Exploration Capabilities Research Articles

Disturbance rejecting PID-FF controller design of a non-ideal buck converter using an innovative snake optimizer with pattern search algorithm

The optimal design of a proportional-integral-derivative controller with two cascaded first-order low-pass filters (PID-FF) for non-ideal buck converters faces significant challenges, including effective disturbance rejection, robustness to parameter variations, and the mitigation of high-frequency signal noise, with existing approaches often struggling and leading to suboptimal performance in practical applications. This study addresses these challenges by introducing a constraint on the open-loop crossover frequency to mitigate high-frequency noise and ensuring the controller prioritizes maintaining constant output voltage and robust responsiveness to input voltage and load current variations. This study also introduces an innovative metaheuristic algorithm, the opposition-based snake optimizer with pattern search (OSOPS), designed to address these limitations. OSOPS enhances the Snake Optimizer (SO) by integrating opposition-based learning (OBL) and Pattern Search (PS), thereby improving its exploration and exploitation capabilities. The proposed algorithm design includes a crossover frequency constraint aimed at counteracting high-frequency noise and ensuring robust performance under diverse disturbances. The efficacy of the OSOPS algorithm is demonstrated through rigorous statistical box plot analysis and convergence response comparisons with the original SO algorithm. Additionally, we systematically compare the performance of the OSOPS-based PID–FF–controlled non-ideal buck converter system against systems utilizing the original SO algorithm and the classical pole placement (PP) method. This evaluation encompasses transient and frequency responses, disturbance rejection, and robustness analysis. The results reveal that the OSOPS-based system outperforms the SO- and PP-based systems with 14.21 % and 32.10 % faster rise times, along with 15.38 % and 84.95 % faster settling times, respectively. The OSOPS and SO systems also exhibit higher bandwidths, exceeding the PP-based system by 18.74 % and 17.03 %, respectively. By addressing the key challenges in PID-FF controller design for non-ideal buck converters, this study provides a substantial advancement in control strategy, promising enhanced performance in practical applications.

CMGWO: Grey wolf optimizer for fusion cell-like P systems

The grey wolf optimizer is a widely used parametric optimization algorithm. It is affected by the structure and rank of grey wolves and is prone to falling into the local optimum. In this study, we propose a grey wolf optimizer for fusion cell-like P systems. Cell-like P systems can parallelize computation and communicate from cell membrane to cell membrane, which can help the grey wolf optimizer jump out of the local optimum. Design new convergence factors and use different convergence factors in other cell membranes to balance the overall exploration and utilization capabilities of the algorithm. At the same time, dynamic weights are introduced to accelerate the convergence speed of the algorithm. Experiments are performed on 24 test functions to verify their global optimization performance. Meanwhile, a support vector machine model optimized by the grey wolf optimizer for fusion cell-like P systems has been developed and tested on six benchmark datasets. Finally, the optimizing ability of grey wolf optimizer for fusion cell-like P systems on constrained optimization problems is verified on three real engineering design problems. Compared with other algorithms, grey wolf optimizer for fusion cell-like P systems obtains higher accuracy and faster convergence speed on the test function, and at the same time, it can find a better parameter set stably for the optimization of support vector machine parameters, in addition to being more competitive on constrained engineering design problems. The results show that grey wolf optimizer for fusion cell-like P systems improves the searching ability of the population, has a better ability to jump out of the local optimum, has a faster convergence speed, and has better stability.

Optimistic sequential multi-agent reinforcement learning with motivational communication

Centralized Training with Decentralized Execution (CTDE) is a prevalent paradigm in the field of fully cooperative Multi-Agent Reinforcement Learning (MARL). Existing algorithms often encounter two major problems: independent strategies tend to underestimate the potential value of actions, leading to the convergence on sub-optimal Nash Equilibria (NE); some communication paradigms introduce added complexity to the learning process, complicating the focus on the essential elements of the messages. To address these challenges, we propose a novel method called Optimistic Sequential Soft Actor Critic with Motivational Communication (OSSMC). The key idea of OSSMC is to utilize a greedy-driven approach to explore the potential value of individual policies, named optimistic Q-values, which serve as an upper bound for the Q-value of the current policy. We then integrate a sequential update mechanism with optimistic Q-value for agents, aiming to ensure monotonic improvement in the joint policy optimization process. Moreover, we establish motivational communication modules for each agent to disseminate motivational messages to promote cooperative behaviors. Finally, we employ a value regularization strategy from the Soft Actor Critic (SAC) method to maximize entropy and improve exploration capabilities. The performance of OSSMC was rigorously evaluated against a series of challenging benchmark sets. Empirical results demonstrate that OSSMC not only surpasses current baseline algorithms but also exhibits a more rapid convergence rate.

