Application of Automated Machine Learning (AutoML) Method in Wind Turbine Fault Detection

• Published in: Journal of physics. Conference series 2022-08, Vol.2312 (1), p.12074
• Main Authors: Fadzail, N F, Mat Zali, S, Mid, E C, Jailani, R
• Format: Article
• Language: English
• Subjects: Algorithms; Automation; Fault detection; Impedance; Inductance; Induction generators; Machine learning; Maintenance costs; Neural networks; Physics; Root-mean-square errors; Short circuits; Stators; Wind turbines
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/2312/1/012074

Fault detection has drew much attention nowadays, as it can save time and operational maintenance costs, especially in the wind turbine (WT) that is becoming familiar with renewable energy. Machine learning became widespread use in fault detection methods. However, most available machine learning needs more data and much time to train. Therefore, there is a need to detect faults using a few data during the training process. This paper aims to apply Automated Machine Learning (AutoML) method for fault detection in WT systems. The fault detection in the WT system focuses on the internal stator fault in the generator as it is the main part of the WT. The AutoML model was developed using a neural network (NN) algorithm in python based on the Auto-Keras model. The model was developed using four inputs, i.e. stator and rotor currents in the d-q axis ( I qs , I ds , I qr and I dr ) while the outputs are impedance values, i.e. stator resistance, R s , and stator inductance, L s . The WT system used in this research is the doubly-fed induction generator (DFIG) in MATLAB/Simulink. In the Auto-Keras model, the impedance values ( R s and L s ) indicated the condition of the DFIG, either normal or fault conditions. Two fault types were applied to the WT system, i.e. inter-turn short circuit and open circuit fault. The Auto-Keras model was trained and tested with the various values of data. The accuracy and the root means square error (RMSE) value of the model were calculated. The result shows that the accuracy is high as it is more than 93% in most conditions, and the RMSE value is low, close to the zero value. Applying the AutoML method in fault detection of the WT system shows its capability to identify faults accurately.