Fault Detection Method for Power Conversion Circuits Using Thermal Image and Convolutional Autoencoder

TL;DR

This paper introduces a fault detection approach for power conversion circuits using thermal imaging and a convolutional autoencoder, achieving high accuracy in identifying faults through image reconstruction analysis.

Contribution

It presents a novel fault detection method leveraging thermal images and autoencoders, with comprehensive evaluation of hyperparameters affecting detection performance.

Findings

Autoencoder detects faults with 100% accuracy under tested conditions.

Thermal imaging combined with autoencoder effectively identifies anomalies.

Hyperparameter tuning influences detection accuracy significantly.

Abstract

A fault detection method for power conversion circuits using thermal images and a convolutional autoencoder is presented. The autoencoder is trained on thermal images captured from a commercial power module at randomly varied load currents and augmented image2 generated through image processing techniques such as resizing, rotation, perspective transformation, and bright and contrast adjustment. Since the autoencoder is trained to output images identical to input only for normal samples, it reconstructs images similar to normal ones even when the input images containing faults. A small heater is attached to the circuit board to simulate a fault on a power module, and then thermal images were captured from different angles and positions, as well as various load currents to test the trained autoencoder model. The areas under the curve (AUC) were obtained to evaluate the proposed method. The results show the autoencoder model can detect anomalies with 100% accuracy under given conditions. The influence of hyperparameters such as the number of convolutional layers and image augmentation conditions on anomaly detection accuracy was also investigated.