Impact of Interdependencies: Multi-Component System Perspective toward Predictive Maintenance Based on Machine Learning and XAI
Taking the multi-component perspective in Predictive Maintenance (PdM) is one promising approach to improve prediction quality. Therefore, detection and modeling of interdependencies within systems are important, especially as systems become more complex and personalized. However, existing solutions...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/5/3088 |
| _version_ | 1797615747491430400 |
|---|---|
| author | Milot Gashi Belgin Mutlu Stefan Thalmann |
| author_facet | Milot Gashi Belgin Mutlu Stefan Thalmann |
| author_sort | Milot Gashi |
| collection | DOAJ |
| description | Taking the multi-component perspective in Predictive Maintenance (PdM) is one promising approach to improve prediction quality. Therefore, detection and modeling of interdependencies within systems are important, especially as systems become more complex and personalized. However, existing solutions in PdM mostly focus on a single-component perspective, neglecting the dependencies between components, even if interdependencies can be found between most components in the real world. The major reason for this lost opportunity is the challenge of identifying and modeling interdependencies between components. This paper introduces a framework to identify interdependencies and explain their impact on PdM within a Multi-Component System (MCS). The contribution of this approach is two-fold. First, it shows the impact of modeling interdependencies in predictive analytics. Second, it helps to understand which components interact with each other and to which degree they affect the deterioration state of corresponding components. As a result, our approach can identify and explain the existence of interdependencies within components. In particular, we demonstrate that <i>time from last change of component</i> is a valuable feature to quantify interdependencies. Moreover, we show that taking into account the interdependencies provides a statistically significant improvement of f1-score by 7% on average compared to the model where interdependencies are neglected. We expect that our findings will improve maintenance scheduling in the industry while improving prediction models in general. |
| first_indexed | 2024-03-11T07:31:04Z |
| format | Article |
| id | doaj.art-c34fdb64e344457ba4a4a475e66b6a4e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T07:31:04Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-c34fdb64e344457ba4a4a475e66b6a4e2023-11-17T07:19:04ZengMDPI AGApplied Sciences2076-34172023-02-01135308810.3390/app13053088Impact of Interdependencies: Multi-Component System Perspective toward Predictive Maintenance Based on Machine Learning and XAIMilot Gashi0Belgin Mutlu1Stefan Thalmann2Pro2future GmbH Graz, 8010 Graz, AustriaPro2future GmbH Graz, 8010 Graz, AustriaBusiness Analytics and Data Science Center, University of Graz, 8010 Graz, AustriaTaking the multi-component perspective in Predictive Maintenance (PdM) is one promising approach to improve prediction quality. Therefore, detection and modeling of interdependencies within systems are important, especially as systems become more complex and personalized. However, existing solutions in PdM mostly focus on a single-component perspective, neglecting the dependencies between components, even if interdependencies can be found between most components in the real world. The major reason for this lost opportunity is the challenge of identifying and modeling interdependencies between components. This paper introduces a framework to identify interdependencies and explain their impact on PdM within a Multi-Component System (MCS). The contribution of this approach is two-fold. First, it shows the impact of modeling interdependencies in predictive analytics. Second, it helps to understand which components interact with each other and to which degree they affect the deterioration state of corresponding components. As a result, our approach can identify and explain the existence of interdependencies within components. In particular, we demonstrate that <i>time from last change of component</i> is a valuable feature to quantify interdependencies. Moreover, we show that taking into account the interdependencies provides a statistically significant improvement of f1-score by 7% on average compared to the model where interdependencies are neglected. We expect that our findings will improve maintenance scheduling in the industry while improving prediction models in general.https://www.mdpi.com/2076-3417/13/5/3088predictive maintenanceIndustry 4.0ShapleyXAIMulti-component SystemsInterdependencies |
| spellingShingle | Milot Gashi Belgin Mutlu Stefan Thalmann Impact of Interdependencies: Multi-Component System Perspective toward Predictive Maintenance Based on Machine Learning and XAI Applied Sciences predictive maintenance Industry 4.0 Shapley XAI Multi-component Systems Interdependencies |
| title | Impact of Interdependencies: Multi-Component System Perspective toward Predictive Maintenance Based on Machine Learning and XAI |
| title_full | Impact of Interdependencies: Multi-Component System Perspective toward Predictive Maintenance Based on Machine Learning and XAI |
| title_fullStr | Impact of Interdependencies: Multi-Component System Perspective toward Predictive Maintenance Based on Machine Learning and XAI |
| title_full_unstemmed | Impact of Interdependencies: Multi-Component System Perspective toward Predictive Maintenance Based on Machine Learning and XAI |
| title_short | Impact of Interdependencies: Multi-Component System Perspective toward Predictive Maintenance Based on Machine Learning and XAI |
| title_sort | impact of interdependencies multi component system perspective toward predictive maintenance based on machine learning and xai |
| topic | predictive maintenance Industry 4.0 Shapley XAI Multi-component Systems Interdependencies |
| url | https://www.mdpi.com/2076-3417/13/5/3088 |
| work_keys_str_mv | AT milotgashi impactofinterdependenciesmulticomponentsystemperspectivetowardpredictivemaintenancebasedonmachinelearningandxai AT belginmutlu impactofinterdependenciesmulticomponentsystemperspectivetowardpredictivemaintenancebasedonmachinelearningandxai AT stefanthalmann impactofinterdependenciesmulticomponentsystemperspectivetowardpredictivemaintenancebasedonmachinelearningandxai |