전력 부하 분석을 통한 절삭 공정 이상탐지
Anomaly Detection of Machining Process based on Power Load Analysis
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
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.
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.
참고문헌 (13)
- 최수진, "서포트벡터 회귀를 이용한 실시간 제품표면거칠기 예측", 한국산업경영시스템학회지, 44(3), pp.117~124 (2021), 한국산업경영시스템학회
- Ha, Y. W., "FGLS estimation for process cycle pattern ex-traction and anomaly detection using Chi-square dis-tribution", Proceedings of the Korean Institute of Industrial Engineers, pp.4029~4036 (2022)
- Jin, S. J., "Welding process time series data anomaly detection using AutoEncoder", Isolation Forest algorithm, 2022, 4130~4135
- Jung, J., "Anomalous Records Detection in Process data using Robust Linear Regression", Proceedings of Korea Institute of information and Communication Engineering, pp.513~515 (2022)
- Jung, M. Y., "Welding process anomaly detection using GMM-Mahalanobis distance", Proceedings of the Korea Society of Manufacturing Technology and Engineering, pp.5873~5878 (2021)
- Kim, S. Y., "Prediction of production process equip-ment defects using explainable outlier detection algo-rithm", Proceedings of the Korean Institute of Industrial Engineers, pp.428~442 (2021)
- Kim, Y. S., "Performance Evaluation of Sensor Pattern Anomaly Detection Using Deep Learning", pp.2018
- Lee, H. Y., "Process anomaly detection based on deep learning", Proceedings of the Korean Institute of Industrial Engineers, pp.5306~5323 (2016)
- Lee, J. H., "Anomaly detection on the process utilizing robust deep autoencoder", Proceedings of the Korean Institute of Industrial Engineers, pp.2729~2750 (2019)
- 이재현, "웨이블릿을 이용한 주기 신호 데이터의 이상 탐지에 관한 연구", 한국시뮬레이션학회 논문지, 16(4), pp.13~22 (2007), 한국시뮬레이션학회
- 이승희, "다중 식별자를 이용한 Adversarial Autoencoder 기반 제조 공정 이상 탐지", 대한산업공학회지, 47(2), pp.217~223 (2021), 대한산업공학회
- 박철순, "주조공정 설비에 대한 실시간 모니터링을 통한 불량예측에 대한 연구", 한국산업경영시스템학회지, 45(4), pp.157~166 (2022), 한국산업경영시스템학회
- Yoo, G. H., "Abnomal de-tection of the mold cylinder temperature cycle using 1D CNN", Proceedings of the Korean Institute of Industrial Engineers, pp.5873~5878 (2021)