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

Industrial process fault diagnosis method for complex fault

A fault diagnosis and industrial process technology, which is applied in general control systems, instruments, test/monitoring control systems, etc., can solve problems such as large amount of calculation and inability to diagnose industrial process faults

Active Publication Date: 2018-12-21
HUAZHONG UNIV OF SCI & TECH
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above defects or improvement needs of the prior art, the present invention provides an industrial process fault diagnosis method for complex faults, thereby solving the problem that the prior art has a large amount of calculation and cannot accurately diagnose industrial process faults under complex faults technical issues

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
  • Industrial process fault diagnosis method for complex fault
  • Industrial process fault diagnosis method for complex fault
  • Industrial process fault diagnosis method for complex fault

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0143] In embodiment 1, the Monte Carlo (Monte Carlo) numerical simulation example is specifically described as:

[0144]

[0145] where x is the sample under normal working conditions, t 1 , t 2 , t 3 It is three latent variable signals with mean value 0 and standard deviation 1, 0.8 and 0.6 respectively, conforming to Gaussian distribution, noise is white noise with mean value 0 and standard deviation 0.2, noise~N(0, 0.2); total 3000 normal samples to form the training set;

[0146] The fault samples to be detected are expressed in the following general form:

[0147]

[0148] In Embodiment 1, ξ=[0 1 1 0 0 0], f=t / 400 indicates a linearly increasing fault, and a fault occurs from the 200th sample, and there are a total of 1000 fault samples to be tested.

[0149] Using the fault diagnosis method provided in this example, the specific steps for fault diagnosis of Embodiment 1 are as follows:

[0150] (1) For normal sample set matrix X∈R 3000×6 Carry out standardiz...

Embodiment 2

[0163] Embodiment 2 improves the difficulty of diagnosis and expands variables to high-dimensional faults, specifically described as:

[0164]

[0165] where A∈R 20×3 , the sample to be tested The fault is adjusted to a step fault with an amplitude of 2, and three sets of tests are carried out. The first set of fault directions is 2, 5, 7, and 8, the second set of fault directions is based on the first set plus 9, 10, and the third set Group fault direction is to add 12, 13 on the basis of the second group, other parameters are not changed, image 3 (a)(b) is the first set of test results, image 3 (c)(d) is the second set of test results, image 3 (e)(f) is the third group of test results, as can be seen from the figure, the present invention has carried out positioning and tracking to the fault variables well, even when the coefficient matrix A is constantly changing and the fault variables are constantly changing , also has a high accuracy rate, and the system after...

Embodiment 3

[0167] Embodiment 3 is to carry out the test of the 6th kind of fault in TE simulation data set, Figure 4 (a), (b), and (c) are respectively the traditional RBC contribution graph, the traditional RBC plus Bayesian filter, and the diagnosis results of the present invention, Figure 4 (d) is the change graph of each variable. From Figure 4 In (a), it can be seen that due to excessive interaction between variables and fault propagation, almost every variable is diagnosed as a fault, which is a failure diagnosis caused by too much coupling between variables; Figure 4 In (b), it can be seen that the Bayesian filter has filtered many variables, resulting in almost only one or two variables in the result, while the comparison Figure 4 (d) it can be seen that the diagnosis is not meaningful; Figure 4 (c) with Figure 4 (d) Contrast can be found, the present invention has pointed out all variables of failure accurately, and the system after diagnosis returns to normal state, ...

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 industrial process fault diagnosis method for a complex fault. The method comprises the steps of collecting sample data in a normal mode and building a fault monitoring model; solving parameters by using maximum likelihood estimation, thereby obtaining probability density functions of variables i; collecting a to-be-diagnosed sample and calculating a statistical quantity; when it is detected that the fault occurs, calculating deviation factors of the variables, and performing training to obtain conditional probability density functions of the deviation factors, thereby calculating out posterior probabilities; and selecting the variable with the highest posterior probability to perform multi-dimensional reconstruction, thereby finding out the fault variable. According to the method, the calculation amount is small, and the industrial process fault diagnosis can be accurately carried out under the complex fault. The method is remarkable for an industrial process result, and effectively aims at the complex fault problems of small faults, multi-variable simultaneous faults, excessively high variable dimension and the like.

Description

technical field [0001] The invention belongs to the technical field of industrial process fault diagnosis and isolation, and more specifically relates to an industrial process fault diagnosis method for complex faults. Background technique [0002] In industrial processes, rapid detection and identification of abnormal events is crucial to improving system safety and reducing production losses. Therefore, fault detection and diagnosis is a very important topic in the field of process control. Traditional fault detection methods start from the system model and mechanism, but as modern industrial systems become more and more complex and large, the establishment of mechanism models faces great difficulties. At the same time, with the improvement of computer computing power, the operation of large-scale industrial data becomes possible. Therefore, research on data-driven methods has become a hot topic. [0003] The most widely used methods for fault detection in data-driven t...

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): G05B23/02
CPCG05B23/024
Inventor 郑英周威张洪王彦伟
Owner HUAZHONG UNIV OF SCI & TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com