Real-Time Neural Classifiers for Sensor and Actuator Faults in Three-Phase Induction Motors

Sánchez, Oscar D.; Martinez-Soltero, Gabriel; Álvarez, Jesús Gerardo Cruz; Alanis, Alma Y.

doi:10.3390/machines10121198

Cited by 5 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where c t−1 represents the previous memory cell state value, the operation × is matrix vector multiplication, and the operation ⊗ is the Element-Wise product [28][29][30][31]. As highlighted in Section 1, the FDI system addresses the crucial challenge of timely and accurate detection of faults in multirotor UAVs.…”

Section: Overview Of Lstmmentioning

confidence: 99%

Deep Learning-Based Robust Actuator Fault Detection and Isolation Scheme for Highly Redundant Multirotor UAVs

Debele

Shi

Wondosen

et al. 2023

Drones

View full text Add to dashboard Cite

This article presents a novel approach for detecting and isolating faulty actuators in highly redundant Multirotor UAVs using cascaded Deep Neural Network (DNN) models. The proposed Fault Detection and Isolation (FDI) framework combines Long Short-Term Memory (LSTM)-based fault detection and faulty actuator locator models to achieve real-time monitoring. The study focuses on a Hexadecarotor multirotor UAV equipped with sixteen rotors. To tackle the complexity of FDI resulting from redundancy, a partitioning technique is introduced based on system dynamics. The proposed FDI scheme is composed of a region classifier model responsible for detecting faults and fault locator models that precisely determine the location of the failed actuator. Extensive training and testing of the models demonstrate high accuracy, with the regional classifier model achieving 98.97% accuracy and the fault locator model achieving 99.107% accuracy. Furthermore, the scheme was integrated into the flight control system of the UAV, before being tested via both real-time monitoring in the simulation environment and analysis of recorded real flight data. The models exhibit remarkable performance in detecting and localizing injected faults. Therefore, using DNN models and the partitioning technique, this research offers a promising method for accurately detecting and isolating faulty actuators, thereby improving the overall performance and dependability of highly redundant Multirotor UAVs in various operational scenarios.

show abstract

Section: Overview Of Lstmmentioning

confidence: 99%

Deep Learning-Based Robust Actuator Fault Detection and Isolation Scheme for Highly Redundant Multirotor UAVs

Debele

Shi

Wondosen

et al. 2023

Drones

View full text Add to dashboard Cite

show abstract

“…In the work published by our research group [28], we focus on the applicability of deep neural networks for failure classification, mainly on actuators with simulated data. Also, using a convolutional neural network with 1×1 kernel in the convolution layer for the classification of univariate time series.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Neural Classifiers for Sensor Faults in Three Phase Induction Motors

et al. 2023

Self Cite

View full text Add to dashboard Cite

Induction motors can be modeled in different ways for correct operation and control, one of these is the αβ representation, this model has six state variables that can be monitored: rotor position, rotor speed, α flux, β flux, α current and β current. Usually, only three of these variables can be measured directly with sensors. These sensors are subject to long periods of work and stress, so a failure in these sensors cannot be ruled out. Sensor failure can cause problems to control the motor, instability or motor performance degradation. That is why fault tolerant controllers are proposed to maintain the stability of the induction motor despite sensor failure, assuming that the error is classified correctly and in a short period of time. This paper is concerned with the detection and classification of sensor faults: rotor position, α and β currents, in real time, considered faults can occur by sensor disconnection, sensor degradation, sensor failure, or connection damage, among other hardware or software phenomena. Different neural networks are proposed and compared for real-time classification, these are: Multilayer perceptron, convolutional neural network, the unidirectional Long short-term memory (LSTM) and bidirectional LSTM. The results show that the CNN neural network presents the best performance compared to the other methods, but the LSTM has a shorter classification time with high accuracy to classify the true class. The CNN used corresponds to a simple configuration of a convolution layer with 20 filters of 2×1, followed by a pooling layer and two dense layers. The results show that CNN has a classification accuracy above 99% and an average classification time per sample of 4.6236e-08 s. For its part, the LSTM shows a classification accuracy of approximately 99% and an average classification time per sample of 3.1298e-09 s, MLP shows a classification accuracy of 97.96% with a classification time of 5.5 e-10 s, while BiLSTM shows an accuracy above of 98% and a classification time of 4.47e-4 s.

show abstract

“…Then, the reconfiguration stage, the last stage of FDIR, involves modifying the system configuration to compensate for the faulty component or subsystem identified during the fault isolation phase. By integrating alternative measurements, estimations, or controllers, system reconfiguration aims to restore the system's functionality and ensure its continued operation with acceptable performance despite the presence of the fault [24].…”

Section: Introductionmentioning

confidence: 99%

Experimental Validation of Current Sensors Fault Detection and Tolerant Control Strategy for Three-Phase Permanent Magnet Synchronous Motor Drives

Azzoug,

Pusca,

Sahraoui

et al. 2023

Machines

View full text Add to dashboard Cite

This paper presents the experimental validation of a Fault-Tolerant Control (FTC) system for Permanent Magnet Synchronous Motor (PMSM) drives, specifically focusing on current sensors. The FTC system is designed to detect and diagnose both single and multiple faults in the current sensors and to reconfigure the control loop to ensure uninterrupted operation in the presence of such faults. Several crucial aspects are addressed in the proposed approach, including fault detection, isolation of faulty sensors, and reconfiguration of the control system through accurate current estimation. To achieve this, a novel adaptation of the Luenberger observer is proposed and employed for estimating the stator currents. The effectiveness of the fault-tolerant control strategy is demonstrated through experimental tests conducted on a 7.2 kW PMSM utilizing a field-oriented vectorial strategy implemented in a dSpace 1104 platform.

show abstract

Real-Time Neural Classifiers for Sensor and Actuator Faults in Three-Phase Induction Motors

Cited by 5 publications

References 53 publications

Deep Learning-Based Robust Actuator Fault Detection and Isolation Scheme for Highly Redundant Multirotor UAVs

Deep Learning-Based Robust Actuator Fault Detection and Isolation Scheme for Highly Redundant Multirotor UAVs

Real-Time Neural Classifiers for Sensor Faults in Three Phase Induction Motors

Experimental Validation of Current Sensors Fault Detection and Tolerant Control Strategy for Three-Phase Permanent Magnet Synchronous Motor Drives

Contact Info

Product

Resources

About