Digitalization of Nuclear Power Plant Asset Management Using Artificial Intelligence and Machine Learning Methods
A special issue of Energies (ISSN 1996-1073). This special issue belongs to the section "B4: Nuclear Energy".
Deadline for manuscript submissions: 30 May 2024 | Viewed by 254
Special Issue Editors
2. Energy Department, Politecnico di Milano, Via La Masa 34, 20156 Milano, Italy
Interests: risk assessment; reliability analysis; simulation; artificial intelligence; nuclear systems
Special Issues, Collections and Topics in MDPI journals
Interests: nuclear systems
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
The quest for improving the safety and reliability of Nuclear Power Plants (NPP) is motivating the nuclear industry to explore the recent advancements in smart sensing, data analysis and computational efficiency for the realization of reliable control, efficient production, real-time early failure detection and mitigation, the minimization of unplanned shutdown, the improvement of safety and operation, and a reduction in maintenance costs. Paired with the increasing adoption of digitalization in nuclear systems and the associated availability of large volumes of data, Artificial Intelligence (AI) and Machine Learning (ML) methods offer the enhanced capacity to determine the operating conditions directly from a wide range of heterogenous datasets, ranging from single modality to multi-modality sets of data.
The aim of this Special Issue is to promote, collect and share recent research in AI and ML advancements, including both methodological and practical research for the digitalization of nuclear systems, ranging from modeling and simulation, control, prediction, detection, diagnostics and prognostics, to reliability decision-making and risk assessment.
The topics of interest include, but are not limited to, the following:
- Digital twins and digital-twin-enabling technologies for the modelling and simulation of NPP;
- AI/ML methods for prognostics and health management of NPP components and systems;
- AI/ML methods for structural health management of NPP assets;
- AI/ML methods for resilience assessment and enhancement of NPP;
- Reinforcement learning for maintenance decision-making in NPP;
- Explainability/interpretability of AI/ML methods for NPP applications;
- Risk-informed system health and asset management;
- Risk-informed condition-based predictive maintenance;
- AI/ML methods for domain adaptation;
- Other relevant AI and ML approaches for the digitalization of NPP.
Prof. Dr. Enrico Zio
Dr. Ibrahim Ahmed
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. Energies 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 2600 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
- nuclear power plants
- digital twin
- asset management
- control
- prognostics and health management
- artificial intelligence
- machine learning
Planned Papers
The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.
Title: Challenges of artificial intelligence in nuclear safety regulation
Authors: José Balmisa
Affiliation: Consejo de Seguridad Nuclear (Spain)
Title: Reliability evaluation of reinforcement learning for autonomous control in nuclear power plants
Authors: Wenqing Yao etc.
Affiliation: China Nuclear Power Engineering Co., Ltd.
Abstract: Special evaluation metrics and methods should be considered on AI reliability (or quality), such as robustness, fairness, explainability, lineage, expandability, uncertainty and so on. This work first reviews the research and practices of AI reliability in both academia and industry. A reinforcement learning model for HPR1000 auxiliary steam release valve control after SGTR accident is then described and analyzed on these aspects as an example. Performance analysis is performed independently from the research group who wrote the algorithm. Adversarial samples are generated to test the model’s susceptibility to sensor noise. The results are shown and comprehensive methodologies are proposed to evaluate the reliability of AI algorithms in actual applications.
