| 282 | 0 | 47 |
| 下载次数 | 被引频次 | 阅读次数 |
针对储能电站因电池温度异常引发的安全问题，本文提出了一种基于人工智能（AI）技术的温度数据异常分析与问题定位方法。通过在储能电站关键区域部署高精度温度传感器，构建三维测温网络，并对采集的数据进行中值滤波去噪、自回归积分移动平均（ARIMA）模型插值填补缺失值以及最小-最大（Min-Max）归一化等预处理操作。在特征提取方面，不仅需考虑原始温度值，还需计算温度变化率、相邻传感器温差等基础特征，以及滑动窗口统计量和频域特征等衍生特征，最终筛选出12项对异常检测最具区分度的特征。本文构建了卷积神经网络-长短期记忆网络（CNN-LSTM）融合模型和孤立森林模型，并采用Stacking集成策略进行模型融合，使异常检测的F1值提升至0.95。通过将电池区域划分为网格，结合地理信息系统（GIS）技术和K-近邻算法（KNN算法），实现对问题电池的精准定位。
Abstract：To address safety issues caused by abnormal battery temperatures in energy storage power stations, this paper proposed an AI-based method for temperature data anomaly analysis and fault localization. By deploying high-precision temperature sensors in critical areas of the station, a threedimensional temperature measurement network is established. The collected data undergoes preprocessing operations including median filtering for noise removal, ARIMA model interpolation to fill missing values, and Min-Max normalization. For feature extraction, the approach considers not only raw temperature readings but also fundamental features such as temperature rate of change and temperature differences between adjacent sensors, along with derived features like sliding window statistics and frequency domain characteristics, ultimately identifying 12 most discriminative features for anomaly detection. A fusion model combining convolutional neural network-long short-term memory and Isolation Forest model was developed, with Stacking integration strategy employed to enhance the F1-score for anomaly detection to 0.95. By dividing battery zones into grids and integrating geographic information system technology with the K-nearest neighbors algorithm, precise localization of faulty batteries is achieved.
[1]Dixit P,Bhattacharya P,Tanwar S,et al. Anomaly detection in autonomous electric vehicles using AI techniques:A comprehensive survey[J]. Expert Systems,2022,39(5):e12754.
[2]Chen F X,Chen X L,Jin J W,et al.A data-driven early warning method for thermal runaway of energy storage batteries and its application in retired lithium batteries[J].Frontiers in Energy Research,2024,11:1334558.
[3]Chekifi T,Boukraa M,Benmoussa A. Artificial intelligence for thermal energy storage enhancement:A comprehensive review[J]. Journal of Energy Resources Technology,2024,146(6):060802.
[4]Hossain lipu M S,Miah M S,Jamal T,et al.Artificial intelligence approaches for advanced battery management system in electric vehicle applications:A statistical analysis towards future research opportunities[J].Vehicles,2024,6(1):22-70.
[5]Alhamrouni I,Abdul K N H,Salem M,et al.A comprehensive review on the role of artificial intelligence in power system stability,control,and protection:Insights and future directions[J]. Applied Sciences,2024,14(14):6214.
[6]Xiang H,Li X L,Liao X,et al.Artificial intelligence in renewable energy systems:Applications and security challenges[J].Energies,2025,18(8):1931.
[7]Ahmad H,Gulzar M M,Aziz S,et al. AI-based anomaly identification techniques for vehicles communication protocol systems:Comprehensive investigation,research opportunities and challenges[J]. Internet of Things,2024,27:101245.
[8]Shi Y,Zhang L Z.Robust deep auto-encoding network for real-time anomaly detection at nuclear power plants[J]. Process Safety and Environmental Protection,2022,163:438-452.
[9]Letaief K B,Shi Y M,Lu J M,et al.Edge artificial intelligence for 6G:Vision,enabling technologies,and applications[J].IEEE Journal on Selected Areas in Communications,2022,40(1):5-36.
[10]Kou L L,Chen J X,Qin Y,et al.The robust multi-scale deep-SVDD model for anomaly online detection of rolling bearings[J].Sensors,2022,22(15):5681.
[11]Gan N F,Sun Z Y,Zhang Z S,et al.Data-driven fault diagnosis of lithium-ion battery overdischarge in electric vehicles[J].IEEE Transactions on Power Electronics,2022,37(4):4575-4588.
