances combustion efficiency, reduces brake specific fuel consumption, and improves brake thermal efficiency, although it also leads to higher nitrogen oxide emissions. Biofuels improve brake thermal efficiency due to their higher oxygen content. However, the increased viscosity of biodiesel can hinder fuel atomization, resulting in higher emissions. In contrast, biokerosene improves brake thermal efficiency by facilitating earlier combustion and reducing emissions. Performance is primarily affected by load, while emissions are influenced by both biokerosene content and load. Gradient boosting models and optimization techniques, such as the non-dominated sorting genetic algorithm III (NSGA-III) and adaptive geometry estimation-based multi-objective evolutionary algorithms (AGE-MOEA), produce consistent results, with AGE-MOEA identifying denser optimal points. The findings suggest that optimal biokerosene blends ranging from 20 % to 40 %, across all compression ratios and loads of 50 %–75 %, provide valuable insights for advancing sustainable fuel utilization practices in automotive vehicles.

Two-stage multimodal multi-objective evolutionary algorithm based on global density updating strategy

Two-stage multimodal multi-objective evolutionary algorithm based on global density updating strategy

A clustering-aided multi-agent deep reinforcement learning for multi-objective parallel batch processing machines scheduling in semiconductor manufacturing

Batch processing machines are often the bottleneck in semiconductor manufacturing and their scheduling plays a key role in production management. Pioneer researches on multi-objective batch machines scheduling mainly focus on evolutionary algorithms, failing to meet the online scheduling demand. To deal with the challenges confronted by incompatible job families, dynamic job arrivals, capacitated machines and multiple objectives, we propose a clustering-aided multi-agent deep reinforcement learning approach (CA-MADRL) for the scheduling problem. Specifically, to achieve diverse nondominated solutions, an offline multi-objective scheduling algorithm named Multi-Subpopulation fast elitist Non-Dominated Sorting Genetic Algorithm (MS-NSGA-II) is firstly developed to obtain the Pareto Fronts, and a clustering algorithm based on cosine distance is employed to analyze the distribution of Pareto frontier solution, which would be used to guide reward functions design in multi-agent deep reinforcement learning. To realize multi-objective optimization, several reinforcement learning base models are trained for different optimization directions, each of which composed of batch forming agent and batch scheduling agent. To alleviate time complexity of model training, a parameter sharing strategy is introduced between different reinforcement learning base model. By validating the proposed approach with 16 instances designed based on actual production data from a semiconductor manufacturing company, it has been demonstrated that the approach not only meets the high-frequency scheduling requirements of manufacturing systems for parallel batch processing machines but also effectively reduces the total job tardiness and machine energy consumption.

AdaGuiDE: An adaptive and guided differential evolution for continuous optimization problems

Differential evolution (DE) has been proven as a simple yet powerful meta-heuristic algorithm on tackling continuous optimization problems. Nevertheless most existing DE methods still suffer from certain drawbacks including the use of ineffective mechanisms to adjust mutation strategies and their control parameters that may possibly mislead the search directions, and also the lack of intelligent guidance and reset mechanisms to escape from local optima. Therefore, to enhance the adaptability of DE-based search frameworks and the robustness on optimizing complex problems full of local optima, an adaptive and guided differential evolution (AdaGuiDE) algorithm is proposed. Essentially, the adaptability of the AdaGuiDE search framework is enhanced by three schemes to iteratively refine the search behaviour at two different levels. At the macroscopic level, the AdaGuiDE search framework revises the existing adaptive mechanism for selecting appropriate DE search strategies by counting the actual contributions in terms of solution quality. In addition, the adaption strategy is extended to the microscopic level where a penalty-based guided DE search is employed to guide the search escaping from local optima through temporarily penalizing the local optima and their neighborhood. Furthermore, a systematic boundary revision scheme is introduced to dynamically adjust the search boundary for locating any potential regions of interest during the search. For a rigorous evaluation of the proposed search framework, the AdaGuiDE algorithm is compared against other well-known meta-heuristic approaches on three sets of benchmark functions involving different dimensions in which the AdaGuiDE algorithm attained remarkable results especially on the high-dimensional and complex optimization problems. More importantly, the proposed AdaGuiDE framework shed lights on many possible directions to further enhance the adaptability of the underlying DE-based search strategies in tackling many challenging real-world applications.

Two-stage multi-objective optimization based on knowledge-driven approach: A case study on production and transportation integration

The multi-objective evolutionary algorithm (MOEA) has been widely applied to solve various optimization problems. Existing search models based on dominance and decomposition are extensively used in MOEAs to balance convergence and diversity during the search process. In this paper, we propose for the first time a two-stage MOEA based on a knowledge-driven approach (TMOK). The first stage aims to find a rough Pareto front through an improved nondominated sorting algorithm, whereas the second stage incorporates a dynamic learning mechanism into a decomposition-based search model to reasonably allocate computational resources. To further speed up the convergence of TMOK, we present a Markov chain-based TMOK (MTMOK), which can potentially capture variable dependencies. In particular, MTMOK employs a marginal probability distribution of single variables and an N-state Markov chain of two adjacent variables to extract valuable knowledge about the problem solved. Moreover, a simple yet effective local search is embedded into MTMOK to improve solutions through variable neighborhood search procedures. To illustrate the potential of the proposed algorithms, we apply them to solve a distributed production and transportation-integrated problem encountered in many industries. Numerical results and comparisons on 54 test instances with different sizes verify the effectiveness of TMOK and MTMOK. We have made the 54 instances and the source code of our algorithms publicly available to support future research and real-life applications.