A novel asymmetrical autoencoder with a sparsifying discrete cosine Stockwell transform layer for gearbox sensor data compression
This work addresses a domain-specific challenge in industrial gearbox monitoring by enabling more efficient data transmission for fault diagnosis, though it appears incremental as it builds on existing autoencoder methods.
The authors tackled the problem of compressing gearbox sensor data for wireless transmission in fault diagnosis by proposing an asymmetrical autoencoder with a sparsifying discrete cosine Stockwell transform layer, which improved average quality scores by 2.00% to 32.35% compared to other autoencoder-based methods on benchmark datasets.
The lack of an efficient compression model remains a challenge for the wireless transmission of gearbox data in non-contact gear fault diagnosis problems. In this paper, we present a signal-adaptive asymmetrical autoencoder with a transform domain layer to compress sensor signals. First, a new discrete cosine Stockwell transform (DCST) layer is introduced to replace linear layers in a multi-layer autoencoder. A trainable filter is implemented in the DCST domain by utilizing the multiplication property of the convolution. A trainable hard-thresholding layer is applied to reduce redundant data in the DCST layer to make the feature map sparse. In comparison to the linear layer, the DCST layer reduces the number of trainable parameters and improves the accuracy of data reconstruction. Second, training the autoencoder with a sparsifying DCST layer only requires a small number of datasets. The proposed method is superior to other autoencoder-based methods on the University of Connecticut (UoC) and Southeast University (SEU) gearbox datasets, as the average quality score is improved by 2.00% at the lowest and 32.35% at the highest with a limited number of training samples