An intelligent fault diagnosis method based on domain adaptation for rolling bearings under variable load conditions

Abstract

To identify rolling bearing faults under variable load conditions, a method named DISA-KNN is proposed in this paper, which is based on the strategy of feature extraction-domain adaptation-classification. To be specific, the time-domain and frequency-domain indicators are used for feature extraction. Discriminative and domain invariant subspace alignment (DISA) is used to minimize the data distributions’ discrepancies between the training data (source domain) and testing data (target domain). K-nearest neighbor (KNN) is applied to identify rolling bearing faults. DISA-KNN’s validation is proved by the experimental signal collected under different load conditions. The identification accuracies obtained by the DISA-KNN method are more than 90% on four datasets, including one dataset with 99.5% accuracy. The strength of the proposed method is further highlighted by comparisons with the other 8 methods. These results reveal that the proposed method is promising for the rolling bearing fault diagnosis in real rotating machinery.

Robust fault diagnosis of quayside container crane gearbox based on 2D image representation in frequency domain and CNN

“…Zhang et al 11 used domain adaption technology to solve the problem that training data and testing data come from different load conditions. The seven methods of 2D characterization of vibration signals in Table 9 can achieve a recognition accuracy of more than 80%, including 94.55% obtained by the proposed method, which does not use domain adaptation or other transfer learning techniques.…”

“…Feature selection is a feature dimensionality reduction method, which removes redundant information by selecting feature subsets, to accurately distinguish multiple categories of health and fault states. 8 There are many shallow machine learning models for classification, such as support vector machine, 9 extreme learning machine, 10 K-nearest neighbor, 11 etc. On the one hand, manual feature extraction depends on prior knowledge, and its universality is poor.…”

Non intrusive load identification method based on deep learning

“…The active power feature can be taken as an easy to obtain steady state feature to directly reflect the energy consumption of the load. In the existing intelligent power control structure, the load identification module can directly communicate with the metering core to read the real-time active power value [8]. Similarly, reactive power can be obtained directly from the metering core in real time.…”

The Design of Dynamic Channelization and Signal Control System

“…Alhajyaseen [4] believes that the dynamic lane group can be better adapted to the changing traffic demand at the entrance of the intersection compared with the fixed lane group. The essence of dynamic lane and dynamic approach lane [5] is to switch lane functions of two or more lanes in a specific lane, without increasing the total number of approach lanes. The role of dynamic direction lane is equivalent to the capacity stored up, which is called according to the actual traffic demand at the approaches of the intersection.…”