Advertisement

Fault Diagnosis and Prediction Method of SPC for Engine Block Based on LSTM Neural Network

  • Chunying JiangEmail author
  • Ping Jin
  • Yuxiang Kang
  • Changlong Ye
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11743)

Abstract

Aiming at the problem of insufficient data volume and data time series being ignored during analysis in current quality statistical process control. A statistical process control (SPC) quality analysis and prediction model based on principal component analysis (PCA) and Long Short-Term Memory (LSTM) is proposed. Firstly, based on the normalization of the data, the key process affecting the production quality is determined based on the PCA model. The size of the previous time is the input of the LSTM, the size of the next time is the output, and the LSTM model is trained. Predictions show that LSTM has a prediction accuracy of over 92%. Secondly, combined with SPC’s conventional control chart, cumulative Sum (CUSUM) control chart and exponentially weighted moving average (EWMA) control chart, the LSTM prediction value is analyzed for the small deviation problem in production, and the measurement of the data of the machining center in the actual production process is used to validates the proposed method. The results show that the proposed prediction model has high precision and good stability and can be used for quality management and predictive testing in the production process.

Keywords

LSTM neural network Principal component analysis Statistical process control 

References

  1. 1.
    Cao, J., Yin, C., Liu, F., Li, J.-C., Yin, Q.: Research and application on dynamic statistical process control of key process in multi-varieties and small-batch machining workshop. China Mech. Eng. 22(23), 2822–2827 (2011)Google Scholar
  2. 2.
    Huang, Z., Tian, L., Xiang, D.: WEIei hybrid. J. Tsinghua Univ. (Sci. Technol.) 58(6), 539–546 (2018)Google Scholar
  3. 3.
    Zhang, R., Qiu, L.: Fault detection of hydraulic servo-system based on dynamic neural network 38(3), 46–49 (2002)Google Scholar
  4. 4.
    Wang, X., Wu, J., Liu, C., Yang, H., Du, Y., Niu, W.: Exploring LSTM based recurrent neural network for failure time series prediction. J. Beijing Univ. Aeronaut. A 44(4), 772–784 (2018)Google Scholar
  5. 5.
    Sun, W., Chen, J., Li, J.: Decision tree and PCA-based fault diagnosis of rotating machinery. Mech. Syst. Signal Process. 21(3), 1300–1317 (2006). http://kns.cnki.net/kcms/detail/detail.aspx?filename=SJES13012100145247&dbcode=SJES
  6. 6.
    Ma, X., Tao, Z., Wang, Y., Yu, H., Wang, Y.: Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transp. Res. Part C 54, 187–197 (2015). http://kns.cnki.net/kcms/detail/detail.aspx?filename=SJES3020B5D814FC272C4693E3441D2527AB&dbcode=SJES
  7. 7.
    das Chagas Moura, M., Zio, E., Lins, I.D., Droguett, E.: Failure and reliability prediction by support vector machines regression of time series data. Reliab. Eng. Syst. Saf. 96(11), 1527–1534 (2011). http://kns.cnki.net/kcms/detail/detail.aspx?filename=SJES13011501716145&dbcode=SJES

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Chunying Jiang
    • 1
    Email author
  • Ping Jin
    • 1
  • Yuxiang Kang
    • 1
  • Changlong Ye
    • 1
  1. 1.Shenyang Aerospace UniversityShenyangChina

Personalised recommendations