TY - GEN
T1 - Fast Adaption for Multi Motor Anomaly Detection via Meta Learning and deep unsupervised learning
AU - Yu, Yi Cheng
AU - Chuang, Shang Wen
AU - Shuai, Hong Han
AU - Lee, Chen-Yi
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - For PHM(Predictive Health Management) in an industrial scenario, motor vibration anomaly detection requires a large number of labeled data. The problem is that the anomaly vibration signal data is scarce and difficult to be obtained, especially the problem of insufficient data in the building and deployment of multi-machine models. This paper proposes a Meta-learning method based on deep unsupervised learning(Autoencoder). We use non-labeled and a small amount of vibration signal data which is converted into 52 key physical and statistical features to build models of different motors. By inputting these 52 features into designed models, other 52 features can be reconstructed as output. We use input and output features to calculate reconstruction error which is used as the criterion for the performance of models. We also use accuracy as the criterion for the performance of models. In the actual industrial situation, the improvement of accuracy by our proposed method is about 33.50% better than the method only with unsupervised learning for the new sensor model with few vibration data.
AB - For PHM(Predictive Health Management) in an industrial scenario, motor vibration anomaly detection requires a large number of labeled data. The problem is that the anomaly vibration signal data is scarce and difficult to be obtained, especially the problem of insufficient data in the building and deployment of multi-machine models. This paper proposes a Meta-learning method based on deep unsupervised learning(Autoencoder). We use non-labeled and a small amount of vibration signal data which is converted into 52 key physical and statistical features to build models of different motors. By inputting these 52 features into designed models, other 52 features can be reconstructed as output. We use input and output features to calculate reconstruction error which is used as the criterion for the performance of models. We also use accuracy as the criterion for the performance of models. In the actual industrial situation, the improvement of accuracy by our proposed method is about 33.50% better than the method only with unsupervised learning for the new sensor model with few vibration data.
KW - Autoencoder
KW - Meta-learning
KW - reconstruction error
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85135870815&partnerID=8YFLogxK
U2 - 10.1109/ISIE51582.2022.9831559
DO - 10.1109/ISIE51582.2022.9831559
M3 - Conference contribution
AN - SCOPUS:85135870815
T3 - IEEE International Symposium on Industrial Electronics
SP - 1186
EP - 1189
BT - 2022 IEEE 31st International Symposium on Industrial Electronics, ISIE 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 31st IEEE International Symposium on Industrial Electronics, ISIE 2022
Y2 - 1 June 2022 through 3 June 2022
ER -