Using Deep Learning to Diagnose Faults in Industrial Power Systems

Using Deep Learning to Diagnose Faults in Industrial Power Systems

Saman Alirezaei1 Helia Mehryab2

1) Department of Electrical Engineering, Shahid Beheshti University, Tehran, Iran
2) Department of Electrical Engineering, Shahid Beheshti University, Tehran, Iran

IOI Code : XKBA-AZHZZD
Publication : 3rd International Conference on Recent Advances in Engineering, Innovation and Technology - Belgium(eitconf.com/3rd)
Abstract :
    In this Paper, Deep Learning (DL) is utilized as an innovative method for fault detection in industrial electrical systems. Industrial electrical systems face high complexity and sensitivity, and faults in these systems can lead to financial losses and reduced productivity. By employing Convolutional Neural Networks (CNN) for image data analysis and Recurrent Neural Networks (RNN) for time-series analysis, a comprehensive approach is proposed for fault detection and classification. The proposed model was tested on both simulated and real data, showing high performance in accuracy and reduced processing time. The results indicate that deep learning can be an effective tool for enhancing the reliability of industrial electrical systems and optimizing maintenance processes.

Keywords : fault detection deep learning convolutional neural networks (cnn) recurrent neural networks (rnn) hybrid models (cnn rnn)