Name
Title | ||
|---|---|---|
Roller Bearing Failures Classification with Low Computational Cost Embedded Machine Learning |
Abstract | ||
|---|---|---|
In this work, the authors present a Machine Learning (ML) algorithm which is able to detect incipient failures of roller bearings starting from data provided by accelerometers. Three typologies of signals coming from typical bearing failures are exploited to test the algorithm. Specifically, faults related to the bearing balls, the inner raceways, and the outer raceways are taken into account. Besides these, also a control set containing data related to bearings having no faults is exploited. Moreover, the ML algorithm is designed to be executed by a microprocessor, which can be used in a distributed sensor network that can be the base for an Internet of Things (IoT) monitoring system. In so doing, a predictive maintenance paradigm, relying on Artificial Intelligence (AI), for bearings is set up, enabling condition monitoring systems to actively predict faults thus timely halting machines. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/MetroAutomotive54295.2022.9855137 | 2022 IEEE International Workshop on Metrology for Automotive (MetroAutomotive) |
Keywords | DocType | ISBN |
Roller Bearing Failure,Machine Learning,Artificial Intelligence,Condition Monitoring,IoT,Vibrations,Predictive Maintenance,Microcontroller | Conference | 978-1-6654-6690-5 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Matteo Bertocco | 1 | 0 | 0.68 |
| Ada Fort | 2 | 1 | 2.09 |
| Elia Landi | 3 | 2 | 5.14 |
| Marco Mugnaini | 4 | 1 | 1.75 |
| Lorenzo Parri | 5 | 3 | 5.10 |
| Giacomo Peruzzi | 6 | 1 | 1.03 |
| Alessandro Pozzebon | 7 | 0 | 1.35 |