Digital Technologies Research and Applications

Topical Collection on "Technological Developments in Machine Learning for Electrical Engineering and Electronics with Multidisciplinary Applications"

A topical collection of Digital Technologies Research and Applications (DTRA) (E-ISSN: 2754-5687).
Deadline for manuscript submissions: 31 March 2025

Collection Editors: 

Dr. Barmak Honarvar Shakibaei Asli
Centre for Life-Cycle Engineering and Management, School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield, Bedfordshire MK43 0AL, UK
Research Interests: Digital signal and image processing; Machine learning and artificial intelligence; Digital filter design, pattern recognition and classification

 

Topical Collection Information:

Dear Colleagues,

In the fields of electrical engineering and electronics, machine learning (ML) has become a potent instrument that facilitates breakthroughs and creative solutions across a range of applications. Considerable technical advancements with interdisciplinary applications have resulted from combining machine learning techniques with conventional electrical engineering concepts. The goal of this Topical Collection is to investigate the many uses of machine learning for electrical engineering and electronics across several disciplines, while also exploring the most recent technical advancements in this field.

We are particularly interested in papers exploring the integration of ML algorithms with electrical engineering principles for applications such as predictive maintenance, fault detection, and energy optimization. Moreover, the research focuses on investigating the use of ML for signal processing, pattern recognition, and control systems design in electronic devices and circuits.

Researchers and industry professionals have a rare chance to exhibit their work, advance the field, and work together to pave the way for a technological development in ML that is more effective, dependable, and intelligent with this Topical Collection. We are thrilled to see the contributions that will influence the direction of ML in electrical engineering fields and are looking forward to receiving your submissions.

Dr. Barmak Honarvar Shakibaei Asli
Collection Editors

Keywords:

  • Electrical Engineering
  • Artificial-Intelligence-Based Electrical Machines and Drives
  • Deep Learning
  • Machine Learning
  • Digital Signal and Image Processing
  • Data Analysis
  • Pattern Recognition
  • Predictive Maintenance
  • Structural health monitoring (SHM)
  • Data Classification, Segmentation, and Clustering
  • Object Detection and Tracking
  • Medical imaging for EEG/ECG Signal Processing
  • Feature selection, Extraction, and Learning

Manuscript Submission Information:

Please visit the Submissions Guidelines page before submitting a manuscript. Submitted papers should be well formatted and use good English. Manuscripts should be submitted online through the online manuscript submission and editorial system. Additionally, please include a cover letter specifying that the manuscript is intended for the Topical Collection "Technological Developments in Machine Learning for Electrical Engineering and Electronics with Multidisciplinary Applications" when submitting it online. Manuscripts can be submitted until the submission deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal and will be listed together on the Topical Collection website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract can be sent to the Editorial Office dtra@ukscip.com for announcement on this website.

The Article Processing Charge (APC) for publication in this open access journal is 300 USD. Authors who are unable to cover this cost or those who are invited to submit papers may be eligible for discounts or waivers.

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 double-blind peer-review process.

Planned paper information:

Title: Effective Analytical Techniques for the Condition Monitoring of Induction Motors

Abstract: As industrialisation increases, electric machines become more and more common in the industrial production industries. The normal operation of the electric machines can guarantee the productivity, safety and ease of the manufacturing process. As a result, the focus of research in electric machine conditions monitoring has shifted to electric motor fault monitoring. In this paper, we will look at the typical rotor broken bar fault and the eccentricity fault in the induction motor fault as examples. We will analyse the fault mechanism of the motor model, and establish the normal and the faulty state of the motor model by finite element simulation. We will extract relative stator current signals, and analyze and compare the current spectrum. On one hand, we will verify the correctness of extracted stator currents data, and on the other, we will provide a robust and efficient data extraction method for the following feature extraction method: The TQWT method and the box dimension method are used to extract the characteristics of the signal during operation. The TQWT method is better at characterising the signal than the other methods. Next, SVM and ANN are used to diagnose induction motor faults with 91.67% accuracy and 100% accuracy respectively. The results demonstrate that ANN is more accurate than SVM and the strategy proposed can be used to automatically detect motor faults. The use of intelligent systems helps to prevent unplanned and unnecessary system downtime caused by electric machine faults.