A5027807668- Fuel Cells and Related Materials
- Fault Detection and Control Systems
- Advanced Battery Technologies Research
- Machine Fault Diagnosis Techniques
- Neural Networks and Applications
- Fuzzy Logic and Control Systems
- Machine Learning and ELM
- Electrocatalysts for Energy Conversion
- Advancements in Solid Oxide Fuel Cells
- Engineering Diagnostics and Reliability
- Quality and Safety in Healthcare
- Advanced Memory and Neural Computing
- Stock Market Forecasting Methods
- Neural Networks and Reservoir Computing
- Energy Load and Power Forecasting
- Electric and Hybrid Vehicle Technologies
- Reliability and Maintenance Optimization
- Analytical Chemistry and Sensors
- Advanced battery technologies research
- Advanced Machining and Optimization Techniques
- Advanced machining processes and optimization
- Electrochemical Analysis and Applications
- Business Process Modeling and Analysis
- Medical Coding and Health Information
- Electric Vehicles and Infrastructure
Centre National de la Recherche Scientifique
2008-2019
École Nationale Supérieure de Mécanique et des Microtechniques
2008-2019
Franche-Comté Électronique Mécanique Thermique et Optique - Sciences et Technologies
2010-2019
Fédération de Recherche FCLAB
2014-2019
Université de technologie de belfort-montbéliard
2009-2016
Institut UTINAM
2016
Université Bourgogne Franche-Comté
2016
Université de franche-comté
2014
ASM International
2012
École Nationale d'Ingénieurs de Tarbes
2004
The performance of data-driven prognostics approaches is closely dependent on the form and trend extracted features. Indeed, features that clearly reflect machine degradation should lead to accurate prognostics, which global objective this paper. This paper contributes a new approach for feature extraction/selection: extraction based trigonometric functions cumulative transformation, selection performed by evaluating fitness using monotonicity trendability characteristics. proposition...
Prognostics is a core process of prognostics and health management (PHM) discipline, that estimates the remaining useful life (RUL) degrading machinery to optimize its service delivery potential. However, operates in dynamic environment acquired condition monitoring data are usually noisy subject high level uncertainty/unpredictability, which complicates prognostics. The complexity further increases, when there absence prior knowledge about ground truth (or failure definition). For such...
One remaining technological bottleneck to develop industrial Fuel Cell (FC) applications resides in the system limited useful lifetime. Consequently, it is important failure diagnostic and prognostic tools enabling optimization of FC. Among all existing prognostics approaches, datamining methods such as artificial neural networks aim at estimating process' behavior without huge knowledge about underlying physical phenomena. Nevertheless, this kind approach needs learning dataset. Also,...
Proton Exchange Membrane Fuel Cells (PEMFC) are promising energy converters, but still suffer from a short life duration. Applying Prognostics and Health Management seems to be great solution overcome that issue. But developing prognostics anticipate try avoid failures is critical challenge. To tackle this problem, hybrid approach proposed. It aims at predicting the power aging of PEMFC stack working constant operating condition current solicitation. The main difficulties lack adapted...
Prognostic is nowadays recognized as a key feature in maintenance strategies it should allow avoiding inopportune spending. Real prognostic systems are however scarce industry. That can be explained from different aspects, on of them being the difficulty choosing an efficient technology: many approaches to support process exist, whose applicability highly dependent industrial constraints. Thus, general purpose paper explore way performing failure prognostics so that manager act consequently....