Asymmetric Studies with Complex Mechanical Systems
A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Engineering and Materials".
Deadline for manuscript submissions: 30 June 2024 | Viewed by 1121
Special Issue Editors
Interests: deep transfer learning; federated learning; signal processing; fault diagnosis
Special Issues, Collections and Topics in MDPI journals
Interests: condition monitoring; reliability; machine learning
Interests: mahcine diagnostics and prognostics; signal processing; sparse representation; machine learning
Interests: signal processing; fault diagnosis and prognosis; vibration analysis and suppression
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Asymmetry analysis is a crucial aspect of mechanical engineering that helps in identifying and diagnosing faults in machines. By studying the asymmetrical characteristics of a mechanical system, engineers can pinpoint the root cause of issues such as unbalance, misalignment, and faults of motors, bearings, etc. With the advent of modern technology, the complexity of mechanical systems has increased, making it more challenging to detect and predict faults accurately.
Machine learning has emerged as a powerful tool for asymmetric analysis in mechanical fault detection and diagnosis. By leveraging the power of artificial intelligence, engineers can train machines to identify patterns and anomalies in data, making it easier to detect faults in real time. The integration of machine learning with cloud computing and Industry 4.0 technologies has opened up new possibilities for improving the accuracy and efficiency of fault diagnosis in complex systems.
Topics may include, but are not limited to:
- Asymmetry analysis of mechanical systems;
- Abnormal detection;
- Intelligent diagnosis;
- Fault prognosis;
- Real-time monitoring;
- Predictive maintenance.
Dr. Zhuyun Chen
Dr. Borong Hu
Dr. Yun Kong
Dr. Minghui Hu
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Symmetry is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- asymmetry analysis
- abnormal detection
- condition monitoring
- artificial intelligence
Planned Papers
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Title: An Explainable Deep Wavelet Network for Abnormal Detection of Machinery
Authors: Yi He, Weidong Xu, Haiyang Wan, Zhuyun Chen*
Affiliation: School of Mechanical and Automotive Engineering, South China University of Technology
Abstract: The detection of abnormalities in machinery is crucial for ensuring the safety and efficiency of industrial operations. In recent years, deep learning techniques have shown great potential in abnormal detection tasks. However, the lack of interpretability in deep learning models hinders their practical application in industrial settings. In this study, we propose an Explainable Deep Wavelet Network (EDWN) for abnormal detection in machinery. The EDWN combines the strengths of deep learning and wavelet transform to enhance the interpretability of the model. The wavelet transform allows for the extraction of both time and frequency domain features, which are then fed into a deep neural network for abnormal detection. Experimental results on a real-world machinery dataset demonstrate the effectiveness and interpretability of the EDWN. The proposed model not only achieves high accuracy in abnormal detection but also provides insights into the underlying patterns contributing to abnormalities.