Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Fault Diagnosis Method Based on Adaptive Manifold Embedding and Dynamic Distribution Alignment

An adaptive flow and fault diagnosis technology, which is applied in the fields of mechanical fault diagnosis and machine learning, can solve problems such as data feature distortion and unsatisfactory model diagnosis effects, and achieve fast execution speed, strong interpretability, and avoid feature distortion.

Active Publication Date: 2021-12-07
SUZHOU UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Furthermore, when adaptive distribution alignment is performed in the original Euclidean space, data feature distortions inevitably occur, leading to suboptimal diagnostic performance of the model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Fault Diagnosis Method Based on Adaptive Manifold Embedding and Dynamic Distribution Alignment
  • A Fault Diagnosis Method Based on Adaptive Manifold Embedding and Dynamic Distribution Alignment
  • A Fault Diagnosis Method Based on Adaptive Manifold Embedding and Dynamic Distribution Alignment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, so that those skilled in the art can better understand the present invention and implement it, but the examples given are not intended to limit the present invention.

[0082] The present invention is described in detail in conjunction with actual experimental data:

[0083] The experimental data adopts the bearing data set of Case Western Reserve University (CWRU). The data acquisition system is shown in Figure 1. The rolling bearing test bench includes a 2-horsepower motor (1hp=746W), a torque sensor, a dynamometer and Electronic controls. Introduce faults in test bearing rollers, inner rings and outer rings by electric discharge machining (EDM), and set different fault sizes. Vibration data is collected using accelerometers.

[0084] In this example, we select the bearing vibration signal with a sampling frequency of 12KHz as the original da...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a fault diagnosis method based on adaptive manifold embedding and dynamic distribution alignment. The method automatically calculates the optimal subspace dimension, calculates the geodesic flow kernel and the transformed manifold feature representation, It can effectively avoid the characteristic distortion of the data in the original Euclidean space. Introduce the similarity measure A‑distance to define an adaptive factor, dynamically adjust the relative weight of the conditional distribution and edge distribution of the sample data, effectively narrow the distribution difference between the source domain and the target domain samples, and greatly improve the accuracy of rolling bearing faults under variable working conditions. The accuracy and validity of the diagnosis, the method has strong interpretability, lower requirements on computer hardware resources, faster execution speed, and excellent diagnostic accuracy, algorithm convergence and parameter robustness. This method is especially suitable for multi-scenario and multi-fault bearing fault diagnosis under variable working conditions, and can be widely used in fault diagnosis tasks under variable working conditions of complex systems such as machinery, electric power, chemical industry, and aviation.

Description

technical field [0001] The invention relates to the technical fields of mechanical fault diagnosis and machine learning, in particular to a fault diagnosis method based on adaptive manifold embedding and dynamic distribution alignment. Background technique [0002] Rotating machinery is ubiquitous in modern industrial production. As a key component in industrial production equipment, rolling bearings are widely used in various important fields such as machinery, electric power, chemical industry, aviation, etc. At the same time, rolling bearings often work under high temperature, high speed, heavy load In such harsh environments, failures such as wear, cracks, and fractures are prone to occur. Once the bearing fails, it will bring huge economic losses, and cause catastrophic accidents such as casualties. Therefore, it is necessary to strengthen the condition monitoring capabilities of mechanical equipment and improve It is of positive and great significance to qualitatively ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G01M13/045G06K9/62G06N20/10
CPCG01M13/045G06N20/10G06F18/2411G06F18/24147G06F18/22
Inventor 雷飘沈长青谢靖张爱文江星星王俊石娟娟黄伟国朱忠奎
Owner SUZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products