applsci-logo

Journal Browser

Journal Browser

Application of Artificial Intelligence in Fault Detection, Diagnosis, and Prediction

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 20 October 2025 | Viewed by 488

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer Science, University of Cordoba, 14071 Cordoba, Spain
Interests: machine learning; data mining techniques; soft computing
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
INESC TEC—Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ciência, 4200-465 Porto, Portugal
Interests: multi-agent systems; artificial intelligence; personalisation; recommendation systems; data streams

Special Issue Information

Dear Colleagues,

Artificial Intelligence (AI) has become an invaluable tool in enhancing the detection, diagnosis, and prediction of faults across various industries. These applications are critical for improving system reliability, reducing downtime, and ensuring the efficiency of processes. AI techniques, such as machine learning and deep learning, are particularly useful in identifying potential issues in complex systems where traditional methods may fall short.

In fault detection, AI systems can analyze data from various sensors and devices to automatically identify anomalies or irregular behaviors in equipment or processes. Machine learning models, such as classification algorithms, are trained on historical data to recognize patterns that signify malfunctions or failures. These systems offer real-time monitoring capabilities and can be applied to industries like manufacturing, automotive, energy, and aerospace to prevent costly breakdowns.

For fault diagnosis, AI can help to interpret the underlying causes of system failures by analyzing data from multiple sources, such as operational logs, sensor data, and maintenance records. Advanced diagnostic tools, powered by AI, provide insights into the root causes of faults, improving decision-making processes and ensuring timely interventions. The integration of AI in fault diagnosis systems also enhances precision, reducing human error and the need for manual inspections.

Predictive maintenance, a key application of AI, uses data-driven models to forecast when equipment is likely to fail. By analyzing historical data and patterns, AI models predict potential failures before they occur, allowing for proactive maintenance scheduling and minimizing unexpected downtime. This approach leads to significant cost savings, improved system performance, and extended equipment lifespan.

The topic invites research on both theoretical and applied advancements in AI for fault detection, diagnosis, and prediction. Relevant areas include, but are not limited to, the following:

  • AI-based Fault Detection Techniques: Machine learning and deep learning algorithms for detecting and identifying faults in real-time.
  • Predictive Maintenance: AI models for predicting potential equipment failures and optimizing maintenance schedules.
  • Fault Diagnosis Systems: AI methods for diagnosing faults and identifying their root causes using sensor data and system logs.
  • Anomaly Detection: The application of AI in detecting abnormal behavior in complex systems.
  • Big Data Analytics for Fault Management: Using AI to process and analyze vast amounts of sensor and operational data to enhance fault management capabilities.
  • Data-driven Fault Prediction: Techniques for utilizing data-driven approaches to predict future faults and failures in industrial systems.
  • AI in Industrial Systems: AI applications in various industries, such as manufacturing, automotive, energy, and aerospace, to improve fault detection and maintenance strategies.
  • Integration of AI with the IoT for Fault Management: The use of AI in conjunction with the Internet of Things to enhance fault detection and diagnosis capabilities.

This topic will highlight the latest research and advancements in applying AI to improve fault management processes, leading to more reliable and efficient systems.

Dr. Amelia Zafra
Dr. Bruno Miguel Veloso
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. Applied Sciences 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 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

  • fault detection
  • fault diagnosis
  • predictive maintenance
  • artificial intelligence
  • machine learning
  • deep learning
  • anomaly detection
  • industrial systems

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 (2 papers)

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

Research

14 pages, 590 KiB  
Article
Detection and Identification of Degradation Root Causes in a Photovoltaic Cell Based on Physical Modeling and Deep Learning
by Mohand Djeziri, Ndricim Ferko, Marc Bendahan, Hiba Al Sheikh and Nazih Moubayed
Appl. Sci. 2025, 15(14), 7684; https://doi.org/10.3390/app15147684 (registering DOI) - 9 Jul 2025
Abstract
Photovoltaic (PV) systems are key renewable energy sources due to their ease of implementation, scalability, and global solar availability. Enhancing their lifespan and performance is vital for wider adoption. Identifying degradation root causes is essential for improving PV design and maintenance, thus extending [...] Read more.
Photovoltaic (PV) systems are key renewable energy sources due to their ease of implementation, scalability, and global solar availability. Enhancing their lifespan and performance is vital for wider adoption. Identifying degradation root causes is essential for improving PV design and maintenance, thus extending lifespan. This paper proposes a hybrid fault diagnosis method combining a bond graph-based PV cell model with empirical degradation models to simulate faults, and a deep learning approach for root-cause detection. The experimentally validated model simulates degradation effects on measurable variables (voltage, current, ambient, and cell temperatures). The resulting dataset trains an Optimized Feed-Forward Neural Network (OFFNN), achieving 75.43% accuracy in multi-class classification, which effectively identifies degradation processes. Full article
Show Figures

Figure 1

33 pages, 5290 KiB  
Article
Enhancing Power Converter Reliability Through a Logistic Regression-Based Non-Invasive Fault Diagnosis Technique
by Acácio M. R. Amaral
Appl. Sci. 2025, 15(13), 6971; https://doi.org/10.3390/app15136971 - 20 Jun 2025
Viewed by 173
Abstract
Sustainability can be achieved through the widespread adoption of electrification across multiple sectors of activity, which would thereby enable increased operational efficiency and reduce the environmental impact. The attainment of this purpose relies on electrical circuits that convert electrical energy from renewable power [...] Read more.
Sustainability can be achieved through the widespread adoption of electrification across multiple sectors of activity, which would thereby enable increased operational efficiency and reduce the environmental impact. The attainment of this purpose relies on electrical circuits that convert electrical energy from renewable power plants into forms that are compatible with the specific requirements of the load. Failure of the aforementioned circuits, denominated as power converters, can lead to financial losses resulting from unexpected shutdowns and, in critical systems, can pose significant risks to human life. This article focuses on the topic of fault diagnosis in power converters. Some of the most vulnerable components of these converters are the capacitors used in the DC-link, whose failure evolves gradually. When the capacitor internal resistance (ESR) or the capacitor capacitance (C) exceeds a certain threshold value, it is advisable to propose a system shutdown, as soon as possible, to replace the capacitor. The solution presented in this article combines signal processing techniques (SPTs) with a machine learning (ML) algorithm to determine the optimal time for capacitor replacement. The ML algorithm employed herein was a logistic regression (LR) algorithm which classified the capacitor into one of two states: normal operation (0) or failure (1). To train and evaluate the LR model, two different datasets were created using various electrical quantities that can be measured non-invasively. The model demonstrated excellent performance, achieving an accuracy, precision, recall, and F1 score above 0.99. Full article
Show Figures

Figure 1

Back to TopTop