电工技术学报  2019, Vol. 34 Issue (11): 2324-2332    DOI: 10.19595/j.cnki.1000-6753.tces.180637
电机与电器 |
改进的LSTM方法在冷水机组传感器故障检测中的应用
李冬辉, 尹海燕, 郑博文, 刘玲玲
天津大学电气自动化与信息工程学院 天津 300072
Application of Improved LSTM Method in Sensor Fault Detection of the Chiller
Li Donghui, Yin Haiyan, Zheng Bowen, Liu Lingling
School of Electrical and Information Engineering Tianjin University Tianjin 300072 China
全文: PDF (1648 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 针对目前国内外对于冷水机组传感器偏差故障检测效果不理想的问题,结合长短期记忆网络(LSTM)适用于处理高维、强耦合、高度时间相关性数据的特点,该文提出一种基于改进LSTM的深度学习方法,用于冷水机组传感器偏差故障检测。现场采集风冷冷水机组传感器数据,用于训练改进的LSTM。通过实验分析得出,不同传感器检测效率不同。将该文所提方法的检测结果与自动编码器(Auto encoder)、主元分析法(PCA)、标准的LSTM三种方法的检测结果进行比较,得出该文所提方法在冷水机组传感器偏差故障检测中检测效率明显优于其他三种方法;并且针对同一传感器相同大小、不同正负的偏差故障,所提方法的检测效率具有更好的对称性。最后证明该文所提的改进LSTM方法具有良好的泛化性。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
李冬辉
尹海燕
郑博文
刘玲玲
关键词 长短期记忆网络深度学习冷水机组传感器故障检测    
Abstract:At present, the sensor deviation fault detection of the water-cooled chiller is unexpected all over the world. Long short-term memory (LSTM) is suitable for processing high-dimensional, high-coupling, high-time correlation data. Taking into account the characteristics of LSTM, this paper proposed a deep learning method based on improved LSTM for the sensor deviation fault detection of the water-cooled chiller. The paper collected sensor data of the water-cooled chiller on site to train the improved LSTM network. It could be know through simulation experiments that the detection efficiency of different sensors is different, and the results were compared with the results of three other methods: auto encoder, principal component analysis (PCA) and standard LSTM. Finally, the detection efficiency of the method proposed in this paper is significantly better than the other three methods in sensor deviation fault detection of the water-cooled chiller. Furthermore, the detection efficiency of the proposed method has better symmetry for positive and negative fault levels with same absolute magnitude. Finally, it was proved that the proposed network has good generalization ability.
Key wordsLong short-term memory    deep learning    water-cooled chiller    sensor    fault detection   
收稿日期: 2018-04-19      出版日期: 2019-06-14
PACS: TP277  
通讯作者: 尹海燕 女,1992年生,硕士研究生,研究方向为深度学习、故障检测。E-mail:Yin_haiyan@tju. edu.cn   
作者简介: 作者简介李冬辉 男,1962年生,教授,博士生导师,研究方向为故障检测、电力电子技术、电机系统及其控制。E-mail:lidonghui@tju.edu.cn
引用本文:   
李冬辉, 尹海燕, 郑博文, 刘玲玲. 改进的LSTM方法在冷水机组传感器故障检测中的应用[J]. 电工技术学报, 2019, 34(11): 2324-2332. Li Donghui, Yin Haiyan, Zheng Bowen, Liu Lingling. Application of Improved LSTM Method in Sensor Fault Detection of the Chiller. Transactions of China Electrotechnical Society, 2019, 34(11): 2324-2332.
链接本文:  
https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.180637          https://dgjsxb.ces-transaction.com/CN/Y2019/V34/I11/2324