Frequency-Domain Feature Reconstruction Network with Memory Units for Anomaly Detection of Fused Magnesium Furnaces

Anomaly detection of smelting process benefits the operation safety of fused magnesium furnaces (FMFs). While generative models that fit well complex data distributions in the latent space offer an effective way to anomaly detection, conventional generative models have difficulties in adapting to visual interferences such as dynamic water mist, dust, and on-site lighting changes. To this end, this paper establishes a new frequency-domain feature reconstruction network with memory units for anomaly detection of fused magnesium furnaces. This network utilizes high-frequency filtering to extract features in the frequency domain to suppress the adverse effects of brightness variations caused by fluctuations in the furnace flame. Using the extracted frequency domain features, wavelet sampling is integrated with memory units for reconstruction to eliminate interferences in the frequency domain while preserving anomalous features, thereby alleviating overgeneralization. Moreover, a new adaptive threshold calculation method is proposed for the anomaly detection of FMFs. Finally, the effectiveness of the proposed method is demonstrated by using the image collected from a real FMF.