State of Charge Estimation based on Port AGV Dynamic sPSO-DBN-ELM

Heng Wang

《International Core Journal of Engineering》 10卷4期 (2024/04) Pp. 38-46

https://doi.org/10.6919/ICJE.202404_10(4).0005

摘要

The state of charge (SOC) of the battery is a crucial aspect in ensuring the safe charging of Automated Guided Vehicles (AGVs). However, with battery aging, it becomes challenging for the Battery Management System (BMS) to maintain the accuracy of SOC data, leading to overcharging during the charging process. To address this issue, a SOC estimation method based on DBN-ELM for AGVs is proposed, along with the use of an improved dynamic simplified particle swarm optimization to overcome the issue of manually setting parameters in traditional DBN. Furthermore, for addressing missing data during the charging process, bidirectional LSSVM is utilized for data completion. Experimental results demonstrate that this method effectively enhances the SOC prediction accuracy of AGVs and holds practical significance.

關鍵字

SOC Estimation ； DBN ； ELM ； Dynamic Simplified Particle Swarm ； LSSVM

參考文獻

LING S,NGUYEN K,ROUX-LANGLOIS A,et al.A lattice-based group signature scheme with verifier-local revocation [J].Theoretical Computer Science,2018,730(19):1-20.

Antonucci, Giovanni Artale, Giovanni Bruna-ccini, Giuseppe Caravello et a1. Li-ionModeling and State of Charge Estimation Method Including the Hysteresis Effect[J]. Electronics, 2019,8(11):453-459.

Fan B, Luan X, Zhang R, et al. Research on SOC Estimation Algorithm for Lithium Battery Based on EKF Algorithm and Ampere-hour Integration Method[C]//Science and Engineering Research Center. Proceedings of 2017 2nd International Conference on Electrical, Control and Automation Engineering (ECAE 2017). Science and Engineering Research Center: Science and Engineering Research Center. 2017: 110-114.

Frendo O, Graf J, Gärtner N, et al. Data-driven smart charging for heterogeneous electric vehicle fleets[J]. Energy and AI, 2020, 1: 100007.

Guo L, Zhang Y. Application of SPCA-LSSVM model in soft measurement of Gasoline dry point[C]// 2020 13th International Symposium on Computational Intelligence and Design (ISCID). IEEE, 2020: 200-204.