Fault detection method based on dimensional variable type independent component analysis model

Abstract

The invention discloses a fault detection method based on a dimensional variable type independent component analysis model. The method comprises the following steps: in an offline modeling phase, according to differences of values of various column vector elements of a separation matrix in a traditional independent component analysis (ICA) model, various variables are firstly and correspondingly endowed with different weights to reflect differences of dimensions; afterwards, because each column vector in the separation matrix represent a difference of the corresponding measurement variable in a projection direction, the dimensions have a plurality of variable forms, and a plurality of ICA fault detection models can be established correspondingly; and, when online monitoring in performed, the multiple ICA models are called to calculated corresponding monitoring statistics, and a final probability type monitoring index is obtained by utilizing Bayesian reasoning in order to provide convenience for fault decision-making. Compared with a traditional method, the method is advantageous in that modeling considers uncoordinated importance of the measurement variables, and fault detection is implemented by utilizing the multiple modes at the same time. According to the method, description for a normal data characteristic is comprehensive, and an excellent fault detection effect is obtained through utilization.

Description

technical field [0001] The invention relates to an industrial process fault detection method, in particular to a fault detection method based on a dimension variable independent element analysis model. Background technique [0002] With the wide application of computer technology in industrial systems, the modern industrial production process is moving towards the "big data era". Massive production process data resources provide a solid data foundation for data-driven monitoring, soft measurement, control, optimization, etc. Among them, data-driven fault detection methods have been developed unprecedentedly in recent years, and various fault detection models emerge in endlessly. The multivariate statistical process monitoring method represented by Principal Component Analysis (PCA) and Independent Component Analysis (ICA) algorithms has attracted extensive attention from academia and industry, resulting in a variety of methods suitable for different working conditions. impl...

AI Technical Summary

Problems solved by technology

Therefore, under the condition of only normal data but no fault data, it is impossible to reflect the dimensional differences in a targeted manner. At this time, standardized processing seems to be a "last resort" preprocessing solution.

Images