In this article, a new decomposition theory, feature mode decomposition (FMD), is tailored for the feature extraction of machinery fault. The proposed FMD is essentially for the purpose of decomposing the different modes by the designed adaptive finite-impulse response (FIR) filters. Benefitting from the superiority of correlated Kurtosis, FMD takes the impulsiveness and periodicity of fault signal into consideration simultaneously. First, a designed FIR filter bank by Hanning window initialization is used to provide a direction for the decomposition. The period estimation and updating process are then used to lock the fault information. Finally, the redundant and mixing modes are removed in the process of mode selection. The superiority of the FMD is demonstrated to adaptively and accurately decompose the fault mode as well as robust to other interferences and noise using simulated and experimental data collected from bearing single and compound fault. Moreover, it has been demonstrated that FMD has superiority in feature extraction of machinery fault compared with the most popular variational mode decomposition.

A group of kurtosis-guided-grams, such as Kurtogram, Protrugram and SKRgram, is designed to detect the resonance band excited by faults based on the sparsity index. However, a common issue associated with these methods is that they tend to choose the frequency band with individual impulses rather than the desired fault impulses. This may be attributed to the selection of the sparsity index, kurtosis, which is vulnerable to impulsive noise. In this paper, to solve the problem, a sparsity index, called the Gini index, is introduced as an alternative estimator for the selection of the resonance band. It has been found that the sparsity index is still able to provide guidelines for the selection of the fault band without prior information of the fault period. More importantly, the Gini index has unique performance in random-impulse resistance, which renders the improved methods using the index free from the random impulse caused by external knocks on the bearing housing, or electromagnetic interference. By virtue of these advantages, the improved methods using the Gini index not only overcome the shortcomings but are more effective under harsh working conditions, even in the complex structure. Finally, the comparison between the kurtosis-guided-grams and the improved methods using the Gini index is made using the simulated and experimental data. The results verify the effectiveness of the improvement by both the fixed-axis bearing and planetary bearing fault signals.

The data distribution shift is inevitable in practical fault diagnosis due to internal and outside changes of equipment. These obstacles will lead to performance degrade or even failure of diagnostic models. In light of these problems, a novel unsupervised intelligent diagnostic framework named Adversarial Adaptation network based on Classifier Discrepancy (AACD) is introduced for mechanical fault diagnosis where the training and test domains have different data distribution. Specifically, AACD mainly contains two parts, one is the shared feature generator built by the one-dimensional convolutional neural network and the other is double task-specific classifiers. They play an adversarial training game to learn class-separable and domain-invariant features for fault diagnosis. The proposed AACD is evaluated by fifteen transfer diagnosis tasks constructed on the planetary gearbox test-bed and the rolling bearing test-bed. Moreover, six popular algorithms are selected for comparison. The comprehensive results validate the effectiveness and superiority of the proposed approach.