Szczegóły publikacji
Opis bibliograficzny
Tool wear prediction using smart data and advanced change point detection techniques for optimized replacement timing in manufacturing systems / Mateusz Janik, Konrad Krzempek, Piotr Sobecki, Dariusz Mazurkiewicz, Tomasz Żabiński, Grzegorz Piecuch // IFAC-PapersOnLine [Dokument elektroniczny]. — Czasopismo elektroniczne ; ISSN 2405-8963 . — 2025 — vol. 59 iss. 24, s. 137-142. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 142, Abstr. — Publikacja dostępna online od: 2025-12-09. — M. Janik, K. Krzempek - afiliacja: Laboratory of Artificial Intelligence, Central Office of Measures, Warsaw, Poland; Laboratory of Artificial Intelligence, Świętokrzyski Laboratory Campus of the Central Office of Measures, Kielce, Poland. — 15th IFAC workshop on Intelligent Manufacturing Systems IMS 2025 : Koszalin, Poland, September 11-12, 2025
Autorzy (6)
- Janik Mateusz
- Krzempek Konrad
- Sobecki Piotr
- Mazurkiewicz Dariusz
- Żabiński Tomasz
- Piecuch Grzegorz
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 165712 |
|---|---|
| Data dodania do BaDAP | 2026-01-28 |
| Tekst źródłowy | URL |
| DOI | 10.1016/j.ifacol.2025.11.854 |
| Rok publikacji | 2025 |
| Typ publikacji | referat w czasopiśmie |
| Otwarty dostęp |  |
| Creative Commons | |
| Czasopismo/seria | IFAC-PapersOnLine |
Abstract
This publication addresses a key challenge in predictive maintenance by proposing a novel approach to tool wear prediction based on change-point detection in signal characteristics. Despite extensive studies on tool wear monitoring, many existing methods lack accuracy in identifying early wear stages under real-time manufacturing conditions. To bridge this gap, this study employs the Pruned Exact Linear Time (PELT) algorithm combined with bandpass filtering and wavelet-based signal energy analysis. The proposed method enables precise detection of tool wear progression by identifying characteristic frequency shifts and abrupt signal changes. Experimental results demonstrate the effectiveness of this approach in forecasting optimal tool replacement timing, reducing maintenance costs, and enhancing manufacturing system reliability. This contribution offers a practical and scalable solution, with potential for integration into real-time machine health monitoring frameworks.