Modified snake optimizer based multi-level thresholding for color image segmentation of agricultural diseases

Image segmentation is crucial for early identification and diagnosis of crop diseases in agriculture. It helps identify disease areas and characteristics, laying the groundwork for disease diagnosis and treatment. However, color image thresholding segmentation method faces challenges in finding the optimal threshold as the number of thresholds increases, which affects segmentation quality. In this paper, a modified snake optimizer (MSO) is proposed to address the color image thresholding segmentation problem using Kapur’s entropy as the objective function. MSO incorporates a dynamic adaptive parameter adjustment method. The improved global position update formula introduces guidance from the optimal individual and disturbance from random individuals, effectively achieving a balance between global and local search capabilities. A dynamic parameter adjustment method is added to accelerate convergence speed during snake movement to food. Lévy flight is introduced to the Flight mode to help the algorithm escape local extremums. A balancing strategy is implemented in the Mating mode, incorporating guidance from the optimal individual and information exchange between sub-populations, enabling balanced exploration and local exploitation capabilities. The hill-climbing jump operation for the optimal individual is added to help the algorithm overcome local stagnation. The proposed MSO is evaluated on CEC 2017 test functions and color test images, and the obtained results are compared with other segmentation methods and other intelligent optimization algorithms. The results demonstrate that MSO exhibits stable and excellent performance in both complex global optimization problems and color image thresholding segmentation problems. Finally, MSO is applied to segment rice disease images, and the results reveal significantly better segmentation performance compared to other algorithms. MSO shows great potential in solving the thresholding segmentation problem for agricultural disease images, thereby assisting in the accurate identification, diagnosis, and treatment of agricultural diseases and insect pests.

Credit card fraud detection using the brown bear optimization algorithm

Fraud detection in banking systems is crucial for financial stability, customer protection, reputation management, and regulatory compliance. Machine Learning (ML) is vital in improving data analysis, real-time fraud detection, and developing fraud techniques by learning from data and adjusting detection strategies accordingly. Feature Selection (FS) is essential for enhancing fraud detection through ML to achieve optimal model accuracy. This is because it helps to eliminate the negative impact of redundant and irrelevant attributes. To enhance the accuracy of the given dataset, the researchers utilized multiple methods to determine the most fitting features. However, it is important to note that when implementing these methods on datasets with larger feature sizes, they may encounter issues with local optimality. Despite this, the researchers continue to work on improving the effectiveness of these methods. This study presents an effective methodology based on the Brown-Bear Optimization (BBO) algorithm to enhance the capacity to accurately identify financial CCF transactions by recognizing pertinent features. BBO has balanced capabilities to reduce dimensionality while enhancing classification accuracy. It is improved by adjusting the positions randomly to enhance exploration and exploitation capabilities, and then it is cloned into a binary variant named Binary BBOA (BBBOA). The Support Vector Machine (SVM), k-nearest Neighbor (k-NN), and Xgb-tree are the ML classifiers used with the suggested methodology. On the Australian credit dataset, the proposed methodology is compared with the basic BBOA and ten current optimizers, such as Binary African Vultures Optimization (BAVO), Binary Salp Swarm Algorithm (BSSA), Binary Atom Search Optimization (BASO), Binary Henry Gas Solubility Optimization (BHGSO), Binary Harris Hawks Optimization (BHHO), Binary Bat Algorithm (BBA), Binary Particle Swarm Optimization (BPSO), Binary Grasshopper Optimization Algorithm (BGOA), and Binary Sailfish Optimizer (BSFO). Regarding Wilcoxon’s rank-sum test (α=0.05), the superiority and effective consequence of the presented methodology are clear on the utilized dataset and got an accuracy of classification up to 91% in the utilized dataset combined with an attribute reduction length down to 67%. The proposed methodology is further validated using 10 benchmark datasets and outperformed its competitors in most utilized datasets regarding different performance measures. In the end, the proposed methodology is further validated using ten benchmark datasets from the UCI repository. It outperformed its competitors in most of the utilized datasets regarding different performance measures.

