Empowering Predictive Maintenance
| Autor: | Henrique Costa Marques, Alberto Martinetti, Dennys Wallace Duncan Imbassahy, Guilherme Conceição Rocha |
|---|---|
| Přispěvatelé: | Design Engineering |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Computer science 02 engineering and technology Reuse Machine learning computer.software_genre lcsh:Technology Predictive maintenance Fault detection and isolation lcsh:Chemistry 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering General Materials Science hybrid method Instrumentation lcsh:QH301-705.5 Fluid Flow and Transfer Processes fault classification business.industry lcsh:T Process Chemistry and Technology General Engineering lcsh:QC1-999 anomaly detection Computer Science Applications Statistical classification Safe operation lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 020201 artificial intelligence & image processing Anomaly detection Artificial intelligence State (computer science) Aerospace systems business lcsh:Engineering (General). Civil engineering (General) computer diagnose lcsh:Physics |
| Zdroj: | Applied Sciences Volume 10 Issue 19 Applied Sciences, 10(19):6929, 1-27. MDPI Applied Sciences, Vol 10, Iss 6929, p 6929 (2020) |
| ISSN: | 2076-3417 |
| Popis: | Aerospace systems are composed of hundreds or thousands of components and complex subsystems which need an appropriate health monitoring capability to enable safe operation in various conditions. In terms of monitoring systems, it is possible to find a considerable number of state-of-the-art works in the literature related to ad-hoc solutions. Still, it is challenging to reuse them even with subtle differences in analogous subsystems or components. This paper proposes the Generic Anomaly Detection Hybridization Algorithm (GADHA) aiming to build a more reusable algorithm to support anomaly detection. The solution consists of analyzing different supervised machine learning classification algorithms combined in ensemble techniques, with a physical model when available, and two levels of a decision to estimate the current state of the monitored system. Finally, the proposed algorithm assures at least equal, or, more typically, better, overall accuracy in fault detection and isolation than the application of such algorithms alone, through few adaptations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|