Abstract
With the growth of computing power, deep learning methods have recently been widely used in machine fault diagnosis. In order to realize highly efficient diagnosis accuracy, people need to know the detailed health condition of collected signals from equipment. However, in the actual situation, it is costly and time-consuming to close down machines and inspect components. This seriously impedes the practical application of data-driven diagnosis. In comparison, the full-labeled machine signals from test rigs or online datasets can be achieved easily, which is helpful for the diagnosis of real equipment. Thus, we introduced an improved Wasserstein distance-based transfer learning method (WDA), which learns transferable features between labeled and unlabeled signals from different forms of equipment. In WDA, Wasserstein distance with cosine similarity is applied to narrow the gap between signals collected from different machines. Meanwhile, we use the Kuhn–Munkres algorithm to calculate the Wasserstein distance. In order to further verify the proposed method, we developed a set of case studies, including two different mechanical parts, five transfer scenarios, and eight transfer learning fault diagnosis experiments. WDA reached an average accuracy of 93.72% in bearing fault diagnosis and 84.84% in ball screw fault diagnosis, which greatly surpasses state-of-the-art transfer learning fault diagnosis methods. In addition, comprehensive analysis and feature visualization are also presented.
Highlights
With the rise of machine learning, especially deep learning, more and more datadriven algorithms have been proposed and applied successfully in different fields in the last few years [1,2,3]
Atoui et al [5] presented Bayesian network for fault detection and diagnosis, Rajakarunakaran S et al [6] proposed artificial neural networks (ANN) for the fault detection of the centrifugal pumping system, and Ivan et al [7] suggested a novel weighted adaptive recursive fault diagnosis method based on principal component analysis (PCA) to reduce the false alarm rate in processing monitoring schemes
The contributions of this paper mainly lie in the following two parts: Sensors 2021, 21, 4394 (1) To achieve classification on unlabeled signals, we propose a transfer learning fault diagnosis method named Wasserstein distance-based transfer learning method (WDA), which makes use of labeled signals from different machines to help the classification of signals
Summary
With the rise of machine learning, especially deep learning, more and more datadriven algorithms have been proposed and applied successfully in different fields in the last few years [1,2,3]. Zhu et al [15] used capsule net to extract more general features from the time-frequency spectrum and achieved higher diagnosis accuracy when dealing with data from different loads With such improvement strategies, artificial neural networks have been proven to be a potential tool to deal with industry data. Transfer learning theory has been introduced to machine fault diagnosis in order to improve domain adaption ability among different machines. Lu et al [16] presented a deep model-based domain adaptation method for the machine fault diagnosis. (1) To achieve classification on unlabeled signals, we propose a transfer learning fault diagnosis method named WDA, which makes use of labeled signals from different machines to help the classification of signals.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
