TY - JOUR
T1 - Sparse Autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties
AU - Yang, Zhe
AU - Gjorgjevikj, Dejan
AU - Long, Jianyu
AU - Zi, Yanyang
AU - Zhang, Shaohui
AU - Li, Chuan
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - Supervised fault diagnosis typically assumes that all the types of machinery failures are known. However, in practice unknown types of defect, i.e., novelties, may occur, whose detection is a challenging task. In this paper, a novel fault diagnostic method is developed for both diagnostics and detection of novelties. To this end, a sparse autoencoder-based multi-head Deep Neural Network (DNN) is presented to jointly learn a shared encoding representation for both unsupervised reconstruction and supervised classification of the monitoring data. The detection of novelties is based on the reconstruction error. Moreover, the computational burden is reduced by directly training the multi-head DNN with rectified linear unit activation function, instead of performing the pre-training and fine-tuning phases required for classical DNNs. The addressed method is applied to a benchmark bearing case study and to experimental data acquired from a delta 3D printer. The results show that its performance is satisfactory both in detection of novelties and fault diagnosis, outperforming other state-of-the-art methods. This research proposes a novel fault diagnostics method which can not only diagnose the known type of defect, but also detect unknown types of defects.
AB - Supervised fault diagnosis typically assumes that all the types of machinery failures are known. However, in practice unknown types of defect, i.e., novelties, may occur, whose detection is a challenging task. In this paper, a novel fault diagnostic method is developed for both diagnostics and detection of novelties. To this end, a sparse autoencoder-based multi-head Deep Neural Network (DNN) is presented to jointly learn a shared encoding representation for both unsupervised reconstruction and supervised classification of the monitoring data. The detection of novelties is based on the reconstruction error. Moreover, the computational burden is reduced by directly training the multi-head DNN with rectified linear unit activation function, instead of performing the pre-training and fine-tuning phases required for classical DNNs. The addressed method is applied to a benchmark bearing case study and to experimental data acquired from a delta 3D printer. The results show that its performance is satisfactory both in detection of novelties and fault diagnosis, outperforming other state-of-the-art methods. This research proposes a novel fault diagnostics method which can not only diagnose the known type of defect, but also detect unknown types of defects.
KW - Deep learning
KW - Fault diagnostics
KW - Multi-head deep neural network
KW - Novelty detection
KW - Sparse autoencoder
UR - https://www.scopus.com/pages/publications/85107279588
U2 - 10.1186/s10033-021-00569-0
DO - 10.1186/s10033-021-00569-0
M3 - 文章
AN - SCOPUS:85107279588
SN - 1000-9345
VL - 34
JO - Chinese Journal of Mechanical Engineering (English Edition)
JF - Chinese Journal of Mechanical Engineering (English Edition)
IS - 1
M1 - 54
ER -