Application of multi-kernel relevance vector machine and data pre-processing by complementary ensemble empirical mode decomposition and mutual dimensionless in fault diagnosis

Abstract

Signals of a faulty building electrical system contain a large amount of information about the electrical systems operating status. However, it is difficult to extract the fault features completely because of their characteristics of non-linearity and non-stationarity which brings a problem of a relatively low fault identification rate of the current fault diagnosis methods based on pattern recognition. Aiming at improving the accuracy of fault diagnosis further, this paper proposes a fault diagnosis method of a building electrical system based on the complementary ensemble empirical mode decomposition and mutual dimensionless index extraction (CEEMD-MDI) combined with the multi-kernel relevance vector machine (MK-RVM). First, the resistance signals of a faulty building electrical system are decomposed into a series of intrinsic mode functions (IMFs) by using an adaptive decomposition ability of the CEEMD. Second, the IMFs are used to extract the mutual dimensionless index (MDI) and to form a feature vector with the resistance signal. Finally, the processed feature vector is input into the MK-RVM for modeling, and the fault diagnosis result of the building electrical system is provided in the form of a probability output. The experimental results show that the fault diagnosis accuracy rate of the proposed method based on CEEMD-MDI and MK-RVM can reach 97.22%, which has better fault diagnosis performance compared with other methods.

A building electrical system fault diagnosis method based on random forest optimized by improved sparrow search algorithm

“…method improves by 1.39% and 6.94% compared to [37,38], respectively. Therefore, compared with the new research results of the building electrical system fault diagnosis field, the proposed method can achieve higher classification accuracy and better classification effect.…”

“…To verify that the proposed building electrical system fault diagnosis method has a strong fault diagnosis ability compared to new research results, the proposed method is compared to the [37,38]. Xiong et al [37,38] both employ the same dataset as this paper. Moreover, compared to the [37,38], the dataset in this paper is collected with two new fault types, S19 and S22.…”

“…Xiong et al [37,38] both employ the same dataset as this paper. Moreover, compared to the [37,38], the dataset in this paper is collected with two new fault types, S19 and S22. The accuracy is used as an evaluation index.…”

“…The accuracy is used as an evaluation index. The results of comparing the accuracy of the proposed method with [37,38] are shown in table 6. According to table 6, the accuracy of the proposed…”

“…In addition to the aforementioned approaches, many other scholars have conducted extensive research in the field of building electrical fault diagnosis. Xiong et al [37] combined complementary ensemble empirical mode decomposition (CEEMD) and mutual dimensionless index (MDI) for feature extraction, subsequently proposing a multi-kernel relevance vector machine (MK-RVM) in the building electrical system fault diagnosis. Xiong et al [38] introduced a feature extraction method combining variational mode decomposition (VMD) and MDI for fault diagnosis of building electrical systems, and used a quantum genetic algorithm optimized support vector machine (QGA-SVM) method in the fault classification part.…”