An end-to-end fault diagnostics method based on convolutional neural network for rotating machinery with multiple case s
- PDF / 6,458,341 Bytes
- 22 Pages / 595.276 x 790.866 pts Page_size
- 87 Downloads / 188 Views
An end-to-end fault diagnostics method based on convolutional neural network for rotating machinery with multiple case studies Yiwei Wang1 · Jian Zhou1 · Lianyu Zheng1
· Christian Gogu2
Received: 29 November 2019 / Accepted: 15 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The fault diagnostics of rotating components are crucial for most mechanical systems since the rotating components faults are the main form of failures of many mechanical systems. In traditional diagnostics approaches, extracting features from raw input is an important prerequisite and normally requires manual extraction based on signal processing techniques. This suffers of some drawbacks such as the strong dependence on domain expertise, the high sensitivity to different mechanical systems, the poor flexibility and generalization ability, and the limitations of mining new features, etc. In this paper, we proposed an end-to-end fault diagnostics model based on a convolutional neural network for rotating machinery using vibration signals. The model learns features directly from the one-dimensional raw vibration signals without any manual feature extraction. To fully validate its effectiveness and robustness, the proposed model is tested on four datasets, including two public ones and two datasets of our own, covering the applications of ball screw, bearing and gearbox. The method of manual, signal processing based feature extraction combined with a classifier is also explored for comparison. The results show that the manually extracted features are sensitive to the various applications, thus needing fine-tuning, while the proposed framework has a good robustness for rotating machinery fault diagnostics with high accuracies for all the four applications, without any application-specific manual fine-tuning. Keywords Fault diagnostics · Rotating machinery · Vibration signals · Convolutional neural network
Introduction Rotating machinery is the essential equipment playing a crucial character in the modern industry. As indispensable key transmission devices of rotating machinery, the typical rotating components such as ball screws, bearings, and gears, are the leading cause of failure in essential industrial equipment such as induction motors, wheelset of high-speed railway bogie, aero-engines, wind-turbine, etc. According to statistics, 30–51% of rotating machinery failure are caused by these key components (Islam and Kim 2019a; Zhao et al. 2020). Failure of the rotating components results in machine performance degradation, unwanted downtime,
B
Lianyu Zheng [email protected]
1
School of Mechanical Engineering and Automation, Beihang University, Beijing 100191, China
2
Institut Clément Ader (UMR CNRS 5312) INSA/UPS/ISAE/Mines Albi, Université de Toulouse, 31400 Toulouse, France
economic losses and even human casualties. Normally, the rotating components are installed deep inside the machine and undergo a long degradation process from healthy to failure. It is not practical to frequently shut
Data Loading...
