Abstract
Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.
Highlights
Publisher’s Note: MDPI stays neutralMechanical equipment is widely used in all walks of life in modern society, where rolling bearings are the most common component of mechanical equipment
To extract more robust fault features from bearing vibration data and improve fault identification accuracy, this paper proposes a bearing fault diagnosis scheme based on optimized stacked variational denoising autoencoder (OSVDAE) with the seagull optimization algorithm (SOA), which can avoid the problem of complexity and the triviality of manually adjusting the parameters of the stacked variational denoising auto-encoder (SVDAE) model
According to the flowchart of the proposed method, the frequency spectra data matrix of size 300 × 2048 is regarded as the training sample set to train an SVDAE model with optimized parameters, while the remainder frequency spectra data matrix of size 300 × 2048 is considered as the testing sample set with which to test the recognition performance of the well-trained SVDAE model and obtain bearing fault diagnoses
Summary
Publisher’s Note: MDPI stays neutralMechanical equipment is widely used in all walks of life in modern society, where rolling bearings are the most common component of mechanical equipment. Due to the continuous influence of alternating impact force and load, rolling bearings are subject to varying degrees of fault, in different positions. It will inevitably cause mechanical equipment to stop work, bringing about economic loss and even causing personnel casualties [1]. Accurate diagnosis of bearing faults is of great significance in ensuring the safe and reliable operation of mechanical equipment [2]. It is very valuable to develop effective bearing fault diagnosis technology for the field of mechanical health monitoring. With the rapid development of technologies such as sensors and industrial internet, the concept of intelligent diagnosis provides a new pathway for feature learning and the intelligent recognition of bearing faults [3,4]. Gunerkar et al [5] adopted wavelet transform (WT) to extract bearing with regard to jurisdictional claims in published maps and institutional affiliations
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.