Hybrid Tiki Taka and Mean Differential Evolution based Weibull distribution: A comprehensive approach for solar PV modules parameter extraction with Newton-Raphson optimization

Effective parameter extraction is crucial in modeling and analyzing complex systems, particularly photovoltaic (PV) cells/modules. Therefore, it is essential to develop a robust optimization model that can effectively determine the optimal parameters of PV models. This study introduces a novel metaheuristic algorithm, Tiki Taka Algorithm (TTA), inspired by sports strategies, particularly the renowned tiki-taka style. The innovation lies in the hybridization of TTA with the Mean Differential Evolution based on Weibull distribution (MDEW). The resultant optimal parameters obtained from this hybridization serve as the initial guess for Newton-Raphson (NR), a critical step that ensures the estimated current closely aligns with the measured current, leading to a minimized Root Mean Square Error (RMSE). The hybrid approach leverages the excellent exploration capabilities of Weibull distribution and the exploitation strength of the Mean Differential Evolution (MeanDE) mutation, offering a comprehensive solution for navigating complex optimization landscapes. The proposed TTA-MDEW effectively identifies various parameters in PV models, including single diodes, double diodes, and PV modules. The findings show that TTA-MDEW holds its ground against the most sophisticated optimization methods in terms of reliability, accuracy, and speed of convergence. Additionally, data from real-world manufacturer datasheets reveal that our method delivers exceptionally precise results under varying irradiance and temperature conditions. Therefore, these outcomes establish the TTA-MDEW as an effective tool for extracting precise parameters from various PV models, enhancing the modeling of PV systems.

Modified dung beetle optimizer with multi-strategy for uncertain multi-modal transport path problem

Abstract Uncertain multi-modal transport path optimization (UMTPO) is a combined optimization non-deterministic polynomial-time hard problem. Its goal is to determine a path with the lowest total transportation cost and carbon emissions from the starting point to the destination. To effectively address this issue, this article proposes a modified dung beetle optimizer (DBO) to address it. DBO is a swarm-based metaheuristic optimization algorithm that has the features of a fast convergence rate and high solution accuracy. Despite this, the disadvantages of weak global exploration capability and falling easily into local optima exist. In this article, we propose a modified DBO called MSHDBO for function optimization and to solve the UMTPO problem. However, for the vast majority of metaheuristic algorithms, they are designed for continuous problems and cannot directly solve discrete problems. Therefore, this article employs a priority based encoding and decoding method to solve the UMTPO problem. To verify the performance and effectiveness of the MSHDBO algorithm, we compared it with other improved versions of the DBO algorithm used in the literature. We confirmed the excellent performance of MSHDBO using 41 benchmark test functions from the IEEE CEC 2017 test suite and IEEE CEC 2022 test suite. Additionally, we compared the MSHDBO algorithm with 10 other state-of-the-art metaheuristic optimization algorithms through a practical UMTPO problem. The experimental results indicated that the MSHDBO algorithm achieved very good performance when solving the UMTPO problem.

Application of Gray Wolf Particle Filter Algorithm Based on Golden Section in Wireless Sensor Network Mobile Target Tracking

In order to address the issue of low tracking accuracy caused by particle depletion in the particle filter, a mobile target tracking algorithm tailored for wireless sensor networks (WSNs) is presented. This algorithm, based on the golden-section gray wolf particle filter (PF), represents a novel approach to target tracking. The algorithm’s originality lies in its ability to guide the particle swarm toward regions of higher weights, thereby striking a balance between global and local exploration capabilities. This not only alleviates issues related to sample depletion and local extrema but also enhances the diversity of the particle swarm, significantly improving tracking performance. To assess the effectiveness of the proposed algorithm, a series of simulation experiments were conducted, comparing it with the extended Kalman filter (EKF) and the standard PF algorithm. The experiments employed a constant velocity circular motion model (CM) for filtering and tracking. The root mean square error metric demonstrated a significant reduction in error of 57% and 37% in comparison to the extended Kalman filter (EKF) and the particle filter (PF), respectively. This serves to illustrate the superiority of our method in enhancing tracking accuracy.

