Surge diagnosis method of centrifugal compressor based on multi-source data fusion

被引：0
|
作者：
Xu Y. [1 ]
Huang W. [2 ]
Mi J. [2 ]
Shen C. [2 ]
Jin J. [2 ]
机构：
[1] China Petroleum and Chemical Corporation, Beijing
[2] College of Control Science and Engineering, Zhejiang University, Zhejiang, Hangzhou
来源：
Huagong Xuebao/CIESC Journal | 2023年 / 74卷 / 07期
关键词：
centrifugal compressor; convolutional neural network; empirical wavelet transform; muti-source data fusion; surge diagnosis; weighted D-S evidence theory;
D O I：
10.11949/0438-1157.20230454
中图分类号：
学科分类号：
摘要：
The centrifugal compressor is the key power equipment for oil refining and chemical production. Once it breaks down, it may cause major plant ' s accidents. Therefore, online equipment monitoring and fault diagnosis throughout the life cycle is conducive to the continuous and stable operation of plant. This paper proposes a surge diagnosis method for centrifugal compressor based on multi-source data fusion such as flow, pressure and vibration. First, the vibration data is decomposed into a specified number of sub band signals by using empirical wavelet transform and the signal is reconstructed according to the correlation order. Convolutional neural network is used to pre-diagnose the reconstructed vibration signal, flow signal and pressure signal, and the final diagnosis is made using the weighted D-S evidence theory for the normalized diagnosis results of the three signals. Through the experiment of surge simulation test on centrifugal compressor, the diagnosis accuracy can reach 97.25% by using the multi-source fusion fault diagnosis method proposed in this paper. Compared with the use of single sensor data, this method significantly improves the fault tolerance ability of diagnosis, and it has higher diagnosis accuracy compared with other methods. © 2023 Chemical Industry Press. All rights reserved.
引用
收藏
页码：2979 / 2987
页数：8
相关论文
共 30 条
  • [1] Lei Y G, Jia F, Zhou X, Et al., A deep learning-based method for machinery health monitoring with big data, Journal of Mechanical Engineering, 51, 21, pp. 49-56, (2015)
  • [2] Zhang T T, Jia M Y., Research on common methods and application of new technology in fault diagnosis of mechanical equipment, Automation & Instrumentation, 10, pp. 38-39, (2017)
  • [3] Xin B., Research on fault diagnosis method of reciprocating compressors, Modern Chemical Research, 6, pp. 70-71, (2018)
  • [4] Zhang H., Research status and prospect of centrifugal compressor, Chemical Engineering Management, 32, (2016)
  • [5] Wang G B, He Z J, Chen X F, Et al., Basic research on machinery fault diagnosis—what is the prescription, Journal of Mechanical Engineering, 49, 1, pp. 63-72, (2013)
  • [6] Rai A, Upadhyay S H., A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings, Tribology International, 96, pp. 289-306, (2016)
  • [7] Lv C, Luan J H, Wang L M, Et al., Fault Diagnosis and Prediction: Principles, Techniques, and Applications, (2012)
  • [8] Ma M., Study on vibration and control of large centrifugal compressor unit, (2019)
  • [9] Yang X J, Zhu X L., Fault diagnosis method of reciprocating compressor based on locality balanced discriminant projection, Machine Design & Research, 38, 1, pp. 215-218, (2022)
  • [10] Pan Y J, Li Y, Wang X W, Et al., Fault feature extraction method of sliding bearing of reciprocating compressor based on SPA and SQPE, Journal of Shenyang Ligong University, 41, 4, pp. 20-25, (2022)
123