Fault Detection and Diagnosis Applications for Electric Vehicles and Power Electronics

Dear Colleagues,

Currently, one of the basic requirements for modern electric drives used in industry and mobility applications is their reliability. Ensuring full control of the process by monitoring the status of individual components during their operation is now an inseparable part of automation systems. A key task of supervisory systems is the detection of drive system irregularities, combined with the concept of early fault detection. Defects that occur in drive systems with induction motors and permanent magnet synchronous motors first require detection and mitigation of the impact of the defect on drive operation. With the use of closed AC motor control structures, the effects of some defects can be partially reduced by changes in the control algorithm, which involves the use of fault-tolerant systems. However, it is still important to develop detection algorithms that ensure the detection of a defect at the earliest possible stage.

The fault diagnosis of drive systems is implemented in three main directions: diagnosis based on mathematical modeling and estimation of object parameters, using analytical methods of signal processing, and systems based on artificial intelligence methods. Each of these approaches is making significant contributions to the development of accurate systems for fault detection and prediction of subsequent object behavior. However, in recent years, hybrid approaches that represent an interdisciplinary approach to diagnostics have been increasingly used. Simple neural classifiers make it possible to determine the technical condition of machines based on symptoms that are the result of known signal analyses in the time or frequency domain. Deep neural networks use signals in the form of images that are the result of higher-order analyses. Neural estimators of difficult-to-measure state variables can detect a defect based on the analysis of changes in a selected machine parameter. Defect features obtained from advanced mathematical models are a source of information for applications based on transfer learning. Accordingly, classical fault diagnosis based on signal analysis, the idea of fault-tolerant control systems, mathematical modeling techniques, artificial intelligence, and machine learning methods are intersecting fields aimed at developing fully automated control and diagnostic systems.

The scope of this Special Issue includes the application of advanced methods for detecting and classifying drive system faults using a combination of different diagnostic approaches. Special attention is paid to the application of various techniques to develop fully automated and accurate detection systems for power electronics and electromobility. Topics of interest for publication include, but are not limited to, the following:

• Fault detection and diagnosis of electrical machines and drives;
• Initial fault detection of AC drives;
• Neural network-based classification systems;
• Data and signal processing in diagnostic applications;
• Fault detection based on deep neural networks and transfer learning;
• Extraction of fault symptoms based on mathematical modeling;
• Fault-tolerant control;
• Estimation theory.

Dr. Maciej Skowron
Guest Editor

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. Energies is an international peer-reviewed open access semimonthly 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 2600 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.

• fault detection and diagnosis
• initial fault detection
• neural network-based classification systems
• data and signal processing
• deep neural networks
• transfer learning
• mathematical modeling
• fault-tolerant control
• estimation theory