Coopetition, exploration and exploitation capabilities, and growth performance in digital healthcare ventures.

Studies focusing on coopetition and dynamic capabilities have expanded significantly over the past several decades. Coopetition strategy and dynamic capabilities are increasingly recognised as sources of sustained competitive advantage. The purpose of this paper is to provide a better understanding of the factors driving growth performance in digital healthcare ventures by examining the role of coopetition, exploration and exploitation capabilities, and environmental uncertainty. While numerous studies have examined the competitive advantage of coopetition, its specific contribution to the growth of ventures in the digital realm remains less explored. Clarifying the strategic role of coopetition in driving growth performance is critical for delineating the intricate relationship between coopetition and growth performance, particularly in the context of digital healthcare ventures. To fill in this research gap, this study uses coopetition theory and dynamic capabilities theory to look at how exploration and exploitation capabilities, as well as environmental uncertainty, affect the relationship between coopetition and growth performance in digital healthcare ventures. We collected a total of 338 questionnaires from Chinese digital healthcare ventures between March 2023 and August 2023. We conducted data analysis using SPSS 26.0 and its macro-program PROCESS. Our results confirm that coopetition has a positive effect on growth performance in digital healthcare ventures. Furthermore, exploration and exploitation capabilities fully mediate the relationship between coopetition and growth performance. Moreover, environmental uncertainty significantly and distinctively moderates the impact of exploration and exploitation capabilities on growth performance. This study contributes to the existing literature by providing deeper insight into the relationship between coopetition and growth performance in digital healthcare ventures. It also offers important practical implications for public health improvement and socio-economic development.

Hybrid Salp Swarm and Improved Whale Optimization Algorithm‐based clustering scheme for improving network lifespan in wireless sensor networks

SummaryWireless sensor networks (WSNs) represent the collection of restricted energy sensor nodes that are deployed in an area of target for gathering potential environment data for decision‐making with respect to their objective of application. However, the implementation of energy‐effective data gathering strategies in large‐scale WSNs is the most challenging due to the limited energy resources. Clustering‐based data gathering strategies are identified to be quite effective for energy saving that directly attributes to extended network lifetime. Moreover, optimal path amid the cluster head (CH) and sink node needs to be selected for sustaining energy efficiency and improving network lifespan. In this article, Hybrid Salp Swarm and Improved Whale Optimization Algorithm (HSSIWOA)‐based clustering scheme is proposed for improving the network lifetime and routing optimization with maximized energy efficacy. It integrated the exploration capability of Salp Swarm Optimization Algorithm (SSOA) with exploitation benefits of Improved Whale Optimization Algorithm (IWOA) for balancing the trade‐off between the rate of exploration and exploitation during CH selection process. It utilized the parameters of residual energy, load balance, intra‐cluster distance, inter‐cluster distance, and node centrality into account during the process of fitness evaluation. It performed well by constructing an optimized number of clusters, such that energy stability and network lifetime are maintained in the network. The experimental results of the proposed HSSIWOA scheme confirmed extended network lifetime of 21.64%, minimized energy utilization of 23.42%, and maximized throughput of 18.56%, better than the baseline approaches.

Motion frequency exploration based force separator for surgical robots interacting with a beating heart

Robotics-assisted beating heart surgery holds significant potential for application as it can reduce the risks of infection. A crucial requirement in beating heart surgery is the real-time and accurate feedback of the interaction forces between the end-effector and cardiac tissues. The primary challenge is developing a sensorless scheme to separate the beating motion-coupled force (MCF) from the robot dynamic state-coupled force (SCF). Acquiring the accurate beating frequency before surgery is often challenging, which limits the use of conventional force observers. To address these difficulties, this article proposes an online force separation scheme. Specifically, we establish a robot-cardiac tissue coupled model that considers robot dynamics, force generation mechanisms, and heart motion characteristics. Based on this, we design a motion frequency exploration-based force separator (MSEFS), utilizing an online expectation–maximization procedure for the joint estimation of the motion state and frequency parameter. Simulation results demonstrate that the proposed scheme surpasses existing force estimation schemes in performance due to its capability for motion frequency exploration.

