Multi-label fault diagnosis of rolling bearing based on meta-learning
- PDF / 3,175,383 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 45 Downloads / 251 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Multi-label fault diagnosis of rolling bearing based on meta-learning Chongchong Yu1,2 • Yaqian Ning1 • Yong Qin3 • Weijun Su1 • Xia Zhao1 Received: 5 May 2020 / Accepted: 3 September 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract In practical applications, it is difficult to acquire sufficient fault samples for training deep learning fault diagnosis model of rolling bearing. Aiming at the few-shot issue and multi-label attributes of single-point faults, a novel fault diagnosis method of rolling bearing based on time–frequency signature matrix (T–FSM) feature and multi-label convolutional neural network with meta-learning (MLCML) is proposed in this paper. At the beginning, the T–FSM features sensitive to fewshot fault diagnosis of measured vibration signal are extracted. Subsequently, a designed multi-label convolutional neural network (MLCNN) with a specific architecture is employed to identify faults. Crucially, the meta-learning strategy of learning initial network parameters susceptive to task changes is incorporated to MLCNN for addressing the few-shot problem. Ultimately, the publicly available rolling bearing dataset is utilized to demonstrate the effectiveness of the proposed method. The experimental results exhibit that the trained MLCML has the capability of learning to learn few-shot fault attributes with outstanding diagnosis accuracy and generalization. More concretely, the model can adapt to new fault categories rapidly owing to that only a few samples and update steps are required to fine-tune the network. Keywords Fault diagnosis Multi-label learning Meta-learning Rolling bearing
1 Introduction Rotating machinery plays a crucial role in many modern industrial fields [1, 2]. As the key components of rotating machinery, rolling bearings have a decisive influence on the working efficiency of mechanical equipment [3]. The complex structure and harsh operating conditions of rolling bearing make it prone to failure [4–6], which may bring about huge economic losses and personnel casualties [7]. Consequently, the fault diagnosis of rolling bearing is of great significance in both industry and academic. The failure types in rolling bearings include cracks, pits, spalls, & Chongchong Yu [email protected] 1
School of Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, People’s Republic of China
2
Key Laboratory of Industrial Internet and Big Data (Beijing Technology and Business University), China National Light Industry, Beijing 100048, People’s Republic of China
3
State Key Lab of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, People’s Republic of China
wears, and so on [8]. This study focuses on the diagnosis of pit faults with different positions and diameters. Recently, interest has been rapidly improving in the intelligent diagnosis technologies with vibration analysis such as support vector machine and artificial neural network [9, 10].
Data Loading...
