人工智能在动力电池健康状态预估中的研究综述
Overview of Artificial Intelligence in Health Prediction of Power Battery
戴国洪 1张道涵 1彭思敏 2苗一凡 2卓悦 2杨瑞鑫 3于全庆4
作者信息
- 1. 常州大学机械与轨道交通学院 常州 213164
- 2. 盐城工学院电气工程学院 盐城 224051
- 3. 北京理工大学机械与车辆学院 北京 100081
- 4. 哈尔滨工业大学(威海)汽车工程学院 威海 264209
- 折叠
摘要
目前先进的电动汽车开发和应用己成为实现"脱碳"的关键技术.准确的电池健康状态(State of health,SOH)预估可有效地表征动力电池性能,对电动汽车动力电池维护和寿命管理具有重要意义.近年来,以深度学习、强化学习和大数据技术等为代表的新一代人工智能技术在电动汽车电池状态预估的应用已成为研究热点.首先简要介绍人工智能技术、SOH的含义以及影响SOH主要因素,然后分别从电池单体与电池系统的角度对几种人工智能模型在SOH预估中的研究进行总结与讨论,最后结合大数据、云计算、区域链等新兴技术,对电池健康状态预估问题进行展望,为提升当前动力电池全生命周期管理能力提供一些思路.
Abstract
The development and application of advanced electric vehicles has become the key technology to achieve"decarbonization".Accurate state of health(SOH)prediction of battery can effectively characterize its operation performance.It is of great significance to the maintenance and life management of battery in electric vehicle.In recent years,a new generation of artificial intelligence technology represented by deep learning,reinforcement learning and big data technology has become a research hotspot in the application of battery state prediction.The basic theory of artificial intelligence technology and SOH and SOH influence factors is briefly introduced.Several main artificial intelligence algorithms in SOH prediction are summarized and discussed from the perspective of battery cell and battery system respectively.Finally,combined with emerging technologies such as big data,cloud computing and regional chain,some battery SOH prediction problems are discussed,which provides some ideas for breaking through the bottleneck of current power battery full life cycle management technology.
关键词
人工智能/健康状态/电池系统/现状与趋势Key words
artificial intelligence/state of health/battery system/status and trend引用本文复制引用
基金项目
国家自然科学基金(52177210)
中国博士后科学基金(2021M690395)
江苏省高等学校"青蓝工程"项目(2021-11)
盐城工学院校级科研项目(xjr2021052)
出版年
2024
NETL
NSTL
万方数据