Fault Detection and Health Assessment of Equipment Based on Fuzzy DPCA Spatial Eigenvalue Similarity

Abstract

To improve the fault recognition rate of the dynamic principal component spatial data drive method, a fault diagnosis and equipment health status assessment method based on similarity fuzzy dynamics principal component analysis was proposed. First, the data are fuzzified according to the error function, and an augmented matrix is constructed. The eigenvalues are decomposed to obtain a score matrix and residual matrix of the fuzzy principal component. Further, the similarity between fault data and normal data is calculated. Meanwhile, a health assessment of the equipment is realized. The contribution rate of the observed variables is calculated. Finally, general Tennessee Eastman data and health assessment of a hydraulic press are used to validate the algorithm. The results show that the SFDPCA has a 100 % fault recognition rate for some faults, and the recognition rate for other faults is also higher than that of DPCA-Diss, DPCA-SPE, and PCA-SPE. The SDDPCA accurately identifies abnormal phenomena. It can determine the health level of prefilling and effectively make up for the shortcomings of PCA − T 2 , PCA-SPE, DPCA-Diss, and other methods and also can be applied to data-driven fault diagnosis to improve the fault recognition rate.

Health Assessment Method of Equipment in Distribution Court Based on Big Data Analysis in the Framework of Distribution Network of Things

“…Since the number of courts has a great impact on the evaluation effect, the proposed method is compared with studies by He et al (2021), Zhou et al (2021), andGao et al (2021) under different numbers of courts; and the evaluation accuracy is shown in Figure 6.…”

“…In addition, He et al (2021) proposed an equipment health status assessment method based on similarity fuzzy PCA, which achieved the equipment health assessment through similarity comparison but lacked a consideration of equipment environmental impact factors. When the number of distribution courts is 90, the evaluation accuracy is only 78%.…”

“…Currently, the domestic research on the evaluation of the distribution network equipment status still needs to be furthered, although many of the research results have been achieved. For example, He et al (2021) propose a method of equipment health assessment based on the similarity fuzzy dynamic principal component analysis (PCA), which uses error function to fuzzify equipment data and uses the PCA method to analyze the score and residual matrix to complete equipment health assessment by comparing the similarity between fault and normal data; but the environmental impact factors of the equipment are not considered. Cheng et al (2022) designed a transmission line operation status evaluation method based on the improved combined weighted evaluation model and determined the weight of the evaluation index through subjective and objective integration; thus, they realized the evaluation of the actual line health status.…”