Journal of Korean Society of Industrial and Systems Engineering (산업경영시스템학회지)

Society of Korea Industrial and System Engineering (한국산업경영시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Anomaly Detection of Machining Process based on Power Load Analysis

전력 부하 분석을 통한 절삭 공정 이상탐지

  • Received : 2023.12.04
  • Accepted : 2023.12.18
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Smart factory companies are installing various sensors in production facilities and collecting field data. However, there are relatively few companies that actively utilize collected data, academic research using field data is actively underway. This study seeks to develop a model that detects anomalies in the process by analyzing spindle power data from a company that processes shafts used in automobile throttle valves. Since the data collected during machining processing is time series data, the model was developed through unsupervised learning by applying the Holt Winters technique and various deep learning algorithms such as RNN, LSTM, GRU, BiRNN, BiLSTM, and BiGRU. To evaluate each model, the difference between predicted and actual values was compared using MSE and RMSE. The BiLSTM model showed the optimal results based on RMSE. In order to diagnose abnormalities in the developed model, the critical point was set using statistical techniques in consultation with experts in the field and verified. By collecting and preprocessing real-world data and developing a model, this study serves as a case study of utilizing time-series data in small and medium-sized enterprises.

Keywords

References

  1. Choi, S. and Lee, D., Real-Time Prediction for Product Surface Roughness by Support Vector Regression, Journal of Korean Society of Industrial and Systems Engineering, 2021, Vol. 44, Issue 3, pp. 117-124. https://doi.org/10.11627/jkise.2021.44.3.117
  2. Ha, Y.W., Yang, H.C., Yoo, K.H., Park, J.P., and Wang, G.N., FGLS estimation for process cycle pattern extraction and anomaly detection using Chi-square distribution, In Proceedings of the Korean Institute of Industrial Engineers, 2022, pp. 4029-4036.
  3. Jin, S.J., Yoo, S.C., Kim, N.G., Ha, Y.W., and Wang, G.N., Welding process time series data anomaly detection using AutoEncoder / Isolation Forest algorithm, In Proceedings of the Korean Institute of Industrial Engineers, 2022, pp. 4130-4135.
  4. Jung, J. and Jin, K.H., Anomalous Records Detection in Process data using Robust Linear Regression, In Proceedings of Korea Institute of information and Communication Engineering, 2022, pp. 513-515.
  5. Jung, M.Y., Yu, G.H., Kim, N.K., Jin, J.S., Yoo, S.C., and Wang, G.N., Welding process anomaly detection using GMM-Mahalanobis distance, In Proceedings of the Korea Society of Manufacturing Technology and Engineering, 2021, pp. 5873-5878.
  6. Kim, S.Y., Lee, J.Y., Mok, C,H., Kim, S.H., Moon, S.H., Kyeong, Y.Y., Chin, Y.G., Lee, Y.G., Choi, J.M., and Kim, S.B., Prediction of production process equipment defects using explainable outlier detection algorithm, In Proceedings of the Korean Institute of Industrial Engineers, 2021, pp. 428-442.
  7. Kim, Y.S., Performance Evaluation of Sensor Pattern Anomaly Detection Using Deep Learning, [dissertation], [Incheon, Korea]: InCheon University, 2018.
  8. Lee, H.Y., Kim, Y.J., and Kim, C.W., Process anomaly detection based on deep learning, In Proceedings of the Korean Institute of Industrial Engineers, 2016, pp. 5306-5323.
  9. Lee, J.H. and Cho, S.J. Anomaly detection on the process utilizing robust deep autoencoder, In Proceedings of the Korean Institute of Industrial Engineers, 2019, pp. 2729-2750.
  10. Lee, J.H., Kim, J.H., Hwang, J.B., and Kim, S.S., A Study on Fault Detection of Cycle-based Signal using Wavelet Transform, Journal of The Korea Society For Simulation, 2007, Vol. 16, No. 4, pp.13-22.
  11. Lee, S.H. and Baek, J.G., Manufacturing Process Anomaly Detection Using Adversarial Autoencoder with Multiple Discriminator, Journal of the Korean Institute of Industrial Engineers, 2021, Vol. 47, No. 2, pp.217-223. https://doi.org/10.7232/JKIIE.2021.47.2.217
  12. Park, C.S. and Kim, H.S., A Study on Defect Prediction through Real-time Monitoring of Die-Casting Process Equipment, Journal of Korean Society of Industrial and Systems Engineering, 2022, Vol. 45, Issue 4, pp.157-166. https://doi.org/10.11627/jksie.2022.45.4.157
  13. Yoo, G.H., Yang, H.C., and Wang, G.N., Abnomal detection of the mold cylinder temperature cycle using 1D CNN, In Proceedings of the Korean Institute of Industrial Engineers, 2021, pp.5873-5878