Many-objective flexible job-shop scheduling based on a loose non-dominated sorting genetic algorithm

ABSTRACT To address the challenges of solving the many-objective flexible job-shop scheduling problem, this study proposes a loose non-dominated sorting genetic algorithm III (LNSGA-III), an enhancement of the non-dominated sorting genetic algorithm III (NSGA-III). First, a loose dominance principle is proposed to overcome the shortcomings of low selection pressure and slow convergence under the Pareto dominance principle. Next, a novel crossover operator without repair, named improved order crossover, is presented to fully preserve the characteristics of exchanged operations and enhance the exploration capability of the algorithm. Experimental studies involve testing algorithms on some typical scheduling instances with six simultaneously optimized objectives. The primary metric for algorithm comparison is the hypervolume, with additional investigation for statistical significance. Other metrics, including coverage, convergence and diversity, are also used for comparison. The experimental results demonstrate the effectiveness of the proposed enhancements, showcasing the significant superiority of the algorithm over some state-of-the-art alternatives.

Many-objective artificial hummingbird algorithm: an effective many-objective algorithm for engineering design problems

Abstract Many-objective optimization presents unique challenges in balancing diversity and convergence of solutions. Traditional approaches struggle with this balance, leading to suboptimal solution distributions in the objective space especially at higher number of objectives. This necessitates the need for innovative strategies to adeptly manage these complexities. This study introduces a Many-Objective Artificial Hummingbird Algorithm (MaOAHA), an advanced evolutionary algorithm designed to overcome the limitations of existing many-objective optimization methods. The objectives are to improve convergence rates, maintain solution diversity, and achieve a uniform distribution in the objective space. MaOAHA implements information feedback mechanism (IFM), reference point-based selection and association, non-dominated sorting, and niche preservation. The IFM utilizes historical data from previous generations to inform the update process, thereby improving the algorithm’s the exploration and exploitation capabilities. Reference point-based selection, along with non-dominated sorting, ensures solutions are both close to the Pareto front and evenly spread in the objective space. Niche preservation and density estimation strategies are employed to maintain diversity and prevent overcrowding. The comprehensive experimental analysis benchmarks MaOAHA against four leading algorithms viz. Many-Objective Gradient-Based Optimizer, Many-Objective Particle Swarm Optimizer, Reference Vector Guided Evolutionary Algorithm, and Nondominated Sorting Genetic Algorithm III. The DTLZ1–DTLZ7 benchmark sets with four, six, and eight objectives and five real-world problems (RWMaOP1–RWMaOP5) are considered for performance assessment of the selected algorithms. The results demonstrate that internal parameter-free MaOAHA significantly outperforms its counterparts, achieving better generational distance by up to 52.38%, inverse generational distance by up to 38.09%, spacing by up to 56%, spread by up to 71.42%, hypervolume by up to 44%, and runtime by up to 52%. These metrics affirm the MaOAHA’s capability to enhance the decision-making processes through its adept balance of convergence, diversity, and uniformity.

Achieving accurate trajectory predicting and tracking for autonomous vehicles via reinforcement learning-assisted control approaches

In complex urban traffic scenarios, autonomous vehicles face significant challenges in adapting to diverse and dynamic traffic conditions. Reward-based reinforcement learning has emerged as an effective approach to tackle these challenges. This paper presents a novel method that combines deep reinforcement learning with automotive dynamics systems. Building upon the Double Deep Q-learning algorithm, our approach integrates a Recurrent Neural Network with Gated Recurrent Units to enhance the environmental exploration capabilities of autonomous vehicles. To obtain more precise reward values, we introduce a trajectory tracking algorithm based on a combination of proportional-integral-derivative control and feedforward control within the automotive dynamics system. The proportional-integral-derivative controller is utilized for longitudinal control, while the Error-Optimized feedforward controller enhances lateral control, thereby improving trajectory tracking accuracy. Finally, extensive simulation experiments are conducted to evaluate the proposed method, comparing it against other baseline methods in terms of vehicle following and lane-changing scenarios. The results demonstrate that our approach significantly improves both the reward values and control performance of the algorithm.

