Data-Driven Fault Diagnosis for Machines and Systems

Dear Colleagues,

The Industrial Internet of Things (IIoT), big data analytics, and artificial intelligence (AI) have significantly transformed the realm of fault diagnosis and prognosis in industrial systems and machinery. This transformation has led to the optimization of production processes, improved quality control, and reduced downtime. Compared to traditional methods, data-driven fault diagnosis offers a more precise and efficient approach, capable of adapting to system behavior changes over time. Despite these advancements, the complexity of modern systems and the escalating need for productivity and efficiency continue to present challenges and opportunities for further research in this area.

The proposed Special Issue aims to cover the latest advancements and challenges in data-driven fault diagnosis and prognosis, including the following:

• Novel approaches for data preprocessing, feature extraction, and feature selection;
• Advanced ML algorithms for fault detection, isolation, and classification;
• Online and real-time fault diagnosis and prognosis techniques;
• Hybrid (physics-based and data-driven) models for fault diagnosis;
• Integration of ML-based fault diagnosis with other smart manufacturing technologies;
• Case studies and applications in different industrial domains such as manufacturing, energy, transportation, and others.

The target audience includes researchers and practitioners in ML, data analytics, industrial engineering, and chemical engineering.

The Special Issue will focus on recent advances in three main directions in ML-based fault detection and diagnosis, including the following:

• Deep learning: This Special Issue will explore the latest developments in this area, including the use of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs).
• Explainable AI: The interpretability of machine learning models is a critical issue in industrial fault diagnosis, where decisions can have significant economic and safety implications. This Special Issue will explore recent work on developing explainable AI methods for fault diagnosis, such as rule extraction and feature importance analysis.
• Physics-based deep learning (DL): This is a growing approach that integrates the principles of physics into the design and training of deep learning models. This Special Issue aims to illuminate how this approach contributes to enhancing the effectiveness, interpretability, and reliability of fault detection and diagnosis in machines and systems.
• Transfer learning: Transfer learning is a promising approach for leveraging pre-trained models to improve the performance of fault diagnosis in new domains or with limited data. This Special Issue will investigate recent advances in transfer learning for fault diagnosis in industrial systems and machines.

Dr. Ahmed Ragab
Dr. Mouloud Amazouz
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. Machines 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.

• fault diagnosis and prognosis
• data-driven modeling
• condition monitoring
• predictive maintenance
• anomaly detection
• decision support systems
• causality analysis
• root cause analysis