主管：中华人民共和国应急管理部
主办：应急管理部天津消防研究所
ISSN 1009-0029  CN 12-1311/TU
消防科学与技术

消防科学与技术 ›› 2025, Vol. 44 ›› Issue (8): 1023-1028.

• •    下一篇

基于改进YOLOv5s算法的锂电池火灾识别模型

张术琳1,2, 王澜凝1,2, 文拙1,2, 鲁义1,2   

  1. （1.湖南科技大学 资源环境与安全工程学院，湖南 湘潭 411201； 2.火灾爆炸防控与应急技术湖南省普通高等学校重点实验室，湖南 湘潭 411201）
  • 收稿日期:2024-07-26 修回日期:2024-09-18 出版日期:2025-08-15 发布日期:2025-08-15
  • 作者简介:张术琳，湖南科技大学资源环境与安全工程学院副教授，博士，主要从事矿井热动力灾害防治、爆炸安全防护技术等方面的研究， 湖南省湘潭市雨湖区桃园路，411201，1010111@hnust.edu.cn。
  • 基金资助:
    国家自然科学基金（52304215）；湖南省重点研发计划项目（2022GK2042）；湖南省自然科学基金（2023JJ40292）；湖南省教育厅科学研究项目（22C0240）

Identification model of lithium battery fire based on improved YOLOv5s algorithm

Zhang Shulin1,2, Wang Lanning1,2, Wen Zhuo1,2, Lu Yi1,2   

  1. (1. School of Resource & Environment and Safety Engineering, Hunan University of Science and Technology, Xiangtan Hunan 411201, China; 2. Key Laboratory of Fire and Explosion Prevention and Emergency Technology in Hunan Province, Xiangtan Hunan 411201, China)
  • Received:2024-07-26 Revised:2024-09-18 Online:2025-08-15 Published:2025-08-15

摘要： 锂电池火灾温度上升迅速，易引起周边物体燃烧，扩大火灾范围；同时，锂电池火灾会产生可燃气体，容易形成爆炸风险，加重火灾的危险性。因此，及时检测锂电池火灾以采取应急救援措施对阻断锂电池连锁事故具有重要意义。本研究基于YOLOv5s算法，添加CA注意力机制增强模型的特征提取能力，并选用Mosaic-9数据增强算法提高模型的泛化能力，同时在模型中添加CIoU损失函数提升模型对小目标火焰的检测精度，建立基于改进YOLOv5s算法的锂电池火灾识别模型，并基于多干扰锂电池火灾数据集训练分析改进前后算法模型的损失函数和评价指标的鲁棒性。结果表明，改进模型的损失值收敛性更好，损失值较低；相比于原算法模型，改进算法模型的精确度提高了2.25%，召回率提升了2.11%，mAP增加了2.98%，F1分数提升了4.14%；改进算法模型在实现46 帧/秒的检测速度的同时维持了准确的识别效果，本模型的建立对智能识别锂电池火灾的研究具有参考价值。

关键词: 锂电池火灾, 火灾检测, YOLOv5s算法, CA注意力机制, Mosaic-9数据增强, CIoU损失函数

Abstract: The temperature of lithium battery fire rises rapidly, which is easy to cause the surrounding objects to burn and expand the fire range; At the same time, flammable gases produced by lithium battery fire are prone to explosion risk, which increases the risk of fire. The timely detection of lithium battery fires and the implementation of emergency rescue measures are crucial in preventing chain accidents. This study enhanced the feature extraction ability of the YOLOv5s algorithm by incorporating the Coordinate Attention mechanism, and improved the model's generalization ability through the use of the Mosaic-9 data augmentation algorithm. Additionally, we introduced the CIoU loss function to enhance small target flame detection accuracy. A lithium battery fire identification model based on the improved YOLOv5s algorithm is established, and the loss function and evaluation index robustness of the algorithm model before and after the improvement are analyzed based on the multi-interference lithium battery fire dataset training. The results indicate that the loss value of the model after the improvement has better convergence, and the loss value of the improved algorithm model is lower; compared with the original algorithm model, the accuracy of the improved algorithm model increased by 2.25%, the recall rate increased by 2.11%, the mAP increased by 2.98%, and the F1 score increased by 4.14%. The improved algorithm model achieves the detection speed of 46 frame per second while maintaining a good recognition effect. The establishment of this model has a reference value for the research of intelligent identification of lithium battery fire.

Key words: lithium battery fire, fire identification, YOLOv5s algorithm, CA mechanism, Mosaic-9 data augmentation, CIoU loss function