Remaining useful life prediction using multi-scale deep convolutional neural network

• Published in: Applied soft computing Vol. 89; p. 106113
• Main Authors: Li, Han, Zhao, Wei, Zhang, Yuxi, Zio, Enrico
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2020
• Subjects: Convolutional neural network; Deep learning; Multi-scale; Remaining useful life; Deep learning; Multi-scale; Remaining useful life; Convolutional neural network
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2020.106113

Accurate and reliable remaining useful life (RUL) assessment result provides decision-makers valuable information to take suitable maintenance strategy to maximize the equipment usage and avoid costly failure. The conventional RUL prediction methods include model-based and data-driven. However, with the rapid development of modern industries, the physical model is becoming less capable of describing sophisticated systems, and the traditional data-driven methods have limited ability to learn sophisticated features. To overcome these problems, a multi-scale deep convolutional neural network (MS-DCNN) which have powerful feature extraction capability due to its multi-scale structure is proposed in this paper. This network constructs a direct relationship between Condition Monitoring (CM) data and ground-RUL without using any prior information. The MS-DCNN has three multi-scale blocks (MS-BLOCKs), where three different sizes of convolution operations are put on each block in parallel. This structure improves the network’s ability to learn complex features by extracting features of different scales. The developed algorithm includes three stages: data pre-processing, model training, and RUL prediction. After the min–max normalization pre-processing, the data is sent to the MS-DCNN network for parameter training directly, and the associated RUL value can be estimated base on the learned representations. Regularization helps to improve prediction accuracy and alleviate the overfitting problem. We evaluate the method on the available modular aero-propulsion system simulation data (C-MAPSS dataset) from NASA. The results show that the proposed method achieves good prognostics performance compared with other network architectures and state-of-the-art methods. RUL prediction result is obtained precisely without increasing the calculation burden. •A new deep learning method based on multi-scale feature extraction is proposed for remaining useful life (RUL) prediction.•The proposed method constructs the direct relationship between the raw data and the ground-RUL.•The proposed method improves the learning ability and robustness of the network by capturing more detailed features using multi-scale structure.•We prove that the proposed method achieves more accurate prediction results on NASA’s C-MAPSS dataset in comparison with other deep learning architectures and state-of-the-art methods without increasing the calculation amount