Fault Detection Based on Deep Learning

Dear Colleagues,

Fault detection is critical to ensure the reliability and safety of industrial systems, infrastructure, and equipment. In recent years, the integration of deep learning techniques into fault detection has shown great promise in enhancing the accuracy and efficiency of diagnostic processes. This Special Issue of Processes aims to explore the latest advancements in the application of deep learning for fault detection across various industries.

In fault detection, deep learning models can process complex sensor data, time-series information, and images to identify faults that may signal impending failures. One of the key challenges in fault detection is handling the large-scale and high-dimensional data generated by modern systems. Deep learning techniques such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and autoencoders have proven to be effective in managing such data, allowing for real-time monitoring and predictive maintenance. Furthermore, techniques such as transfer learning and few-shot learning have made it possible to apply deep learning models to environments with limited labeled data, which is often the case in industrial settings.

For this Special Issue, we seek contributions that cover a wide range of topics related to deep learning-based fault detection, including, but not limited to, the following:

(1) Novel deep learning architectures for fault detection in specific domains (e.g., manufacturing, energy systems, automotive, aerospace, etc.);

(2) Hybrid models that combine deep learning with traditional methods for enhanced performance and robustness;

(3) Transfer learning and data augmentation techniques to improve model generalization with limited fault data;

(4) Explainability and interpretability of deep learning models in fault detection, ensuring their integration into safety-critical applications.

We welcome original research papers that present new methodologies, innovative applications, and insights into the integration of deep learning in fault detection. The goal of this Special Issue is to provide a comprehensive overview of the current state-of-the-art, as well as to stimulate further research and development in this rapidly evolving field. We believe that the combination of deep learning and fault detection has the potential to drive significant advancements in industrial automation, safety, and maintenance, contributing to more efficient, reliable, and sustainable operations.

We look forward to your contributions to this exciting and important area of research.

Prof. Dr. Maoyin Chen
Dr. Zhu Wang
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. Processes 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.

• models
• control
• optimization
• industry