Accurate and robust defect diagnosis methods of relay protection systems could enhance power systems safety and prevent casualties. It is challenging for traditional defect diagnosis methods, such as ID3 (Iterative Dichotomiser 3) and C4.5 (Classifier 4.5), to effectively solve the problem with missing data and ambiguous data that significantly affect the accuracy of diagnosis. To solve the challenges, a novel defect diagnosis method based on Least Square Support Vector Machine Bayesian Network Decision Tree (LSSVM-BNDT) is proposed in this paper. LSSVM is first adopted to fill the missing data. Then, to deal with the non-exclusive ambiguous data, a multi-state Bayesian network is integrated into a decision tree to make a posterior correction. Cases studies are performed to analyze a variety of equipment. And results show that the proposed LSSVM-BNDT has improved detection accuracy by up to 14.87% and 8.56% compared to the ID3 and C4.5 benchmark models, respectively.

Spatial acoustic radiation characteristics analysis is the precondition of reducing the noise influence of outdoor power transformer while multi-physical field coupling method can be applied to quantify and reveal these acoustic characteristics of a running power transformer. In this study, based on the theoretical analysis about noise generation and dissemination process, an acoustic radiation model about oil-immersed power transformer was established and verified with field test data in time and frequency domain. Then, far-field analysis and directivity analysis were accomplished to characterize acoustic field of power transformer under multiple operating conditions. Finally, the acoustic radiation influence on potential surrounding buildings were analyzed and discussed. The visual results and conclusion provide acoustic guide for the optimal planning and design about both power substation and ambient buildings.

Active noise control (ANC) technology can be able to reduce the low frequency noise effectively, and has been widely applied in limited enclosed equipment, such as cars, aircraft cockpits, and headphones, etc. Compared with the traditional noise reduction methods, ANC technology is a cost-effective method in handling the low-frequency noise of transformers. An experimental ANC system in a virtual substation is designed and constructed. An adaptive signal tracking ANC algorithm is proposed, and a set of ANC experimental prototypes applied to a virtual substation is designed. Based on the proposed algorithm, the distributions of the acoustics and spectral characteristics of transformer noise in substations are analyzed. Experimental results show that the effective noise reduction can be achieved an average of 5 dB(A) in a given region with respect to the absence of the ANC system.

Power transformers in substations are common sources of noise in residential areas of neighbourhoods. A quantified and visualized analysis of the power transformer acoustic characteristics is a prerequisite for the suppression of audible noise from the corresponding substation. In this study, based on a combined finite and boundary element method, a full-sized 3D power transformer multiphysics coupling model, which is aimed at realizing high accuracy and improving the computational efficiency, was developed. After validation of the numerical method using comparative tests, profile analyses in the near-field and far-field in the extended planes and three-dimensional areas of a power transformer were conducted to characterize the external acoustic field. The calculation results included the distribution of the spatial sound pressure levels of the power transformer at multiple levels in the frequency domain. These spatial sound pressure levels can be used to guide the efficient measurement of the external acoustic field of a power transformer and the soundscape planning around a substation, and the differentiated design of the sound absorption structure inside a substation.