Fault Diagnosis of Nuclear Power System Based on DTW Algorithm for Incomplete Parameter

被引:0
作者
Zhao X. [1 ]
Cai Q. [1 ]
Wang X. [1 ]
机构
[1] College of Nuclear Science and Technology, Naval University of Engineering, Wuhan
来源
Yuanzineng Kexue Jishu/Atomic Energy Science and Technology | 2019年 / 53卷 / 06期
关键词
Dynamic time warping; Fault diagnosis; Multivariate time series; Random deletion; Sliding time window;
D O I
10.7538/yzk.2018.youxian.0546
中图分类号
学科分类号
摘要
The on-line monitoring parameters of nuclear power system are disturbed by noise during the process of acquisition and transmission, which leads to the random deletion of the final monitoring signal. The great disturbance for the operator to judge the type of accident was caused. Therefore, a sliding time window fault diagnosis model based on dynamic time warping (DTW) was proposed. The multivariate time series were built from on-line real-time monitoring and the existing accident standard series. The sliding time window was used to dynamically search the minimum cumulative distance in the standard series. The absence of monitoring parameters in the test series or the standard series leaded to the unequal length sequence, and DTW was used to deal the phenomenon. The pattern category of the time series depended on the minimum cumulative distance. This method is based on the basic principle of the accident in nuclear power system, and has strong explanation and robustness. At the same time, the model can be extended by other standard accident sequences. © 2019, Editorial Board of Atomic Energy Science and Technology. All right reserved.
引用
收藏
页码:1070 / 1077
页数:7
相关论文
共 12 条
[1]  
Ma J., Guo L., Zhang Y., Et al., Research on hybrid intelligent fault diagnosis system for nuclear power plant, Atomic Energy Science and Technology, 45, 8, pp. 977-982, (2011)
[2]  
Wang H., Cheng S., Zhang Z., Research on condition monitoring method of operator's operation support system, Nuclear Power Engineering, 31, 2, pp. 71-75, (2010)
[3]  
Mu Y., Xia H., Liu Y., Fault diagnosis method for nuclear power plant based on ensemble learning, Atomic Energy Science and Technology, 46, 10, pp. 1255-1258, (2012)
[4]  
Zhang W., Jiang Y., Yin G., Et al., Handling missing values in software effort data based on naïve Bayes and EM algorithm, Systems Engineering-Theory & Practice, 37, 11, pp. 2965-2974, (2017)
[5]  
Li Z., Zhang F., Li K., DTW based pattern matching method for multivariate tine series, Pattern Recognition & Artificial Intelligence, 24, 6, pp. 425-430, (2011)
[6]  
Li Z., Zhang F., Wang Y., Et al., Method of missing data imputation for multivariate tine series, Systems Engineering and Electronics, 40, 1, pp. 225-230, (2018)
[7]  
Banko Z.N., Abonyi J., Correlation based on dynamic time warping of multivariate time series, Expert System with Applications, 39, 17, pp. 12814-12823, (2012)
[8]  
Li H., Liang Y., Wang S., A review on dynamic time warping in time series data mining, Control and Decision, 33, 8, pp. 1345-1553, (2018)
[9]  
Adwan S., Alsaleh I., Mejed R., A new approach for image stitching technique using dynamic time warping (DTW) algorithm towards soliosis X-ray diagnosis, Measurement, 84, pp. 32-46, (2016)
[10]  
Qu Z., Wang H., Real time similarity of streaming time sequence, Computer Engineering and Sicence, 39, 6, pp. 1056-1062, (2017)