|
|
|
|
LEADER |
03162nam a2200445Ia 4500 |
001 |
0.3390-s22082837 |
008 |
220421s2022 CNT 000 0 und d |
020 |
|
|
|a 14248220 (ISSN)
|
245 |
1 |
0 |
|a MEDEP: Maintenance Event Detection for Multivariate Time Series Based on the PELT Approach
|
260 |
|
0 |
|b MDPI
|c 2022
|
856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.3390/s22082837
|
520 |
3 |
|
|a Predictive Maintenance (PdM) is one of the most important applications of advanced data science in Industry 4.0, aiming to facilitate manufacturing processes. To build PdM models, sufficient data, such as condition monitoring and maintenance data of the industrial application, are required. However, collecting maintenance data is complex and challenging as it requires human involvement and expertise. Due to time constrains, motivating workers to provide comprehensive labeled data is very challenging, and thus maintenance data are mostly incomplete or even completely missing. In addition to these aspects, a lot of condition monitoring data-sets exist, but only very few labeled small maintenance data-sets can be found. Hence, our proposed solution can provide additional labels and offer new research possibilities for these data-sets. To address this challenge, we introduce MEDEP, a novel maintenance event detection framework based on the Pruned Exact Linear Time (PELT) approach, promising a low false-positive (FP) rate and high accuracy results in general. MEDEP could help to automatically detect performed maintenance events from the deviations in the condition monitoring data. A heuristic method is proposed as an extension to the PELT approach consisting of the following two steps: (1) mean threshold for multivariate time series and (2) distribution threshold analysis based on the complexity-invariant metric. We validate and compare MEDEP on the Microsoft Azure Predictive Maintenance data-set and data from a real-world use case in the welding industry. The experimental outcomes of the proposed approach resulted in a superior performance with an FP rate of around 10% on average and high sensitivity and accuracy results. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
|
650 |
0 |
4 |
|a change point detection
|
650 |
0 |
4 |
|a Change point detection
|
650 |
0 |
4 |
|a Condition monitoring
|
650 |
0 |
4 |
|a Condition-monitoring data
|
650 |
0 |
4 |
|a Data set
|
650 |
0 |
4 |
|a event detection
|
650 |
0 |
4 |
|a Events detection
|
650 |
0 |
4 |
|a Heuristic methods
|
650 |
0 |
4 |
|a Linear time
|
650 |
0 |
4 |
|a Maintenance
|
650 |
0 |
4 |
|a maintenance event detection
|
650 |
0 |
4 |
|a Maintenance event detection
|
650 |
0 |
4 |
|a Multivariate time series
|
650 |
0 |
4 |
|a predictive maintenance
|
650 |
0 |
4 |
|a Predictive maintenance
|
650 |
0 |
4 |
|a Time series
|
650 |
0 |
4 |
|a Time series analysis
|
650 |
0 |
4 |
|a Welding
|
650 |
0 |
4 |
|a welding industry
|
650 |
0 |
4 |
|a Welding industry
|
650 |
0 |
4 |
|a Windows operating system
|
700 |
1 |
0 |
|a Gashi, M.
|e author
|
700 |
1 |
0 |
|a Gursch, H.
|e author
|
700 |
1 |
0 |
|a Hinterbichler, H.
|e author
|
700 |
1 |
0 |
|a Lindstaedt, S.
|e author
|
700 |
1 |
0 |
|a Pichler, S.
|e author
|
700 |
1 |
0 |
|a Thalmann, S.
|e author
|
773 |
|
|
|t Sensors
|