Fault diagnosis of complex industrial equipment based on chunked statistical global-local feature fusion

Abstract

To achieve sustainable operation of large-scale industrial processes, timely and accurate monitoring and handling of abnormal situations are essential. However, fault monitoring of large equipment requires the collection of abundant data, which includes many complex related variables, resulting in excessive redundant data generated during the fault monitoring process. Moreover, the existing principal component analysis (PCA) method can only retain the global characteristic of variance information, and cannot obtain the local characteristic that can characterize the topological relationship between the data points, which affects its monitoring reliability and intelligence level. In response to these issues, a fault diagnosis model for complex industrial processes based on chunked statistical global-local feature fusion (CSGLFF) is proposed in this paper. First, considering the correlation characteristics between industrial process variables, a correlation variable chunking method mutual information (MI)-based is designed to merge the variables with small correlation to obtain the optimal chunking of variables. Second, principal component analysis (PCA) and locally maintained projection (LPP) are combined to construct a global-local feature fusion (GLFF) model that can extract global and local features simultaneously. The chunked data are imported into the GLFF for the extraction of its features respectively, and the corresponding CSGLFF is established. In addition, Bayesian inference is used to fuse the statistics of each sub-chunk to establish an overall fault monitoring statistical indicators, and the reason for failure is found through the variable contribution graph (VCG). Finally, two cases of Tennessee Eastman process (TEP) and laboratory emulsion pump were used to conduct experimental research on the performance of CSGLFF. The results show that compared with the chunked statistical PCA (CSPCA), chunked statistical LPP (CSLPP), and GLFF algorithms, the proposed model has good monitoring effect in processing data with large variables, reducing the generation of redundant data, improving the accuracy of industrial monitoring, and accurately identifying the relevant variables of fault occurrence. This provides a theoretical basis for determining the fault location and points out the direction for maintenance by staff.