Fault-Tolerant Closed-Loop Controller Using Online Fault Detection by Neural Networks
This paper presents an online model-free sensor fault-tolerant control scheme capable of tolerating the most common faults affecting an induction motor. This approach involves using neural networks for fault detection to provide the controller with sufficient information to counteract adverse conseq...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/12/12/844 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850102887638630400 |
|---|---|
| author | Alma Y. Alanis Jesus G. Alvarez Oscar D. Sanchez Hannia M. Hernandez Arturo Valdivia-G |
| author_facet | Alma Y. Alanis Jesus G. Alvarez Oscar D. Sanchez Hannia M. Hernandez Arturo Valdivia-G |
| author_sort | Alma Y. Alanis |
| collection | DOAJ |
| description | This paper presents an online model-free sensor fault-tolerant control scheme capable of tolerating the most common faults affecting an induction motor. This approach involves using neural networks for fault detection to provide the controller with sufficient information to counteract adverse consequences due to sensor faults, such as degradation in performance, reliability, and even failures in the control system. The proposed approach does not consider the knowledge of the nominal model of the system or when the fault may occur. Therefore, a high-order recurrent neural network trained online by the Extended Kalman Filter is used to obtain a mathematical model of the system. The obtained model is used to synthesize a discrete-time sliding mode control. Then, the fault-detection and -isolation stage is performed by independent neural networks, which have as input the signal from the current sensor and the position sensor, respectively. In this way, the neural classifiers continuously monitor the sensors, showing the ability to know the sensor status. The combination of controller and fault detection maintains the operation of the motor during the time of the fault occurrence, whether due to sensor disconnection, degradation, or connection failure. In fact, the MLP neural network achieves an accuracy between 95% and 99% and shows an AUC of 97% to 99%, and this neural network correctly classifies true positives with acceptable performance. The <i>Recall</i> value is high, between 97% and 99%, and the <i>F</i>1 score confirms a good performance. In contrast, the CNN shows a higher accuracy, between 96% and 99% in <i>accuracy</i> and 98% to 99% in AUC. In addition, its <i>Recall</i> and <i>F</i>1 reflect a better balance and capacity to handle complex data, demonstrating its superiority to MLP in fault classification. Therefore, neural networks are a promising approach in areas such as fault-tolerant control. |
| format | Article |
| id | doaj-art-f3757cb512dc4e60a36fee86420ffd4a |
| institution | DOAJ |
| issn | 2075-1702 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj-art-f3757cb512dc4e60a36fee86420ffd4a2025-08-20T02:39:40ZengMDPI AGMachines2075-17022024-11-01121284410.3390/machines12120844Fault-Tolerant Closed-Loop Controller Using Online Fault Detection by Neural NetworksAlma Y. Alanis0Jesus G. Alvarez1Oscar D. Sanchez2Hannia M. Hernandez3Arturo Valdivia-G4University Center of Exact Sciences and Engineering, University of Guadalajara, Marcelino Garcia Barragan 1421, Guadalajara 44430, MexicoUniversity Center of Exact Sciences and Engineering, University of Guadalajara, Marcelino Garcia Barragan 1421, Guadalajara 44430, MexicoUniversity Center of Exact Sciences and Engineering, University of Guadalajara, Marcelino Garcia Barragan 1421, Guadalajara 44430, MexicoUniversity Center of Exact Sciences and Engineering, University of Guadalajara, Marcelino Garcia Barragan 1421, Guadalajara 44430, MexicoUniversity Center of Exact Sciences and Engineering, University of Guadalajara, Marcelino Garcia Barragan 1421, Guadalajara 44430, MexicoThis paper presents an online model-free sensor fault-tolerant control scheme capable of tolerating the most common faults affecting an induction motor. This approach involves using neural networks for fault detection to provide the controller with sufficient information to counteract adverse consequences due to sensor faults, such as degradation in performance, reliability, and even failures in the control system. The proposed approach does not consider the knowledge of the nominal model of the system or when the fault may occur. Therefore, a high-order recurrent neural network trained online by the Extended Kalman Filter is used to obtain a mathematical model of the system. The obtained model is used to synthesize a discrete-time sliding mode control. Then, the fault-detection and -isolation stage is performed by independent neural networks, which have as input the signal from the current sensor and the position sensor, respectively. In this way, the neural classifiers continuously monitor the sensors, showing the ability to know the sensor status. The combination of controller and fault detection maintains the operation of the motor during the time of the fault occurrence, whether due to sensor disconnection, degradation, or connection failure. In fact, the MLP neural network achieves an accuracy between 95% and 99% and shows an AUC of 97% to 99%, and this neural network correctly classifies true positives with acceptable performance. The <i>Recall</i> value is high, between 97% and 99%, and the <i>F</i>1 score confirms a good performance. In contrast, the CNN shows a higher accuracy, between 96% and 99% in <i>accuracy</i> and 98% to 99% in AUC. In addition, its <i>Recall</i> and <i>F</i>1 reflect a better balance and capacity to handle complex data, demonstrating its superiority to MLP in fault classification. Therefore, neural networks are a promising approach in areas such as fault-tolerant control.https://www.mdpi.com/2075-1702/12/12/844deep neural networkfault-tolerant controlfault detection and isolationinduction motordata streams |
| spellingShingle | Alma Y. Alanis Jesus G. Alvarez Oscar D. Sanchez Hannia M. Hernandez Arturo Valdivia-G Fault-Tolerant Closed-Loop Controller Using Online Fault Detection by Neural Networks Machines deep neural network fault-tolerant control fault detection and isolation induction motor data streams |
| title | Fault-Tolerant Closed-Loop Controller Using Online Fault Detection by Neural Networks |
| title_full | Fault-Tolerant Closed-Loop Controller Using Online Fault Detection by Neural Networks |
| title_fullStr | Fault-Tolerant Closed-Loop Controller Using Online Fault Detection by Neural Networks |
| title_full_unstemmed | Fault-Tolerant Closed-Loop Controller Using Online Fault Detection by Neural Networks |
| title_short | Fault-Tolerant Closed-Loop Controller Using Online Fault Detection by Neural Networks |
| title_sort | fault tolerant closed loop controller using online fault detection by neural networks |
| topic | deep neural network fault-tolerant control fault detection and isolation induction motor data streams |
| url | https://www.mdpi.com/2075-1702/12/12/844 |
| work_keys_str_mv | AT almayalanis faulttolerantclosedloopcontrollerusingonlinefaultdetectionbyneuralnetworks AT jesusgalvarez faulttolerantclosedloopcontrollerusingonlinefaultdetectionbyneuralnetworks AT oscardsanchez faulttolerantclosedloopcontrollerusingonlinefaultdetectionbyneuralnetworks AT hanniamhernandez faulttolerantclosedloopcontrollerusingonlinefaultdetectionbyneuralnetworks AT arturovaldiviag faulttolerantclosedloopcontrollerusingonlinefaultdetectionbyneuralnetworks |