Exponent regularization and null space linearity discriminant analysis-based fault diagnosis method

A linear differential analysis and fault diagnosis technology, applied in the direction of instruments, electrical testing/monitoring, control/regulation systems, etc., can solve problems such as blindness, unsupervised, and limited ability to solve singular matrices, and achieve accurate identification and improve accuracy Effect

Inactive Publication Date: 2017-06-30
HUNAN INSTITUTE OF ENGINEERING
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Although nonlinear reduction can be achieved by introducing a kernel function, which can avoid the "small sample" problem to a certain extent, its unsupervised basic properties lead to blindness in the process of dimension reduction.
[0010] Null Space Linear Discriminant Analysis (NSLDA) uses

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
  • Exponent regularization and null space linearity discriminant analysis-based fault diagnosis method
  • Exponent regularization and null space linearity discriminant analysis-based fault diagnosis method
  • Exponent regularization and null space linearity discriminant analysis-based fault diagnosis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Engine AVL simulation model: it can simulate four states of engine normal state, one-cylinder misfire failure, one-two cylinder misfire and one-four cylinder misfire failure. In each state, three speeds of 800r / min, 1200r / min and 2000r / min are designed respectively. In the experiment, the vibration signals of four types of faults in each speed state were extracted, a total of 12 groups of vibration signals, the sampling time was 10 seconds, and the number of sampling points was 57000.

[0064] For the engine, the vibration signal of the cylinder head contains rich information, which can effectively reflect changes in the speed, cylinder pressure and piston impact, so the use of it for engine fault diagnosis and status monitoring has high universality and easy signal acquisition. In this experiment, by studying the changes of the engine vibration signal, extracting the corresponding time-domain features and frequency-domain features, combined with the ERNSLDA algorithm p...

Embodiment 2

[0070] Gearbox fault simulation: The gearbox fault simulation test bench mainly simulates five states of bearing outer ring fault, inner ring fault, rolling element fault, gear tooth surface loss and broken tooth fault, respectively recorded as (f1, f2, f3, f4, f5), where the number of gears at the input end is 55, the number of gears at the output end is 75, and the modulus is 2. The vibration signal is collected by the vibration acceleration sensor. During the signal collection process, the motor speed is set to 1200r / min, and the sampling frequency is 10KHz. 20 groups of vibration signals in each of the 5 states are collected, totaling 100 groups of vibration signals.

[0071] The time domain, frequency domain and time-frequency domain signal features are extracted from the original vibration signal to form a corresponding high-dimensional fault feature set. The ERNSLDA algorithm proposed in this paper is used to classify and identify the fault state of the gearbox, and the ...

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 an exponent regularization and null space linearity discriminant analysis-based fault diagnosis method. Regularization discriminant analysis is combined with null space discriminant analysis, advantages of NSLDA and RLDA in terms of mode identification are integrated, a regularized intra-class sample matrix Sw1 is used for replacing a class sample matrix Sw in null space discriminant analysis, small sample problems can be further solved; in discrimination criteria for discriminant analysis, an exponential function is introduced, the regularized intra-class sample matrix Sw1 and an inter-class sample matrix Sb are respectively subjected to exponential operation, and therefore more characteristic information can be obtained; faults can be effectively and accurately identified, fault diagnosis precision can be effectively improved, and a new train of thought is put forward for small fault diagnosis based on data driving.

Description

technical field [0001] The invention relates to a fault diagnosis method, in particular to a fault diagnosis method based on exponential regularization null space linear discriminant analysis. Background technique [0002] With the complexity and scale of equipment in modern control systems, the abnormal detection and fault diagnosis of related systems have always been the focus of academic circles. Mechanical fault diagnosis is of great significance to ensure the safe operation of equipment. Once a mechanical equipment fails, if it cannot be found and dealt with in time, it will cause huge economic losses and casualties. Therefore, the safety and reliability of equipment and systems have become one of the focuses of people's attention. If the faults can be detected in a controllable industrial operation process in time to avoid the occurrence of abnormal events, it is necessary to perform reasonable fault diagnosis on complex systems. Problems to be solved. [0003] Fault...

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
IPC IPC(8): G05B23/02
CPCG05B23/0243G05B2219/24065
Inventor 吴迪
Owner HUNAN INSTITUTE OF ENGINEERING
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap