A Width Transfer Learning Network and Rolling Bearing Fault Diagnosis Method Based on Width Transfer Learning Network

A technology of transfer learning and rolling bearings, which is applied in the field of bearing fault diagnosis, can solve problems such as large differences in the distribution of source domain data and target domain data, low diagnostic accuracy and model training efficiency, and unbalanced distribution of multi-state data, so as to reduce training costs. time, shorten training time, and improve accuracy

CN110849627BActive Publication Date: 2021-11-16HARBIN UNIV OF SCI & TECH
6 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2021-11-16

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

A width transfer learning network and a rolling bearing fault diagnosis method based on the width transfer learning network belong to the technical field of bearing fault diagnosis. In view of the scarcity of vibration data with marked information of rolling bearings under variable loads, the large difference in the distribution of source domain data and target domain data in the same state, the unbalanced distribution of multi-state data, and the low diagnostic accuracy and model training efficiency, a new method is proposed. Width transfer learning network and an intelligent diagnosis method for rolling bearings based on it. The present invention uses the breadth learning system to extract the characteristics of the source domain data and the target domain data and constructs a sample set, and on this basis, adopts the balanced distribution adaptation method in transfer learning to reduce the difference between the source domain and the target domain. The chicken flock algorithm is introduced to optimize the width transfer learning network parameters, and then the width transfer learning network model is established. The proposed network model is applied to the intelligent diagnosis of rolling bearing faults under variable loads, and the experimental results verify the efficiency and accuracy of the proposed method.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to a rolling bearing fault diagnosis method, which belongs to the technical field of bearing fault diagnosis. Background technique

[0002] Rolling bearings are one of the most important components in rotating machinery, and their health status has a huge impact on the performance, stability and service life of the entire mechanical equipment [1] . In the actual working state of the rolling bearing, the load often changes, and the change of the load will directly affect the change of the vibration characteristics of the rolling bearing [2] . Therefore, under variable load conditions, it is of great significance to accurately identify the running state of the rolling bearing to ensure the normal operation of the entire mechanical equipment.

[0003] In recent years, with the continuous rise of machine learning research, intelligent fault diagnosis algorithms have gained a place in the field of mechanical fault diagnosis. Litera...

Examples

Embodiment Construction

[0059] combined with Figures 1 to 10 A width transfer learning network and a rolling bearing fault diagnosis method based on the width transfer learning network of the present invention are described in detail as follows:

[0060] 1 Basic theory

[0061] 1.1 Breadth Learning System (BLS)

[0062] Breadth Learning System (BLS) perfectly inherits random vector functional-link neural network (random vector functional-link neural network, RVFLNN) [26] The advantages of extremely strong nonlinear mapping capabilities, and can process data quickly and efficiently, saving time and improving efficiency. Many neural networks are plagued by time-consuming training, the main reason is that there are a large number of parameters between their layers, resulting in long training cycles and low efficiency, and when the established model does not achieve the desired purpose, it will consume a lot of time again. Retrain. The design of wide learning network provides an effective solution t...