Early warning of reciprocating compressor valve fault based on deep learning network and multi-source information fusion

Abstract

An early warning method of compressor valve fault based on multi-parameter signals (vibration, pressure, and temperature) is presented in this work. Due to the complexity working condition, the run data of the compressor are of problems like noise and feature aliasing, which makes it difficult to extract useful features and find out the running law from the original signals. In this work, an improved deep learning network Multi-Level Fusion long short-term memory based on Component Evaluating Empirical Mode Decomposition and Fuzzy C-Means (CEEMD-FCM & MLF-LSTM) for parameter prediction of reciprocating compressor and an information fusion strategy is proposed for compressor valve fault warning. The CEEMD-FCM & MLF-LSTM network consists of data processing block, information learning block, and prediction output block, which is mainly responsible for parameter prediction. In the data processing block, the CEEMD-FCM algorithm is used for parameter decomposition, noise removal, and fuzzy mode (FM) reconstruction, which generates the input for the information learning block to ensure the predicting accuracy and reduce model complexity. MLF-LSTM is constructed to predict the parameter in the future by learning the temporal and spatial characteristics of FMs of the run data. Then, an early warning strategy for compressor valve fault based on multi-source information fusion is developed. Experimental results have verified that the proposed CEEMD-FCM & MLF-LSTM model and early warning strategy could realize early warning of compressor valve fault effectively.

Keywords

Compressor valve fault deep learning parameter prediction early warning multi-source information fusion

Get full access to this article

View all access options for this article.

References

Cabrera

Guaman

Zhang

, et al. (2020) Bayesian approach and time series dimensionality reduction to LSTM-based model-building for fault diagnosis of a reciprocating compressor. Neurocomputing 380: 51–66.

Chao

Wang

Chen

, et al. (2021) Extraction of local and global features by a convolutional neural network-long short-term memory network for diagnosing bearing faults. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science 236(3): 1877–1887.

Chen

Zhu

Zeng

, et al. (2021) Compressor fault diagnosis knowledge: A benchmark dataset for knowledge extraction from maintenance log sheets based on sequence labeling. IEEE Access 9: 59394–59405.

Flandrin

Goncalves

Rilling

(2004) Detrending and denoising with empirical mode decompositions. In: 12th European signal processing conference, EUSIPCO 2004, Vienna, 6–10 September, pp. 1581–1584. New York: IEEE.

Gord

Khoshnazar

(2016) Valve fault detection for single-stage reciprocating compressors. Journal of Natural Gas Science and Engineering 35: 1239–1248.

Huang

Shen

Long

(1998) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Physical and Engineering Sciences 454: 903–995.

Tang

Deng

, et al. (2021) Self-attention convLSTM and its application in RUL prediction of rolling bearings. IEEE Transactions on Instrumentation and Measurement 70: 1–11.

Cerrada

Cabrera

, et al. (2018a) A comparison of fuzzy clustering algorithms for bearing fault diagnosis. Journal of Intelligent and Fuzzy Systems 34(6): 3565–3580.

Zhao

(2018b) An improved EMD method with modified envelope algorithm based on C2 piecewise rational cubic spline interpolation for EMI signal decomposition. Applied Mathematics and Computation 335: 112–123.

10.

Wang

Zhao

, et al. (2019) Fault diagnosis method based on modified multi scale entropy and global distance evaluation for the valve fault of a reciprocating compressor. Journal of Mechanical Engineering 65: 123–135.

11.

Rehman

Mandic

(2011) Multivariate empirical mode decomposition. Proceeding of the Royal Society A: Mathematical Physical and Engineering Sciences 466: 1291–1302.

12.

Tabrizi

Garibaldi

Fasana

, et al. (2016) Automatic damage identification of roller bearings and effects of sifting stop criterion of IMFs. Measurement 93: 435–441.

13.

Tang

Chen

, et al. (2021) A deep convolutional neural network approach with information fusion for bearing fault diagnosis under different working conditions. Journal of Mechanical Engineering Science 235(8): 1389–1400.

14.

Tian

Ren

(2021) An adaptive update model based on improved Long Short Term Memory for online prediction of vibration signal. Journal of Intelligent Manufacturing 32(1): 37–49.

15.

Toroghi

Sadighi

(2020) Fault detection of reciprocating air compressors based on electrical signature analysis using long short-term memory networks. In: 6th Iranian conference on signal processing and intelligent systems, ICSPIS 2020, Mashhad, 23–24 December, pp. 1–6. New York: IEEE.

16.

Tran

AlThobiani

Ball

(2014) An approach to fault diagnosis of reciprocating compressor valves using Teager–Kaiser energy operator and deep belief networks. Expert Systems with Applications 41(9): 4113–4122.

17.

Tucker

Shand

Lewis

(2019) Handling missing data in self-exciting point process models. Spatial Statistics 29: 160–176.

18.

Wang

Dong

Zhou

, et al. (2019) Fault diagnosis of reciprocating compressor using component estimating empirical mode decomposition and de-dimension template with double-loop correction algorithm. IEEE Access 7: 90630–90639.

19.

Wang

Xue

Jia

, et al. (2015) Fault diagnosis of reciprocating compressor valve with the method integrating acoustic emission signal and simulated valve motion. Mechanical Systems and Signal Processing 56–57: 197–212.

20.

Chen

, et al. (2021) Degradation-aware remaining useful life prediction with LSTM autoencoder. IEEE Transactions on Instrumentation and Measurement 70: 1–10.

21.

Ding

Huang

(2020) Approach for fault prognosis using recurrent neural network. Journal of Intelligent Manufacturing 31: 1621–1633.

22.

Zhang

Hou

, et al. (2019) Research on the diagnosis method of reciprocating compressor valve leakage fault with vibration signal. In: Proceedings of the ASME 2019 international mechanical engineering congress and exposition, IMECE 2019, Salt Lake City, UT, 11–14 November, pp. 11–14. New York: ASME.