Multi-Scale Residual Attention GAN Method for IGBT Switching Transient Data Compression and Reconstruction

Insulated Gate Bipolar Transistors (IGBTs) play a vital role in power electronics, producing large volumes of time-series data critical for fault detection and system health monitoring. The sheer data size challenges efficient storage and transmission, especially in IoT and edge computing scenarios. Conventional compression techniques, like wavelet transforms and PCA, often struggle to retain the complex, non-linear patterns in IGBT signals, leading to reduced reconstruction quality and impaired fault diagnosis. To overcome these issues, we introduce a novel Multi-Scale Residual Attention Generative Adversarial Network (MRA-GAN) tailored for IGBT data compression and reconstruction. The model features a generator with multi-scale convolutions, residual connections, and a spatiotemporal attention mechanism to effectively capture diverse signal characteristics. A discriminator ensures the reconstructed data closely mimics real IGBT signals through adversarial training. By balancing reconstruction accuracy and data realism, MRA-GAN achieves high compression ratios while preserving fault-related features. Evaluations show it outperforms traditional methods, supporting precise fault detection and enabling efficient data handling for real-time industrial monitoring. This approach significantly enhances data processing for IGBT applications, offering a scalable solution for power electronics diagnostics and resource-constrained environments.