Article
Energy & Fuels
Guanyong Zhang, Bizhong Xia, Jiamin Wang
Summary: This paper proposes a series of intelligent SOC estimation methods using BPNN based on the L-M algorithm, and compares them with the EKF method. By optimizing BPNN with GA and PSO algorithms, the estimated accuracy and convergence speed are improved. The intelligent SOC estimation methods proposed in this paper demonstrate high accuracy and strong robustness through experimental validation.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Computer Science, Artificial Intelligence
Lalit Kumar, Manish Pandey, Mitul Kumar Ahirwal
Summary: The computational time of swarm optimization algorithms, including Particle Swarm Optimization (PSO), is increased due to the large number of decision variables in complex problems. A new Global Best-Worst Particle Swarm Optimization (GBWPSO) algorithm, combining PSO and Jaya algorithm, is proposed to provide a more parallel version of the algorithm. The proposed algorithm outperforms other parallel PSO versions and Jaya algorithm in terms of computational time and optimal solution.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Bin Bai, Junyi Zhang, Xuan Wu, Guang Wei Zhu, Xinye Li
Summary: A new reliability prediction model, SDWPSO-BPNN, combining particle swarm optimization and neural networks, has been developed and demonstrated better accuracy and search ability in reliability prediction in engineering systems.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Construction & Building Technology
Lu Li, Yumiao Zhang, Jimmy C. H. Fung, Huamin Qu, Alexis K. H. Lau
Summary: This study aims to rapidly predict and optimize indoor air quality (IAQ) by using computational fluid dynamics (CFD) combined with back propagation neural network (BPNN) and particle swarm optimizer (PSO) algorithm. The BPNN-PSO algorithm reduces indoor air pollutants concentration and computational costs compared to other methods.
BUILDING AND ENVIRONMENT
(2022)
Article
Chemistry, Analytical
Xuhao Li, Lifu Gao, Xiaohui Li, Huibin Cao, Yuxiang Sun
Summary: Six-axis force/torque sensors are widely used in manipulators, but they are easily damaged in adverse environments. Self-restoration methods can enhance the robustness and practicality of the sensors. The coupling effect allows inferring the damaged dimension based on other regular dimensions. By using the particle swarm optimization algorithm, the hyperparameters of BPNN can be tuned to establish relationships among the dimensions. The proposed PSO-BPNN fault restoration method proves to be viable and practical, restoring the F/T sensor to its original measurement precision.
Article
Engineering, Aerospace
Xiande Wu, Yuheng Yang, Yuqi Sun, Yaen Xie, Xiangshuai Song, Bing Huang
Summary: This paper proposes a novel region splitting algorithm based on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) algorithm to achieve high coverage, low overlap ratio, and efficient satellite utilization in regional observation. The encoding method and parallel iterative optimal method are detailed. Finally, simulation results validate the proposed algorithm and analyze the effects of algorithm parameters.
Article
Multidisciplinary Sciences
Pham Vu Hong Son, Nghiep Trinh Nguyen Dang
Summary: The study introduces a hybrid multi-verse optimizer model (hDMVO) that combines the multi-verse optimizer (MVO) and the sine cosine algorithm (SCA) to solve the discrete time-cost trade-off problem (DTCTP). The optimality of the algorithm is evaluated using 23 benchmark test functions, demonstrating its competitiveness with other algorithms. The performance of hDMVO is further evaluated using four benchmark test problems, showing its superiority in time-cost optimization for large-scale and complex projects compared to previous algorithms.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Jian Peng, Yibing Li, Hongwei Kang, Yong Shen, Xingping Sun, Qingyi Chen
Summary: This study investigates the relationship between information propagation speed and algorithm performance in particle swarm optimization, finding a strong negative correlation with population diversity in early iterations. It also highlights that the impact of population topology on optimization results is similar when solving problems with the same property.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Chemistry, Multidisciplinary
Weihang Dong, Xianqing Xiong, Ying Ma, Xinyi Yue
Summary: A novel woodworking tool wear condition monitoring method is proposed in this study, utilizing limiting arithmetic average filtering method and PSO-BP neural network algorithm, to accurately monitor the woodworking tool wear conditions under different milling parameters.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Aerospace
Tianpeng Huang, Deqing Huang, Na Qin, Yanan Li
Summary: This paper proposes an integrated approach in artificial potential field to avoid obstacles in path planning and develops a parallel search algorithm to address the issue of unreachable target. Additionally, a nonlinear disturbance observer and backstepping controller are designed to eliminate attitude tracking errors.
INTERNATIONAL JOURNAL OF AEROSPACE ENGINEERING
(2021)
Article
Multidisciplinary Sciences
El-Sayed M. El-kenawy, Seyedali Mirjalili, Nima Khodadadi, Abdelaziz A. Abdelhamid, Marwa M. Eid, M. El-Said, Abdelhameed Ibrahim
Summary: This study proposes a high-accuracy wind speed prediction method based on a weighted ensemble model. The proposed algorithm outperforms existing algorithms and demonstrates stability and robustness through statistical analysis.
Article
Peripheral Vascular Disease
Yan Yan, Rong Chen, Zihua Yang, Yong Ma, Jialu Huang, Ling Luo, Hao Liu, Jian Xu, Weiying Chen, Yuanlin Ding, Danli Kong, Qiaoli Zhang, Haibing Yu
Summary: The back propagation neural network optimized by the particle swarm optimization algorithm showed the best fitting and prediction performance. The risk factors related to hypertension were identified using the mean influence value algorithm, and a risk prediction model was constructed.
JOURNAL OF CLINICAL HYPERTENSION
(2022)
Article
Computer Science, Artificial Intelligence
Xiaoyong Tang, Cheng Shi, Tan Deng, Zhiqiang Wu, Li Yang
Summary: The study introduces a random matrix particle swarm optimization scheduling algorithm for cloud service scheduling, as well as two parallel algorithms to reduce its time complexity. Experimental results demonstrate that the GPU-accelerated algorithm performs better compared to the others.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Hong Wang, Yikun Ou, Yixin Wang, Tongtong Xing, Lijing Tan
Summary: A semi-supervised bacterial heuristic feature selection algorithm is proposed to address high-dimensional and label-missing problems. The algorithm utilizes a k-nearest neighbor semi-supervised learning strategy to reconstruct missing labels and improves the bacterial heuristic algorithm using population initialization, dynamic learning, and elite population evolution strategies. Experimental results demonstrate its advantages in terms of classification accuracy and selected feature numbers.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Hardware & Architecture
Yang Song, Helin Jin, Hongzhi Wang, You Liu
Summary: This study aimed to optimize the computation of complex expressions through graph modeling and simplification algorithms. Experimental results demonstrate that the proposed method effectively reduces computation costs.
JOURNAL OF SUPERCOMPUTING
(2021)