Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection Tasks
For the last two decades, artificial neural networks (ANNs) of the third generation, also known as spiking neural networks (SNN), have remained a subject of interest for researchers. A significant difficulty for the practical application of SNNs is their poor suitability for von Neumann computer arc...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/7/2/110 |
| _version_ | 1797596112054386688 |
|---|---|
| author | Vladislav Kholkin Olga Druzhina Valerii Vatnik Maksim Kulagin Timur Karimov Denis Butusov |
| author_facet | Vladislav Kholkin Olga Druzhina Valerii Vatnik Maksim Kulagin Timur Karimov Denis Butusov |
| author_sort | Vladislav Kholkin |
| collection | DOAJ |
| description | For the last two decades, artificial neural networks (ANNs) of the third generation, also known as spiking neural networks (SNN), have remained a subject of interest for researchers. A significant difficulty for the practical application of SNNs is their poor suitability for von Neumann computer architecture, so many researchers are currently focusing on the development of alternative hardware. Nevertheless, today several experimental libraries implementing SNNs for conventional computers are available. In this paper, using the RCNet library, we compare the performance of reservoir computing architectures based on artificial and spiking neural networks. We explicitly show that, despite the higher execution time, SNNs can demonstrate outstanding classification accuracy in the case of complicated datasets, such as data from industrial sensors used for the fault detection of bearings and gears. For one of the test problems, namely, ball bearing diagnosis using an accelerometer, the accuracy of the classification using reservoir SNN almost reached 100%, while the reservoir ANN was able to achieve recognition accuracy up to only 61%. The results of the study clearly demonstrate the superiority and benefits of SNN classificators. |
| first_indexed | 2024-03-11T02:45:53Z |
| format | Article |
| id | doaj.art-9d0cd8210eec47248d30b9942fdd5439 |
| institution | Directory Open Access Journal |
| issn | 2504-2289 |
| language | English |
| last_indexed | 2024-03-11T02:45:53Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj.art-9d0cd8210eec47248d30b9942fdd54392023-11-18T09:18:53ZengMDPI AGBig Data and Cognitive Computing2504-22892023-06-017211010.3390/bdcc7020110Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection TasksVladislav Kholkin0Olga Druzhina1Valerii Vatnik2Maksim Kulagin3Timur Karimov4Denis Butusov5Department of Computer-Aided Design, St. Petersburg Electrotechnical University “LETI”, 5 Professora Popova St., 197022 Saint Petersburg, RussiaYouth Research Institute, St. Petersburg Electrotechnical University “LETI”, 5 Professora Popova St., 197022 Saint Petersburg, RussiaDepartment of Computer-Aided Design, St. Petersburg Electrotechnical University “LETI”, 5 Professora Popova St., 197022 Saint Petersburg, RussiaYouth Research Institute, St. Petersburg Electrotechnical University “LETI”, 5 Professora Popova St., 197022 Saint Petersburg, RussiaYouth Research Institute, St. Petersburg Electrotechnical University “LETI”, 5 Professora Popova St., 197022 Saint Petersburg, RussiaDepartment of Computer-Aided Design, St. Petersburg Electrotechnical University “LETI”, 5 Professora Popova St., 197022 Saint Petersburg, RussiaFor the last two decades, artificial neural networks (ANNs) of the third generation, also known as spiking neural networks (SNN), have remained a subject of interest for researchers. A significant difficulty for the practical application of SNNs is their poor suitability for von Neumann computer architecture, so many researchers are currently focusing on the development of alternative hardware. Nevertheless, today several experimental libraries implementing SNNs for conventional computers are available. In this paper, using the RCNet library, we compare the performance of reservoir computing architectures based on artificial and spiking neural networks. We explicitly show that, despite the higher execution time, SNNs can demonstrate outstanding classification accuracy in the case of complicated datasets, such as data from industrial sensors used for the fault detection of bearings and gears. For one of the test problems, namely, ball bearing diagnosis using an accelerometer, the accuracy of the classification using reservoir SNN almost reached 100%, while the reservoir ANN was able to achieve recognition accuracy up to only 61%. The results of the study clearly demonstrate the superiority and benefits of SNN classificators.https://www.mdpi.com/2504-2289/7/2/110artificial neural networksspiking neural networksreservoir computingfault diagnosis |
| spellingShingle | Vladislav Kholkin Olga Druzhina Valerii Vatnik Maksim Kulagin Timur Karimov Denis Butusov Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection Tasks Big Data and Cognitive Computing artificial neural networks spiking neural networks reservoir computing fault diagnosis |
| title | Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection Tasks |
| title_full | Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection Tasks |
| title_fullStr | Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection Tasks |
| title_full_unstemmed | Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection Tasks |
| title_short | Comparing Reservoir Artificial and Spiking Neural Networks in Machine Fault Detection Tasks |
| title_sort | comparing reservoir artificial and spiking neural networks in machine fault detection tasks |
| topic | artificial neural networks spiking neural networks reservoir computing fault diagnosis |
| url | https://www.mdpi.com/2504-2289/7/2/110 |
| work_keys_str_mv | AT vladislavkholkin comparingreservoirartificialandspikingneuralnetworksinmachinefaultdetectiontasks AT olgadruzhina comparingreservoirartificialandspikingneuralnetworksinmachinefaultdetectiontasks AT valeriivatnik comparingreservoirartificialandspikingneuralnetworksinmachinefaultdetectiontasks AT maksimkulagin comparingreservoirartificialandspikingneuralnetworksinmachinefaultdetectiontasks AT timurkarimov comparingreservoirartificialandspikingneuralnetworksinmachinefaultdetectiontasks AT denisbutusov comparingreservoirartificialandspikingneuralnetworksinmachinefaultdetectiontasks |