Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis

Subband averaging kurtogram with dual-tree complex wavelet packet transform for rotating machinery fault diagnosis

Imbalanced fault diagnosis of rolling bearing using improved MsR-GAN and feature enhancement-driven CapsNet

Early fault diagnosis of bearing based on frequency band extraction and improved tunable Q-factor wavelet transform

Effective fault diagnosis of rotating machinery plays a pretty important role in the enhanced reliability and improved safety of industrial informatics applications. Although traditional intelligent fault diagnosis techniques, such as support vector machine, extreme learning machine, and convolutional neural network, might achieve satisfactory accuracy, a very high price is caused by marking all samples manually. In this article, a novel fault diagnosis method of the rotating machinery is proposed by integrating semisupervised generative adversarial nets with wavelet transform (WT-SSGANs). The proposed WT-SSGANs’ method involves two parts. In the first part, WT is adopted to transform 1-D raw vibration signals into 2-D time–frequency images. In the second part, the 2-D time–frequency images are inputted into the built SSGANs’ model to realize fault diagnosis with little labeled samples. The advantage of the built model is that the unlabeled samples might be made full use of through an adversarial learning mechanism. Finally, two case studies are implemented to verify the proposed method. The results indicate that it can achieve higher accuracy and use less labeled samples than the other existing methods in the literature. In addition, its performance in stability is pretty good as well. Competitive and promising results are still achieved when working conditions are changed.

Intelligent Fault Diagnosis via Semisupervised Generative Adversarial Nets and Wavelet Transform

Fault diagnosis method based on integration of RSSD and wavelet transform to rolling bearing

The traditional reliability evaluation method based on large sample statistics is inefficient for a single or a small batch computer numerical control turning cutting tool due to the inadequate des...

Operation reliability evaluation of cutting tools based on singular value decomposition transform and support vector space

The invention discloses a cutting-tool operation reliability evaluation method based on SVD transformation and support vector space. The method is characterized in that the method includes: sample data acquisition and significant-feature-quantity extraction, wherein vibration signal data are extracted; SVD dimension reduction, wherein signal reconstruction is carried out on high-dimensional feature quantity indexes, valid components are extracted, and a data dimension number is reduced; support vector space hypersphere construction, wherein the sample data are mapped into the high-dimensionalhypersphere space; and relative-distance index calculation and reliability index definition, wherein a relative distance of a test sample point and a support vector data space hypersphere is calculated, a relative distance index is mapped to [0, 1] through an introduced membership function, and thus an operation reliability index is obtained. The method has the advantage of aiming to solve the cutting-tool reliability evaluation problem under a condition of single equipment or small-batch samples.

Chen Fafa

Papers

Fault diagnosis method based on integration of RSSD and wavelet transform to rolling bearing

Operation reliability evaluation of cutting tools based on singular value decomposition transform and support vector space

Cutting-tool operation reliability evaluation method based on SVD transformation and support vector space