This article develops new deep learning methods, namely, deep residual shrinkage networks, to improve the feature learning ability from highly noised vibration signals and achieve a high fault diagnosing accuracy. Soft thresholding is inserted as nonlinear transformation layers into the deep architectures to eliminate unimportant features. Moreover, considering that it is generally challenging to set proper values for the thresholds, the developed deep residual shrinkage networks integrate a few specialized neural networks as trainable modules to automatically determine the thresholds, so that professional expertise on signal processing is not required. The efficacy of the developed methods is validated through experiments with various types of noise.

Vibration signals under the same health state often have large differences due to changes in operating conditions. Likewise, the differences among vibration signals under different health states can be small under some operating conditions. Traditional deep learning methods apply fixed nonlinear transformations to all the input signals, which has a negative impact on the discriminative feature learning ability, i.e., projecting the intra-class signals into the same region and the inter-class signals into distant regions. Aiming at this issue, this paper develops a new activation function, i.e., adaptively parametric rectifier linear units, and inserts the activation function into deep residual networks to improve the feature learning ability, so that each input signal is trained to have its own set of nonlinear transformations. To be specific, a sub-network is inserted as an embedded module to learn slopes to be used in the nonlinear transformation. The slopes are dependent on the input signal, and thereby the developed method has more flexible nonlinear transformations than the traditional deep learning methods. Finally, the improved performance of the developed method in learning discriminative features has been validated through fault diagnosis applications.

In general, deep learning-based fault diagnosis methods need a large number of training samples, which are often not available in real applications. Aiming at this problem, this article develops a new data augmentation method, i.e., randomized wavelet expansion (RWE), to generate a set of synthesis samples that share similar characteristics with the original sample. The first key point is that the amplitudes of wavelet coefficients at a randomly selected frequency band are enlarged through random expansion. Another key point is that the synthesis samples are processed to have the same mean values and standard deviations as their corresponding original sample. Afterward, the synthesis samples are used as the training dataset to train a deep convolutional neural network (CNN) for implementing the few-shot fault diagnosis of aviation hydraulic pumps. Finally, the performance has been validated through a series of experiments.

Gas-path anomalies account for more than 90% of all civil aero-engine anomalies. It is essential to develop accurate gas-path anomaly detection methods. Therefore, a weakly supervised gas-path anomaly detection method for civil aero-engines based on mapping relationship mining of gas-path parameters and improved density peak clustering is proposed. First, the encoder-decoder, composed of an attention mechanism and a long short-term memory neural network, is used to construct the mapping relationship mining model among gas-path parameters. The predicted values of gas-path parameters under the restriction of mapping relationships are obtained. The deviation degree from the original values to the predicted values is regarded as the feature. To force the extracted features to better reflect the anomalies and make full use of weakly supervised labels, a weakly supervised cross-entropy loss function under extreme class imbalance is deployed. This loss function can be combined with a simple classifier to significantly improve the feature extraction results, in which anomaly samples are more different from normal samples and do not reduce the mining precision. Finally, an anomaly detection method is deployed based on improved density peak clustering and a weakly supervised clustering parameter adjustment strategy. In the improved density peak clustering method, the local density is enhanced by K-nearest neighbors, and the clustering effect is improved by a new outlier threshold determination method and a new outlier treatment method. Through these settings, the accuracy of dividing outliers and clustering can be improved, and the influence of outliers on the clustering process reduced. By introducing weakly supervised label information and automatically iterating according to clustering and anomaly detection results to update the hyperparameter settings, a weakly supervised anomaly detection method without complex parameter adjustment processes can be implemented. The experimental results demonstrate the superiority of the proposed method.