Data-Driven Fault Detection and Diagnosis: Challenges and Opportunities in Real-World Scenarios
The pervasive digital innovation of the last decades has led to a remarkable transformation of maintenance strategies. The data collected from machinery and the extraction of valuable information through machine learning (ML) have assumed a crucial role. As a result, data-driven predictive maintenan...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/18/9212 |
| _version_ | 1797491465979428864 |
|---|---|
| author | Francesca Calabrese Alberto Regattieri Marco Bortolini Francesco Gabriele Galizia |
| author_facet | Francesca Calabrese Alberto Regattieri Marco Bortolini Francesco Gabriele Galizia |
| author_sort | Francesca Calabrese |
| collection | DOAJ |
| description | The pervasive digital innovation of the last decades has led to a remarkable transformation of maintenance strategies. The data collected from machinery and the extraction of valuable information through machine learning (ML) have assumed a crucial role. As a result, data-driven predictive maintenance (PdM) has received significant attention from academics and industries. However, practical issues are limiting the implementation of PdM in manufacturing plants. These issues are related to the availability, quantity, and completeness of the collected data, which do not contain all machinery health conditions, are often unprovided with the contextual information needed by ML models, and are huge in terms of gigabytes per minute. As an extension of previous work by the authors, this paper aims to validate the methodology for streaming fault and novelty detection that reduces the quantity of data to transfer and store, allows the automatic collection of contextual information, and recognizes novel system behaviors. Five distinct datasets are collected from the field, and results show that streaming and incremental clustering-based approaches are effective tools for obtaining labeled datasets and real-time feedback on the machinery’s health condition. |
| first_indexed | 2024-03-10T00:48:53Z |
| format | Article |
| id | doaj.art-502a17858598403d829576690a8e40c6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T00:48:53Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-502a17858598403d829576690a8e40c62023-11-23T14:54:50ZengMDPI AGApplied Sciences2076-34172022-09-011218921210.3390/app12189212Data-Driven Fault Detection and Diagnosis: Challenges and Opportunities in Real-World ScenariosFrancesca Calabrese0Alberto Regattieri1Marco Bortolini2Francesco Gabriele Galizia3Department of Industrial Engineering (DIN), University of Bologna, 40136 Bologna, ItalyDepartment of Industrial Engineering (DIN), University of Bologna, 40136 Bologna, ItalyDepartment of Industrial Engineering (DIN), University of Bologna, 40136 Bologna, ItalyDepartment of Industrial Engineering (DIN), University of Bologna, 40136 Bologna, ItalyThe pervasive digital innovation of the last decades has led to a remarkable transformation of maintenance strategies. The data collected from machinery and the extraction of valuable information through machine learning (ML) have assumed a crucial role. As a result, data-driven predictive maintenance (PdM) has received significant attention from academics and industries. However, practical issues are limiting the implementation of PdM in manufacturing plants. These issues are related to the availability, quantity, and completeness of the collected data, which do not contain all machinery health conditions, are often unprovided with the contextual information needed by ML models, and are huge in terms of gigabytes per minute. As an extension of previous work by the authors, this paper aims to validate the methodology for streaming fault and novelty detection that reduces the quantity of data to transfer and store, allows the automatic collection of contextual information, and recognizes novel system behaviors. Five distinct datasets are collected from the field, and results show that streaming and incremental clustering-based approaches are effective tools for obtaining labeled datasets and real-time feedback on the machinery’s health condition.https://www.mdpi.com/2076-3417/12/18/9212predictive maintenanceindustrial applicationfault detection and diagnosisnovelty detection |
| spellingShingle | Francesca Calabrese Alberto Regattieri Marco Bortolini Francesco Gabriele Galizia Data-Driven Fault Detection and Diagnosis: Challenges and Opportunities in Real-World Scenarios Applied Sciences predictive maintenance industrial application fault detection and diagnosis novelty detection |
| title | Data-Driven Fault Detection and Diagnosis: Challenges and Opportunities in Real-World Scenarios |
| title_full | Data-Driven Fault Detection and Diagnosis: Challenges and Opportunities in Real-World Scenarios |
| title_fullStr | Data-Driven Fault Detection and Diagnosis: Challenges and Opportunities in Real-World Scenarios |
| title_full_unstemmed | Data-Driven Fault Detection and Diagnosis: Challenges and Opportunities in Real-World Scenarios |
| title_short | Data-Driven Fault Detection and Diagnosis: Challenges and Opportunities in Real-World Scenarios |
| title_sort | data driven fault detection and diagnosis challenges and opportunities in real world scenarios |
| topic | predictive maintenance industrial application fault detection and diagnosis novelty detection |
| url | https://www.mdpi.com/2076-3417/12/18/9212 |
| work_keys_str_mv | AT francescacalabrese datadrivenfaultdetectionanddiagnosischallengesandopportunitiesinrealworldscenarios AT albertoregattieri datadrivenfaultdetectionanddiagnosischallengesandopportunitiesinrealworldscenarios AT marcobortolini datadrivenfaultdetectionanddiagnosischallengesandopportunitiesinrealworldscenarios AT francescogabrielegalizia datadrivenfaultdetectionanddiagnosischallengesandopportunitiesinrealworldscenarios |