<?xml version="1.0" encoding="UTF-8"?> <article key="pdf/10013004" mdate="2023-03-14 00:00:00"> <author>Marcel Chevalier and L茅o Dupont and Sylvain Mari茅 and Fr茅d茅rique Roffet and Elena Stolyarova and William Templier and Costin Vasile</author> <title>Validating ConditionBased Maintenance Algorithms Through Simulation</title> <pages>246 - 252</pages> <year>2023</year> <volume>17</volume> <number>3</number> <journal>International Journal of Industrial and Systems Engineering</journal> <ee>https://publications.waset.org/pdf/10013004</ee> <url>https://publications.waset.org/vol/195</url> <publisher>World Academy of Science, Engineering and Technology</publisher> <abstract>Industrial end users are currently facing an increasing need to reduce the risk of unexpected failures and optimize their maintenance. This calls for both shortterm analysis and longterm ageing anticipation. At Schneider Electric, we tackle those two issues using both Machine Learning and First Principles models. Machine learning models are incrementally trained from normal data to predict expected values and detect statistically significant shortterm deviations. Ageing models are constructed from breaking down physical systems into subassemblies, then determining relevant degradation modes and associating each one to the right kinetic law. Validating such anomaly detection and maintenance models is challenging, both because actual incident and ageing data are rare and distorted by human interventions, and incremental learning depends on human feedback. To overcome these difficulties, we propose to simulate physics, systems and humans &amp;ndash; including asset maintenance operations &amp;ndash; in order to validate the overall approaches in accelerated time and possibly choose between algorithmic alternatives.</abstract> <index>Open Science Index 195, 2023</index> </article>