Denoising Diffusion Probabilistic Model Enhanced Tool Condition Monitoring Method Under Imbalanced Conditions

Abstract In recent years, tool condition monitoring (TCM) based on deep learning has been widely concerned and achieved remarkable success. However, these methods usually typically require relatively large training samples to produce significant results, which are both imbalanced and rather troublesome to obtain in the practical application of TCM. To address this issue, a novel TCM method combined with multiscale permutation entropy(MPE), denoising diffusion probabilistic model (DDPM), and a residual network (ResNet) is proposed under conditions of sample imbalance. First, the one-dimensional sensing signal data is converted to a grayscale Recurrence plot (RP) by minimizing the MPE of the signals in each channel. Second, combine and splice these grayscale RPs from different channels in each sample into color RPs. After that, the generated RP images by using DDPM are added to the imbalanced dataset to augment the data so that achieving a balanced state of dataset. Finally, the balanced mixed data set of real and fake samples is input into a ResNet for recognition and monitoring tool condition. TCM experiments are conducted to verify the performance of the proposed method with imbalanced dataset, and the results of experimental investigation demonstrate that the the accuracy of the proposed method improved by 2%~18.8% compared to that of other four sample augmentation methods using ResNet18 when the imbalance rate is 1:200.