Artificial-Intelligence-Based Safety Detection in Nuclear Power Plants

Dear Colleagues,

This Special Issue on "Artificial-Intelligence-Based Safety Detection in Nuclear Power Plants" explores the latest advancements in nuclear operation and control. Nuclear power plants rely on extensive instrumentation and monitoring systems to ensure their safe and efficient operation. These systems employ a network of sensors and control rod position indicators to collect real-time data on reactor conditions. The transition from manual, periodic checks to integrated online monitoring (OLM) systems has been significant. This not only supports operational reliability, but also forms the backbone of predictive maintenance strategies, minimizing human intervention and enhancing response precision.

In addition, the application of AI and machine learning has significantly improved fault detection and diagnosis. Techniques such as deep learning and similarity clustering are employed to detect and classify system-level and component-level faults with high accuracy, even with nonlinear operational data.

Furthermore, equipment health management and prediction technologies are driving the transformation of nuclear power equipment maintenance from preventive to predictive maintenance, thereby enhancing operational efficiency. By advancing techniques such as equipment signal feature extraction, lifespan prediction, and maintenance decision-making, these efforts are promoting a revolution in equipment reliability and operational maintenance.

Finally, to support the upcoming paradigm shift towards unmanned or minimally staffed nuclear power installations, artificial intelligence-based autonomous decision-making and intelligent control technologies are playing an increasingly critical role. These technologies help reduce the operational burden on maintenance personnel, while improving fault tolerance, operational safety, and overall reliability.

This Special Issue invites high-quality research on the following topics:

• Knowledge-based\data-driven\knowledge–data-fusion-based fault diagnosis for NPPs;
• Nuclear sensor anomaly detection/online monitoring/fault detection for NPPs;
• Remaining useful life prediction and intelligent maintenance in NPPs;
• Feature extraction and signal processing for devices in NPPs；
• AI-based fault isolation and handling for NPPs;
• Autonomous decision-making and control for NPPs;
• AI-based nuclear safety analysis and operational performance.

Dr. Hang Wang
Dr. Zhanguo Ma
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 250 words) can be sent to the Editorial Office for assessment.

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 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.