Rotating machinery vibration signals are nonstationary and nonlinear under complicated operating conditions. It is meaningful to extract optimal features from raw signal and provide accurate fault diagnosis results. In order to resolve the nonlinear problem, an enhancement deep feature extraction method based on Gaussian radial basis kernel function and autoencoder (AE) is proposed. Firstly, kernel function is employed to enhance the feature learning capability, and a new AE is designed termed kernel AE (KAE). Subsequently, a deep neural network is constructed with one KAE and multiple AEs to extract inherent features layer by layer. Finally, softmax is adopted as the classifier to accurately identify different bearing faults, and error backpropagation algorithm is used to fine-tune the model parameters. Aircraft engine intershaft bearing vibration data are used to verify the method. The results confirm that the proposed method has a better feature extraction capability, requires fewer iterations, and has a higher accuracy than standard methods using a stacked AE.
:With the rapid development of scientific technological progress and industrial scale, modern industrial monitoring field has entered the era of big data. It is an important task to automatically extract fault features from large scale raw vibration data and make fault diagnosis. In order to further improve the ability of the deep auto-encoder network to deal with the nonlinear problem, a deep neural network method based on kernel function and denoising auto-encoder (DAE) is proposed. The traditional denoising auto-encoder is improved by radial basis kernel function, and the kernel denoising auto-encoder (KDAE) is proposed. A deep neural network consisting of one KDAE layer and multiple AE layers is constructed to extract the fault features, and the softmax classification layer is added as classifier layer. The error back propagation algorithm is used to fine-tune the network parameters, and chaos firefly algorithm is used to optimize the undetermined parameters of the kernel parameters, then the fault diagnosis model is obtained. In response to the problem of poor generalization of traditional auto-encoder, L2 penalty items are added to the target function. It is verified that the proposed method is more accurate than the traditional denoising auto-encoder network through the typical failure test data of aero-engine intermediate bearing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.