A fault diagnosis method for industrial process based on Bayesian theory
A Bayesian theory and industrial process technology, applied in the direction of comprehensive factory control, electrical program control, comprehensive factory control, etc., can solve problems such as information loss, wrong diagnosis results, and influence on the credibility of diagnosis results, so as to reduce dependence, The effect of high accuracy
Active Publication Date: 2019-05-28
WENZHOU UNIVERSITY
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing data-driven methods have the disadvantages of relying on industrial process knowledge to varying degrees, the reliability of fault diagnosis results is not high, and it is easy to get wrong diagnosis results.
It is particularly noteworthy that there are few reports on the fault diagnosis of industrial processes based on discriminant analysis, especially the fault diagnosis based on Bayesian Lasso.
In 2015, Kuang T H, Yan Z, Yao Y. [Kuang T H, Yan Z, Yao Y. Multivariate fault isolation via variable selection indiscriminant analysis. Journal of Process Control, 2015, 35:30-40.] Apply variable selection to For industrial process fault diagnosis, a discriminant analysis method based on variable selection is proposed, which effectively solves the deficiency of previous methods relying on process knowledge
However, this approach is too arbitrary, which can easily cause loss of information and affect the credibility of diagnostic results.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0023] The present invention will be described in more detail below with reference to the accompanying drawings of the present invention. This invention may also be embodied in many different forms and, therefore, it should not be considered limited to the examples set forth in the specification; The specific implementation process of the present invention.
[0024] The industrial process fault diagnosis method based on Bayesian theory provided by the present invention mainly includes the following five functional modules: ① acquisition module of important variable data such as temperature, pressure, and flow in the industrial process; ② fault diagnosis and variable selection conversion fault diagnosis Model building module; ③Model solution module for calculating the probability density function of regression coefficient β; ④Control limit ε solution module for β; ⑤Fault diagnosis result analysis and output module, please refer to the attached figure 1 . For the specific flow...
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
Login to View More Abstract
The invention discloses a method for diagnosing industrial process faults based on Bayesian theory: firstly collect the data of important variables in the industrial process, then standardize the data, use the standardized data to construct a model for variable selection, and use Gibbs The sampling method solves the regression model, obtains the regression coefficient corresponding to the variable, uses the Monte Carlo method to calculate the failure probability of each variable, and finally finds out those variables with a probability exceeding 95% by comparison. Compared with the traditional industrial process fault diagnosis method, this method significantly improves the reliability of fault diagnosis results, reduces the probability of fault misdiagnosis, is conducive to the realization of online monitoring of complex industrial processes, and provides an effective basis for industrial process recovery.
Description
technical field [0001] The invention relates to the technical field of industrial process monitoring and diagnosis, in particular to a method for diagnosing industrial process faults based on Bayesian theory. Background technique [0002] In recent years, due to the continuous progress and development of science and technology, the equipment of industrial processes has become more and more advanced, and the production process has become more and more complicated. Although, the development of computers and the application of automation technology in modern industrial processes have greatly improved productivity, reduced production costs, and reduced energy consumption, bringing huge economic and social benefits to enterprises and the country. However, due to the characteristics of industrial processes such as high complexity, strong correlation, and susceptibility to interference, industrial processes have become difficult to manage. If some small faults occur in the equipme...
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
Login to View More Patent Type & AuthorityPatents(China)
IPC IPC(8): G05B19/418G05B23/02
CPCY02P90/02
Inventor闫正兵张申波吴平张正江张佳跃
OwnerWENZHOU UNIVERSITY