As a model used for parameter estimation, BP neural network has a remarkable effect in many prediction algorithms. However, there are situations that will fall into the local optimal solution and the learning speed is slow. To solve these two problems, this paper combines the dynamic adaptive strategy in the genetic algorithm, the method of eliminating honey sources in the bee colony algorithm, the adaptive greedy strategy in the ant colony algorithm, and the introduction of variation operator in the particle swarm algorithm to improve the two defects of the BP neural network, It has made optimization research on the use of BP neural network and prediction, and also laid the groundwork for the future research on optimization of BP neural network.

Botao Liu. Review of swarm intelligence algorithm optimization of BP neural network. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 6: 151-155. https://doi.org/10.25236/AJCIS.2023.060624.

[1] Wu Xing, Liu Tianyu, Jiang Xiuchen, Sheng Gehao. Reactive power optimization of offshore wind farm based on improved genetic algorithm [J]. Electric Measurement and Instrumentation, 2020, 57 (04): 108-113. DOI: 10.19753/j.issn1001-1390.2020.04.017

[2] Wang Ziyi. (2022). Research on optimization of material ordering and transportation based on multi-stage evaluation and selection genetic algorithm Technology and Innovation (22), 1-3. doi: 10.15913/j.cnki.kjycx. 2022.22.001

[3] Xiong Zhibin. Credit evaluation modeling based on adaptive genetic fuzzy neural network [J]. Journal of System Simulation, 2011, 23 (03): 490-496

[4] Ma Wei, Sun Zhengxing. (2014). Artificial bee colony algorithm based on elite bee colony search strategy Computer Application (08), 2299-2305

[5] Wang Xiu. (2018). Research on artificial bee colony algorithm based on multidimensional search optimization strategy (master's thesis, Xi'an University of Electronic Science and Technology) https://kns.cnki.net/KCMS/detail/detail.aspx?dbname=CMFD201901&filename=1019004231.nh

[6] Xia Le. Research and application of ant colony optimization algorithm based on greedy strategy [D]. Jiangxi University of Technology, 2022. DOI: 10.27176/d.cnki.gnfyc. 2022.000579

[7] Wang Qian, Zhao Jie, Wang Wanshan. (2022). Tailing dam deformation prediction based on PSO-BP combined modelGeospatial information (11), 119-122+128

[8] Zhang Yu, He Xiaoxing, Sun Xiwen. Prediction and analysis of sea level change based on improved particle swarm optimization neural network algorithm [J]. Beijing Surveying and Mapping, 2023,37 (01): 131-136

[9] Yu Mingtao, Ye Xiaotong. Prediction of tourist flow based on improved particle swarm optimization BP neural network [J]. Microcomputer and Application, 2015, 34 (21): 51-54. DOI: 10.19358/j.issn. 1674-7720.2015.21.017

[10] Wang He, Cao Yi, Li Yu, Lin Lin, Ren Lihui, Liu Guohui, Zhou Gangxia. Establishment of BP neural network prediction model for grain temperature in single storages based on improved particle swarm optimization algorithm [J]. Journal of China Grain and Oil Journal: 1-10