ICA-PCA multi-working condition fault diagnosis method based on local neighborhood standardization and Bayesian inference

Abstract

The invention discloses an ICA-PCA multi-working condition fault diagnosis method based on local neighborhood standardization and Bayesian inference. The method firstly carries out independent sampling of each normal working condition during an industrial course to obtain a training dataset, carries out the local neighborhood standardization of the training dataset to obtain a dataset which follows single distribution, and then uses an ICA-PCA method to respectively analyze and process Gaussian features and non-Gaussian features of the dataset so as to obtain an overall model. At an online monitoring stage, independent and repeated sampling is carried out to industrial course data, a plurality of statistical quantities are acquired by applying the model to carry out analysis and processing after the local neighborhood standardization processing, then the multiple statistical quantities are combined into one statistical quantity by the Bayesian inference, and a fault diagnosis result is acquired by comparing control limits. In comparison with traditional fault diagnosis methods, the ICA-PCA multi-working condition fault diagnosis method based on the local neighborhood standardization and the Bayesian inference disclosed by the invention can simplify processing courses, improve diagnosis effects and improve course monitoring performance, and can also make workers' monitoring and observation convenient, make for avoiding safety hidden dangers and guarantee normal running of the industrial course.

Description

technical field [0001] The invention belongs to the field of industrial process monitoring, in particular to an ICA-PCA multi-working condition fault diagnosis method based on local neighborhood standardization and Bayesian inference. Background technique [0002] Modern complex industrial processes often contain different working conditions with nonlinear, non-Gaussian, dynamic and other characteristics, and the data under multiple working conditions obey different distributions. However, most multivariate statistical process monitoring methods such as Principal Component Analysis (PCA) and Partial Least Squares (PLS) assume that the data obeys a single Gaussian distribution, so the monitoring effect of these methods in the process of multi-working conditions has great limitations. [0003] In recent years, in order to effectively solve the problem of online monitoring of multi-working-condition processes, some scholars have proposed multi-model monitoring strategies. Metho...

AI Technical Summary

Problems solved by technology

However, in the offline modeling stage, it is difficult to obtain the prior knowledge of how to classify historical data into corresponding sub-models, and it is not easy to determine the model to which the new data belongs in the online monitoring stage. Different sub-models have their own monitoring graphs. It is convenient for operators to observe and judge

Images