TY - JOUR
T1 - Machine Health Management System Using Moving Average Feature With Bidirectional Long-Short Term Memory
AU - Mubarak, Akram
AU - Asmelash, Mebrahitom
AU - Azhari, Azmir
AU - Haggos, Ftwi Yohannes
AU - Mulubrhan, Freselam
N1 - Publisher Copyright:
© 2022 American Society of Civil Engineers (ASCE). All rights reserved.
PY - 2023
Y1 - 2023
N2 - In today's highly competitive industrial environment, machine health management systems become a crucial factor for sustainability and success. The traditional feature extraction methods to reveal the health condition of the machine are labor-extensive. They usually depend on engineered design features, which require an expert knowledge level. Inspired by the successful results of deep-learning approaches that redefine representation learning from raw data, we propose moving-averaged features-based on Long-Short Term Memory (MaF-LSTM) networks. It is a hybrid approach that combines engineered features design with self-feature learning for the purpose of machine condition monitoring. First, features from overlapped sliding windows of the input time-series signals are extracted. Then, a moving-average filter is applied on the top of the generated features to enhance the feature's condition indicter's content. Next, a bidirectional LSTM is applied to learn the feature representation from the moving-averaged features. Two experiments, namely, bearing fault diagnosis and hydraulic accumulator fault detection, are implemented to verify the effectiveness of the proposed MaF-LSTM. The experimental results demonstrated that the proposed method outperforms all traditional condition monitoring methods in both use cases.
AB - In today's highly competitive industrial environment, machine health management systems become a crucial factor for sustainability and success. The traditional feature extraction methods to reveal the health condition of the machine are labor-extensive. They usually depend on engineered design features, which require an expert knowledge level. Inspired by the successful results of deep-learning approaches that redefine representation learning from raw data, we propose moving-averaged features-based on Long-Short Term Memory (MaF-LSTM) networks. It is a hybrid approach that combines engineered features design with self-feature learning for the purpose of machine condition monitoring. First, features from overlapped sliding windows of the input time-series signals are extracted. Then, a moving-average filter is applied on the top of the generated features to enhance the feature's condition indicter's content. Next, a bidirectional LSTM is applied to learn the feature representation from the moving-averaged features. Two experiments, namely, bearing fault diagnosis and hydraulic accumulator fault detection, are implemented to verify the effectiveness of the proposed MaF-LSTM. The experimental results demonstrated that the proposed method outperforms all traditional condition monitoring methods in both use cases.
UR - http://www.scopus.com/inward/record.url?scp=85136202901&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136202901&partnerID=8YFLogxK
U2 - 10.1115/1.4054690
DO - 10.1115/1.4054690
M3 - Article
AN - SCOPUS:85136202901
SN - 1530-9827
VL - 23
JO - Journal of Computing and Information Science in Engineering
JF - Journal of Computing and Information Science in Engineering
IS - 3
M1 - 031002
ER -