Machining sensor data management for operation-level predictive model
Artykuł w czasopiśmie
MNiSW
140
Lista 2021
Status: | |
Autorzy: | Kozłowski Edward, Mazurkiewicz Dariusz, Żabiński Tomasz, Prucnal Sławomir, Sęp Jarosław |
Dyscypliny: | |
Aby zobaczyć szczegóły należy się zalogować. | |
Rok wydania: | 2020 |
Wersja dokumentu: | Drukowana | Elektroniczna |
Język: | angielski |
Wolumen/Tom: | 159 |
Numer artykułu: | 113600 |
Strony: | 1 - 22 |
Impact Factor: | 6,954 |
Web of Science® Times Cited: | 49 |
Scopus® Cytowania: | 59 |
Bazy: | Web of Science | Scopus |
Efekt badań statutowych | TAK |
Materiał konferencyjny: | NIE |
Publikacja OA: | TAK |
Licencja: | |
Sposób udostępnienia: | Witryna wydawcy |
Wersja tekstu: | Ostateczna wersja opublikowana |
Czas opublikowania: | W momencie opublikowania |
Data opublikowania w OA: | 17 czerwca 2020 |
Abstrakty: | angielski |
Effective transition from raw industrial data to knowledge-based executive actions without human action requires developing new analytical tools, what also means new challenges for expert and intelligent systems. Studies must be conducted especially on developing effective analytical solutions for intelligent modules of Computerized Maintenance Management Systems, that take advantage of data analysis and decision support tools to predict and prevent the potential failure of machines or its elements. This is why the idea of a new classifier for condition assessment and Remaining Useful Life (RUL) prediction as an expert system tool for real-time monitoring of the manufacturing process was presented. Based on monitoring and current system check data, a new method enabling both early prediction of the machine tool’s remaining useful life and its current condition classification was devised. Its failure and normal properties were distinguished as well. To this end, it was proposed that the remaining useful life prediction should be made via the combined use of the Support Vector Machine (SVM) as a classification tool and AutoRegressive and Integrated Moving Average (ARIMA) based identification. This would provide process engineers and machine operators with an expert system that is easy to implement and use at the operational level, thus allowing them confidently perform technological processes, according to the acceptable failure probability. |