Autoregressive data generation method based on wavelet packet transform and cascaded stochastic quantization for bearing fault diagnosis under unbalanced samples

TL;DR: This study proposes BPDF-SegNet, a novel segmentation network that addresses small pitting defects on ball screw surfaces by introducing a bidirectional decoupled region calibration module, deep convolution, and channel shift techniques for improved feature extraction and fusion.

TL;DR: A simple, nonrigorous, synthetic view of wavelet theory is presented for both review and tutorial purposes, which includes nonstationary signal analysis, scale versus frequency,Wavelet analysis and synthesis, scalograms, wavelet frames and orthonormal bases, the discrete-time case, and applications of wavelets in signal processing.

TL;DR: A novel method named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN), which can not only achieve 100% classification accuracy on normal signals, but also outperform the state-of-the-art DNN model which is based on frequency features under different working load and noisy environment conditions.

TL;DR: In this article, the authors explore the use of vector quantized variational autoencoder (VQ-VAE) models for large scale image generation and demonstrate that a multi-scale hierarchical organization with powerful priors over the latent codes is able to generate samples with quality that rivals that of state of the art Generative Adversarial Networks on multifaceted datasets such as ImageNet, while not suffering from GAN's known shortcomings such as mode collapse and lack of diversity.

TL;DR: This study proposes an automatic feature learning neural network that utilizes raw vibration signals as inputs, and uses two convolutional neural networks with different kernel sizes to automatically extract different frequency signal characteristics from raw data.