Diagnosing Faults with Machine Learning

A special issue of Computation (ISSN 2079-3197). This special issue belongs to the section "Computational Engineering".

Deadline for manuscript submissions: 31 December 2025 | Viewed by 705

Special Issue Editors


E-Mail Website1 Website2
Guest Editor
Department of Engineering Sciences, Babes-Bolyai University, 320085 Reşiţa, Romania
Interests: damage detection; gear design; gear manufacturing; gear testing; vibration
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Automation, Industrial Engineering, Textiles and Transportation, Aurel Vlaicu University, Elena Dragoi Street, No. 2, 310130 Arad, Romania
Interests: mechanical engineering; manufacturing technologies; inertial propulsion

Special Issue Information

Dear Colleagues,

In today’s landscape, systems are evolving to become more intricate thanks in part to groundbreaking design concepts and advancements in technologies such as sensing, materials, communication, and overall system integrity. Fault detection and diagnosis play a vital role in fostering a healthy state of awareness, enabling accurate predictions, and helping to prevent potential faults in these systems.

The processes of fault detection and diagnosis in modern systems present certain challenges. These challenges arise from the intricate nature of the subject, which involves careful consideration of performance analysis, sensor placement and communication, and data collection and analysis, as well as the evaluation of benefits and informed decision-making. Additionally, a comprehensive understanding of the operational states of complex systems and their interactions with a range of environmental factors—some of which may be variable or unpredictable—is essential for effective implementation.

Machine learning is a valuable approach for addressing detection and diagnosis challenges in contemporary systems. This advanced tool could complement and enhance traditional model-based methodologies. This Special Issue focuses on the integration of advanced machine learning techniques for effective fault detection and diagnosis in industrial systems. It emphasizes the critical role of fault detection, which can significantly enhance system reliability and efficiency, thereby reducing maintenance costs and downtime. Furthermore, this Special Issue explores predictive maintenance strategies that leverage machine learning to forecast equipment failures, allowing for timely interventions.

Therefore, we welcome contributions on a range of topics, including computational engineering, sensor configuration design solutions, fault detection, fault diagnosis, fault prognosis, and condition-based and predictive maintenance strategies. Original research and review articles related, but not limited, to the following topics are welcomed:

  • New design concepts of health monitoring platforms;
  • Modeling and analyzing of structures health state;
  • Sensing and monitoring advancement toward structures;
  • Computation and simulation tools;
  • Vibration and its prevention;
  • Digital twins;
  • Advanced methodologies on machine learning;
  • Machine learning-based fault detection;
  • Machine learning-based fault diagnosis;
  • Machine learning-based fault prognosis.

Dr. Zoltan-Iosif Korka
Dr. Attila Gerőcs
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. Computation 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 1800 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

  • machine learning
  • fault detection
  • fault diagnosis
  • fault prognosis

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 5766 KiB  
Article
Early Detection of Inter-Turn Short Circuits in Induction Motors Using the Derivative of Stator Current and a Lightweight 1D-ResNet
by Carlos Javier Morales-Perez, David Camarena-Martinez, Juan Pablo Amezquita-Sanchez, Jose de Jesus Rangel-Magdaleno, Edwards Ernesto Sánchez Ramírez and Martin Valtierra-Rodriguez
Computation 2025, 13(6), 140; https://doi.org/10.3390/computation13060140 - 4 Jun 2025
Viewed by 163
Abstract
This work presents a lightweight and practical methodology for detecting inter-turn short-circuit faults in squirrel-cage induction motors under different mechanical load conditions. The proposed approach utilizes a one-dimensional convolutional neural network (1D-CNN) enhanced with residual blocks and trained on differentiated stator current signals [...] Read more.
This work presents a lightweight and practical methodology for detecting inter-turn short-circuit faults in squirrel-cage induction motors under different mechanical load conditions. The proposed approach utilizes a one-dimensional convolutional neural network (1D-CNN) enhanced with residual blocks and trained on differentiated stator current signals obtained under different load mechanical conditions. This preprocessing step enhances fault-related features, enabling improved learning while maintaining the simplicity of a lightweight CNN. The model achieved classification accuracies above 99.16% across all folds in five-fold cross-validation and demonstrated the ability to detect faults involving as few as three short-circuited turns. Comparative experiments with the Multi-Scale 1D-ResNet demonstrate that the proposed method achieves similar or superior performance while significantly reducing training time. These results highlight the model’s suitability for real-time fault detection in embedded and resource-constrained industrial environments. Full article
(This article belongs to the Special Issue Diagnosing Faults with Machine Learning)
Show Figures

Figure 1

Back to TopTop