Abstract
This paper presents an ensemble-boosting algorithm (EBA) for classifying partial discharge (PD) patterns in the condition monitoring of insulation diagnosis applied for electrical assets. This approach presents an optimization technique for creating a sequence of artificial neural network (ANNs), where the training data for each constituent of the sequence is selected based on the performance of previous ANNs. Four different PD faults scenarios were manufactured in the high-voltage (HV) laboratory to simulate the PD faults of cylindrical voids in methacrylate, point-air-plane configuration, ceramic bushing with contaminated surface and a transformer affected by the internal PD. A PD dataset was collected, pre-processed and prepared for its use in the improved boosting algorithm using statistical techniques. In this paper, the EBA is extensively compared with the widely used single artificial neural network (SNN). Results show that the proposed approach can effectively improve the generalization capability of the PD patterns. The application of the proposed technique for both online and offline practical PD recognition is examined.
Highlights
High-voltage (HV) equipment maintenance is an important aspect of the power industry
This representation is known as a phase-resolved partial discharge (PD) (PRPD) pattern due to the fact that each kind of PD source follows a typical form
This paper is organized as follows: Section 1 is the introduction; Section 2 describes the experimental setup; Section 3 provides the description of the ensemble-boosting algorithm (EBA) algorithm; Section 4 explains the single artificial neural network (SNN) algorithm; Section 5 clarifies the PD input parameters for the EBA algorithm; Section 6 presents the strategies for training the EBA; Section 7 presents the results and discussions, while; Section 8 is the conclusions
Summary
High-voltage (HV) equipment maintenance is an important aspect of the power industry. Internal PD can occurs in voids filled with gas or liquid These sources are the most dangerous ones for the insulation systems and CM of electrical machines based on PD measurements. PDs are commonly represented superimposed with an AC cycle of the voltage reference This representation is known as a phase-resolved PD (PRPD) pattern due to the fact that each kind of PD source follows a typical form. The PRPD represented as 2D plots have not been well investigated as the input for PD pattern recognition by artificial intelligence techniques such as artificial neural networks (ANN) [14,15] It is the aim of this paper to extract suitable PD fingerprints from the PRPD without having to carry out any statistical feature extraction. This paper is organized as follows: Section 1 is the introduction; Section 2 describes the experimental setup; Section 3 provides the description of the EBA algorithm; Section 4 explains the SNN algorithm; Section 5 clarifies the PD input parameters for the EBA algorithm; Section 6 presents the strategies for training the EBA; Section 7 presents the results and discussions, while; Section 8 is the conclusions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