[12]Cali U,Catak F O,Halden U. Trustworthy cyberphysical power systems using AI:Dueling algorithms for PMU anomaly detection and cybersecurity[J].Artificial Intelligence Review,2024,57(7):183.
[13]Khan M R,Haider Z M,Malik F H,et al.A comprehensive review of microgrid energy management strategies considering electric vehicles,energy storage systems,and AI techniques[J].Processes,2024,12(2):270.
[14]Bernardi D,Pawlikowski E,Newman J.A general energy balance for battery systems[J].Journal of the Electrochemical Society,1985,132(1):5-12.
[15]Miraftabzadeh S M,Longo M,Di M A,et al.Exploring the synergy of artificial intelligence in energy storage systems for electric vehicles[J].Electronics,2024,13(10):1973.
[16]Kumaresh S S,Devarapalli R,García M F P,et al. A comprehensive review of optimization,market strategies,and AI applications in energy storage systems[J].Evolutionary Intelligence,2025,18(4):79.
[17]Samanta A,Chowdhuri S,Williamson S S. Machine learning-based data-driven fault detection/diagnosis of lithium-ion battery:A critical review[J]. Electronics,2021,10(11):1309.
[18]Zheng X T,Xu N,Trinh L,et al. A multi-scale timeseries dataset with benchmark for machine learning in decarbonized energy grids[J]. Scientific Data,2022,9:359.
[19]Shen Q,Wen X,Xia S W,et al.AI-based analysis and prediction of synergistic development trends in U.S.photovoltaic and energy storage systems[J]. International Journal of Innovative Research in Computer Science and Technology,2024,12(5):36-46.
[20]Khan I U,Javeid N,Taylor C J,et al. A stacked machine and deep learning-based approach for analysing electricity theft in smart grids[J].IEEE Transactions on Smart Grid,2022,13(2):1633-1644.
[21]Biswas P,Rashid A,Al M A,et al. An extensive and methodical review of smart grids for sustainable energy management-addressing challenges with AI,renewable Energy Integration,and leading-edge technologies[J].IEEE Access,2026,14:44798-44815.
[22]Gutiérrez-gómez L,Bovet A,Delvenne J C.Multi-scale anomaly detection on attributed networks[J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(1):678-685.
[23]Wang Z C,Chen H Y,Zhu J M,et al.Multi-scale deep learning and optimal combination ensemble approach for AQI forecasting using big data with meteorological conditions[J].Journal of Intelligent&Fuzzy Systems,2021,40(3):5483-5500.
[24]Wang B Y,Chen Z Y,Zhang P H,et al.The lithiumion battery temperature field prediction model based on CNN-Bi-LSTM-AM[J].Sustainability,2025,17(5):2125.
[25]Safari A,Sabahi M,Oshnoei A. ResFaultyMan:An intelligent fault detection predictive model in power electronics systems using unsupervised learning isolation forest[J].Heliyon,2024,10(15):e35243.
[26]Abdulaal M J,Ibrahem M I,Mahmoud M M E A,et al.Real-time detection of false readings in smart grid AMI using deep and ensemble learning[J]. IEEE Access,2022,10:47541-47556.
[27]Shabayek A,Rathinam A,Ruthven M,et al.AI-enabled thermal monitoring of commercial(PHEV)Li-ion pouch cells with Feature-Adapted Unsupervised Anomaly Detection[J].Journal of Power Sources,2025,629:235982.
[28]刘宝泉，曹小雨．锂电池热失控早期典型气体精准检测方法[J]．储能科学与技术，2024,13(6):1995-2009.
[29]杨明红，叶雍欣，聂琦璐，等．光纤传感技术在储能电池监测中的研究进展[J]．激光与光电子学进展，2023,60(11):1106006.
基本信息:
DOI：10.19996/j.cnki.ChinBatlnd.2026.03.005
中图分类号:TM91;TP18
引用信息:
[1]张浩,刘志凯,陈泓韬,等.基于AI模型的储能电站电池温度异常缺陷定位测试应用[J].电池工业,2026,30(03):299-309.DOI:10.19996/j.cnki.ChinBatlnd.2026.03.005.
基金信息:
年度浙江省“尖兵领雁+X”科技计划项目（2025C02001）
2025-07-21
2025
2025-08-15
2025-08-21
2025
1
2025-09-01
2025-09-01
2025-09-01