Physics-Informed Trainable Models and Hybrid Techniques for Diagnostics and Prognostics of Monitored Systems
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Fault Diagnosis & Sensors".
Deadline for manuscript submissions: closed (30 November 2023) | Viewed by 365
Special Issue Editors
Interests: probabilistic modeling; physics-informed machine learning; machine learning; uncertainty quantification; filtering methods; aerospace systems; research software engineering
Interests: prognostics and post-prognostics methods; scientific computing; digital twin; maintenance modeling; expert system modelling; building and structural engineering
Interests: bayesian methods; optimal sensor placement; physics-informed machine learning; digital twin; damage diagnostics; building and structural engineering
Special Issue Information
Dear Colleagues,
Progress in machine learning algorithms and automatic training methods in the last decade have empowered scientists and researchers in many disciplines to build classification and regression models by leveraging historical data. However, in some fields, the lack of data and interpretability of such models, which are often treated as black boxes, hinder their ability to shine. This is the case for diagnostics and prognostics of critical engineering systems like aircraft, space systems, and power plants, to name but a few. In these areas, few failure data are available, hindering the training process, and far-ahead predictions from black-box models are seldomly trusted. Modelling the full physics of failure is limited to key components given the complexity of the underlying physics and computational costs associated with such models. Due to the latter, physics-of-failure models often cannot be embedded in optimization or decision-making algorithms where different scenarios must be explored to maximize objectives like safety, reliability, minimum downtime or profit.
This Special Issue focuses on recent developments in the area of physics-informed machine learning and hybrid modelling for system diagnostics, prognostics and health management. Contributions in both theoretical and applied works are welcome, together with review articles on specific subjects within the scope of the Special Issue. Potential topics include, but are not limited to, the following:
- Models for fault detection, isolation, classification and quantification;
- Models for health-state evolution, failure and remaining useful life prediction;
- Physics-guided surrogate models;
- System-level uncertainty quantification methods for physics-informed machine learning models and their applications;
- Health-aware system performance models;
- Models for feature representation, with an emphasis to physics-informed features;
- Physics-informed models for application generalization, transfer learning and system-level health management;
- Unsupervised learning for pattern or governing equation discovery, applied to the area of system diagnostics, prognostics and health management.
Dr. Matteo Corbetta
Dr. Manuel Chiachio Ruano
Dr. Juan Chiachio Ruano
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. Sensors 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
- physics-informed machine learning
- hybrid modelling
- diagnostics
- prognostics
- fault detection
- failure prognosis
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.
