Prior knowledge fault diagnosis method based on Tennessee Eastman process

Abstract

The invention relates to a prior knowledge fault diagnosis method based on the Tennessee Eastman process. The method comprises the steps that the offline historical data of the Tennessee Eastman process are acquired; an adjustment parameter matrix that U belongs to R<nxn> and k of a KNN algorithm are selected; an adjacent matrix W is constructed on an existing weighted undirected graph, a matrix D is accordingly calculated, a Laplacian matrix L=D-W is defined, and the Laplace regular term L<~> is calculated according to a Laplace regularization algorithm; the local regular term (I-A)<T>(I-A) is calculated according to a local regularization algorithm; a tag matrix is calculated according to F<*>=(UD<~>+L<~>+(I-A)<T>(I-A))<-1>UD<~>Y; and the unmarked samples are marked according to f=arg maxF<*><ij>, 1<=j<=c, and fault classification information of the industrial process is obtained after normalization. Characteristic information of the marked samples and the unmarked samples is fully mined and utilized to establish a fault diagnosis model and verification is performed by using the Tennessee Eastman process data, and the classifier is improved in the final classification phase so that the classification accuracy can be enhanced, and the classification error rate of the samples and the sample separation degree and other verification standards can be improved.

Description

technical field [0001] The invention relates to a fault detection and diagnosis technology, in particular to a prior knowledge fault diagnosis method based on the Tennessee Eastman process. Background technique [0002] Graph-based semi-supervised classification algorithms are the most widely used class of algorithms in prior knowledge learning. By converting all samples in the data set (including labeled samples and unlabeled samples) into a connected weighted undirected graph that defines nodes representing samples and edges representing weights between nodes. The nodes and the edges of the nodes represent a certain relationship between two samples, which is called similarity. Finally, training is performed on a connected weighted undirected graph. It is pointed out here that this type of algorithm is only effective for samples with certain rules, and can realize the prediction of sample distribution of labeled samples on the entire data set. If the samples in the entir...

AI Technical Summary

Problems solved by technology

In the past knowledge-based models, knowledge often imposed a constraint on the algorithm model when constructing it, such as a Laplacian regular term, and it was often difficult to obtain an effective decision function in past simulations

Images