Xiaoyu Liu, Lang Chen, Lijun Zhu, Jian Wang, Long Chen, Xiankai Zeng, Ziang Song, Lujun Wang
{"title":"基于扩展卡尔曼滤波级联深度信念网络的电池荷电状态高精度估计策略","authors":"Xiaoyu Liu, Lang Chen, Lijun Zhu, Jian Wang, Long Chen, Xiankai Zeng, Ziang Song, Lujun Wang","doi":"10.1115/1.4063431","DOIUrl":null,"url":null,"abstract":"Abstract Battery state of charge (SOC) estimation is one of the main functions of the battery management system in electric vehicles. If the actual SOC of the battery differs significantly from the estimated value, it can lead to improper battery usage, resulting in unexpected rapid voltage drops or increases, which can affect driving safety. Therefore, high-accuracy SOC estimation is of great importance for battery management and usage. Currently used SOC estimation methods suffer from issues such as strong dependence on model parameters, error propagation from measurements, and sensitivity to initial values. In this study, we propose a high-precision SOC estimation strategy based on deep belief network (DBN) feature extraction and extended Kalman filter (EKF) for smooth output. The proposed strategy has been rigorously tested under different temperature conditions using the dynamic stress test (DST) and urban dynamometer driving schedule (US06) driving cycles. The mean absolute error (MAE) and root-mean-square error (RMSE) of the proposed strategy are controlled within 1.1% and 1.2%, respectively. This demonstrates the high-precision estimation achieved. To further validate the generality of this strategy, we also apply it to graphene batteries and conduct tests under US06 and highway fuel economy test (HWFET) driving cycles at temperatures of 25 °C and −10 °C. The test results show MAE of 0.47% and 2.01%, respectively.","PeriodicalId":15579,"journal":{"name":"Journal of Electrochemical Energy Conversion and Storage","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"High-Accuracy Battery SOC Estimation Strategy Based on Deep Belief Network Cascaded with Extended Kalman Filter\",\"authors\":\"Xiaoyu Liu, Lang Chen, Lijun Zhu, Jian Wang, Long Chen, Xiankai Zeng, Ziang Song, Lujun Wang\",\"doi\":\"10.1115/1.4063431\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Battery state of charge (SOC) estimation is one of the main functions of the battery management system in electric vehicles. If the actual SOC of the battery differs significantly from the estimated value, it can lead to improper battery usage, resulting in unexpected rapid voltage drops or increases, which can affect driving safety. Therefore, high-accuracy SOC estimation is of great importance for battery management and usage. Currently used SOC estimation methods suffer from issues such as strong dependence on model parameters, error propagation from measurements, and sensitivity to initial values. In this study, we propose a high-precision SOC estimation strategy based on deep belief network (DBN) feature extraction and extended Kalman filter (EKF) for smooth output. The proposed strategy has been rigorously tested under different temperature conditions using the dynamic stress test (DST) and urban dynamometer driving schedule (US06) driving cycles. The mean absolute error (MAE) and root-mean-square error (RMSE) of the proposed strategy are controlled within 1.1% and 1.2%, respectively. This demonstrates the high-precision estimation achieved. To further validate the generality of this strategy, we also apply it to graphene batteries and conduct tests under US06 and highway fuel economy test (HWFET) driving cycles at temperatures of 25 °C and −10 °C. The test results show MAE of 0.47% and 2.01%, respectively.\",\"PeriodicalId\":15579,\"journal\":{\"name\":\"Journal of Electrochemical Energy Conversion and Storage\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2023-10-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Electrochemical Energy Conversion and Storage\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1115/1.4063431\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ELECTROCHEMISTRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Electrochemical Energy Conversion and Storage","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1115/1.4063431","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ELECTROCHEMISTRY","Score":null,"Total":0}
High-Accuracy Battery SOC Estimation Strategy Based on Deep Belief Network Cascaded with Extended Kalman Filter
Abstract Battery state of charge (SOC) estimation is one of the main functions of the battery management system in electric vehicles. If the actual SOC of the battery differs significantly from the estimated value, it can lead to improper battery usage, resulting in unexpected rapid voltage drops or increases, which can affect driving safety. Therefore, high-accuracy SOC estimation is of great importance for battery management and usage. Currently used SOC estimation methods suffer from issues such as strong dependence on model parameters, error propagation from measurements, and sensitivity to initial values. In this study, we propose a high-precision SOC estimation strategy based on deep belief network (DBN) feature extraction and extended Kalman filter (EKF) for smooth output. The proposed strategy has been rigorously tested under different temperature conditions using the dynamic stress test (DST) and urban dynamometer driving schedule (US06) driving cycles. The mean absolute error (MAE) and root-mean-square error (RMSE) of the proposed strategy are controlled within 1.1% and 1.2%, respectively. This demonstrates the high-precision estimation achieved. To further validate the generality of this strategy, we also apply it to graphene batteries and conduct tests under US06 and highway fuel economy test (HWFET) driving cycles at temperatures of 25 °C and −10 °C. The test results show MAE of 0.47% and 2.01%, respectively.
期刊介绍:
The Journal of Electrochemical Energy Conversion and Storage focuses on processes, components, devices and systems that store and convert electrical and chemical energy. This journal publishes peer-reviewed archival scholarly articles, research papers, technical briefs, review articles, perspective articles, and special volumes. Specific areas of interest include electrochemical engineering, electrocatalysis, novel materials, analysis and design of components, devices, and systems, balance of plant, novel numerical and analytical simulations, advanced materials characterization, innovative material synthesis and manufacturing methods, thermal management, reliability, durability, and damage tolerance.