Improved type principal component analysis model-based fault detection method

A technology of fault detection and principal component analysis, which is applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as missing distance correlation feature mining, and achieve good fault detection results

Inactive Publication Date: 2017-07-11
NINGBO UNIV
View PDF6 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

From this point of view, the traditional PCA algorithm to mine the angular correlation of the training data alone is a one-sided feature extraction method, which lacks the mining of the distance correlation feature.

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
  • Improved type principal component analysis model-based fault detection method
  • Improved type principal component analysis model-based fault detection method
  • Improved type principal component analysis model-based fault detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The method of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0028] Such as figure 1 As shown, the method of the present invention discloses a fault detection method based on the improved principal component analysis model, and the specific implementation steps are as follows:

[0029] Step 1: Collect data samples under the normal operating state of the production process to form a training data set X∈R n×m , and standardize each variable to get a new data matrix with mean 0 and standard deviation 1 Among them, n is the number of training samples, m is the number of process measurement variables, R is the set of real numbers, and R n×m Represents an n×m-dimensional real number matrix, is the standardized data of the i-th measurement variable, i=1, 2, . . . , m is the subscript of the i-th measurement variable.

[0030] Step 2: Follow the formula Calculate the angular correlation matrix S of the training d...

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 improved type principal component analysis model-based fault detection method which is aimed at improving effects exerted by a conventional PCA algorithm on fault detection via further discovery of characteristics of distance correlation between training data. The method comprises the following steps: an angle correlation matrix and a distance correlation matrix of the training data are calculated, a new correlation matrix is obtained after the angle correlation matrix and the distance correlation matrix are added up, and corresponding characteristic values and vectors are calculated. An improved PCA model is built via use of the characteristic vectors, and the PCA model is applied to on-line fault detection. Compared with a conventional method, the fault detection method disclosed in the invention is advantageous in that angle correlation and distance correlation of the training data are taken into account at an off line modeling phase, data correlation characteristics are fully discovered, the improved type PCA model built via the fault detection method can be used for comprehensively describing potential characteristics of normal data, and good fault detection effects should be exerted.

Description

technical field [0001] The invention relates to an industrial fault detection method, in particular to a fault detection method based on an improved principal component analysis model. Background technique [0002] In the entire production automation system, it is very important to monitor the running status of the production process in real time, because it is the simplest and most direct technical means to ensure production safety and maintain product quality stability. With the continuous expansion of the scale of modern industrial processes, advanced instrumentation and computer technology have been widely used. On the one hand, the mechanism model of the production process is becoming more and more difficult to obtain; on the other hand, the production process can collect and store massive data information. It is against this background that traditional fault detection methods based on mechanism models have encountered bottlenecks in their development, while data-drive...

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 Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/22G06F18/2155
Inventor 史旭华蓝艇童楚东
Owner NINGBO UNIV
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