Enhancing slime mould algorithm for engineering optimization: leveraging covariance matrix adaptation and best position management

Abstract The slime mould algorithm (SMA), as an emerging and promising swarm intelligence algorithm, has been studied in various fields. However, SMA suffers from issues such as easily getting trapped in local optima and slow convergence, which pose challenges when applied to practical problems. Therefore, this study proposes an improved SMA, named HESMA, by incorporating the covariance matrix adaptation evolution strategy (CMA-ES) and storing the best position of each individual (SBP). On one hand, CMA-ES enhances the algorithm’s local exploration capability, addressing the issue of the algorithm being unable to explore the vicinity of the optimal solution. On the other hand, SBP enhances the convergence speed of the algorithm and prevents it from diverging to other inferior solutions. Finally, to validate the effectiveness of our proposed algorithm, this study conducted experiments on 30 IEEE CEC 2017 benchmark functions and compared HESMA with 12 conventional metaheuristic algorithms. The results demonstrated that HESMA indeed achieved improvements over SMA. Furthermore, to highlight the performance of HESMA further, this study compared it with 13 advanced algorithms, and the results showed that HESMA outperformed these advanced algorithms significantly. Next, this study applied HESMA to five engineering optimization problems, and the experimental results revealed that HESMA exhibited significant advantages in solving real-world engineering optimization problems. These findings further support the effectiveness and practicality of our algorithm in addressing complex engineering design challenges.

Heterogeneous pbest-guided comprehensive learning particle swarm optimization

The balance between exploration and exploitation in the particle swarm optimization (PSO) algorithm is often discussed but has not been well solved. To further improve the capabilities of exploration and exploitation in the search space, the aim of this study is to focus on a novel comprehensive learning strategy for the PSO algorithm, which is named the heterogeneous pbest-guided comprehensive learning particle swarm optimizer (HPBPSO). In this algorithm, the population is divided into two subpopulations. In the exploration subpopulation, a pbest-guided mechanism is designed for obtaining better particles’ personal best information. Meanwhile, the non-elite personal best particles learn from elite personal best particles by using dynamic crossover strategy. In the exploitation subpopulation, in order to fully leverage the benefits of learning from high-quality individuals, the learning process is divided into two distinct categories: elite individual learning and intragroup learning. Furthermore, intergroup perturbation is designed to accelerate convergence performance. The experiments on classical functions are firstly used to verify the effectiveness and mutuality of the proposed strategies. Moreover, the performance of the proposed algorithm is evaluated on two well-known benchmarks and medical image segmentation problem. According to the statistical results, the HPBPSO algorithm is not only better than the other existing state-of-the-art PSO variants and metaheuristic evolutionary algorithms, but also applicable to real-world optimization problems.

A multi-strategy driven reinforced hierarchical operator in the grey wolf optimizer for feature selection

In this study, a multi-strategy driven reinforced hierarchical operator for a grey wolf optimizer (RHGWO) is proposed to solve the feature selection (FS) problem, whereby tedious data are converted into information and often modeled as a combinatorial optimization problem. First, a multi-strategy mechanism is proposed to provide the GWO algorithm with exploration capabilities, including memory-based diversity and Lévy flight-based extension search. Next, a hierarchical segmentation technique is proposed to allocate exploration and exploitation, thereby providing exploration capability for superior wolves to search diverse regions and exploitation capability for inferior wolves to converge to the promising area. Subsequently, a chaotic elite learning strategy is designed for leaders to prevent misdirection. Finally, a more rational nonlinear parameter transformation is designed. Multiple experiments validate the adaptability and versatility of the proposed RHGWO algorithm.

Equilibrium optimizer-based harmony search algorithm with nonlinear dynamic domains and its application to real-world optimization problems

Harmony Search (HS) algorithm is a swarm intelligence algorithm inspired by musical improvisation. Although HS has been applied to various engineering problems, it faces challenges such as getting trapped in local optima, slow convergence speed, and low optimization accuracy when applied to complex problems. To address these issues, this paper proposes an improved version of HS called Equilibrium Optimization-based Harmony Search Algorithm with Nonlinear Dynamic Domains (EO-HS-NDD). EO-HS-NDD integrates multiple leadership-guided strategies from the Equilibrium Optimizer (EO) algorithm, using harmony memory considering disharmony and historical harmony memory, while leveraging the hidden guidance direction information from the Equilibrium Optimizer. Additionally, the algorithm designs a nonlinear dynamic convergence domain to adaptively adjust the search space size and accelerate convergence speed. Furthermore, to balance exploration and exploitation capabilities, appropriate adaptive adjustments are made to Harmony Memory Considering Rate (HMCR) and Pitch Adjustment Rate (PAR). Experimental validation on the CEC2017 test function set demonstrates that EO-HS-NDD outperforms HS and nine other HS variants in terms of robustness, convergence speed, and optimization accuracy. Comparisons with advanced versions of the Differential Evolution (DE) algorithm also indicate that EO-HS-NDD exhibits superior solving capabilities. Moreover, EO-HS-NDD is applied to solve 15 real-world optimization problems from CEC2020 and compared with advanced algorithms from the CEC2020 competition. The experimental results show that EO-HS-NDD performs well in solving real-world optimization problems.

Multi-subswarm cooperative particle swarm optimization algorithm and its application

Particle swarm optimization (PSO) is a classical evolutionary algorithm and has been widely used to solve continuous optimization problems. However, the performance of the PSO algorithm is highly sensitive to its control parameters and learning strategies. To address this problem, a multi-subswarm cooperative particle swarm optimization algorithm (MSC-PSO) is proposed in this paper. In MSC-PSO, firstly, a population muti-subswarm division method is designed to enhance the global exploration capability. Secondly, a level-based particle adaptive inertia weight strategy is introduced to adjust control parameters. Finally, a level-based update learning mechanism is used for particles adaptive selection learning strategy. The performance of the MSC-PSO is evaluated by the CEC2020 test suite, and five heuristic algorithms are compared with the MSC-PSO in the experiments. The experimental results demonstrate that the proposed MSC-PSO algorithm has significant advantages in terms of convergence speed and solving optimal solutions. Furthermore, the proposed MSC-PSO algorithm is used to solve the plant protection unmanned aerial vehicles (UAV) path planning problem. The experimental results proved that the proposed MSC-PSO algorithm effectively solves the real-world UAV path planning problem, and achieves at most a 34 % reduction in round-trip distance and a 24.1 % reduction in total non-spraying time compared to classical PSO.

Rolling bearing fault diagnosis based on DRS frequency spectrum image and improved DQN

Deep learning may encounter challenges in fault diagnosis, such as exploration capability, long-term planning, and handling non-deterministic factors. The paper introduces a novel fault diagnosis method for rolling bearings combining deep Q-network (DQN) with discrete random separation (DRS) frequency spectrum images. DRS can be used to separate the deterministic components and random components of the fault signal and extract the fault feature very effectively. The improved DQN incorporates the atrous spatial pyramid pooling module for multiscale contextual fault feature extraction, enhancing diagnosis accuracy. Various deep networks, including convolutional neural network, ResNet18, traditional DQN, and the improved DQN, are employed with different frequency spectrum images (power spectral density, cepstrum, and DRS) for diagnosing bearing faults. Simulation results demonstrate that combining DRS frequency spectrum images with the improved DQN enhances fault diagnosis accuracy across diverse conditions. Generalization tests reveal strong capability of the proposed method in handling conditions different from the training data. Validation tests on difficult-to-diagnose fault data from the CWRU-bearing dataset demonstrate commendable performance of the improved DQN, even on difficult datasets. Finally, validation tests using the XJTU–SY bearing dataset reaffirm the excellent performance and robust adaptability of the improved DQN in conjunction with DRS frequency spectrum images.