In the present paper, a novel multi-criterion-based adaptive neuro-fuzzy inference system (ANFIS) is proposed to determine the overall health index (OHI) of power transformer insulation. The proposed model concentrates on 12 diagnostic attributes related to dissolved gases, oil and
paper insulation. On-field data from 150 transformers collected from Himachal Pradesh State Electricity Board, India, are utilised. Initially, the collected data are normalised and correlation among the attributes is established using a multi-criterion approach (MCA) according to IEEE standards
C57.104-2019 and C57.106-2015. Closely related attributes are grouped into three grades. The obtained three grades are applied as input to the ANFIS model and the transformer health index (HI) is output. Among the collected data, 80% are used for training and 20% are used for
testing. The performance of the proposed model is evaluated using two crucial error metrics: root mean square error (RMSE) and correlation coefficient (R
2
). Moreover, the proposed model is validated using 110 data samples collected from the literature and compared with existing
expert models, achieving an accuracy of 98.18%. The integration of the MCA with the ANFIS model overcomes the shortcomings of the previous ANFIS model, requiring huge training time, larger rule formation and a high computational burden on the network. The proposed MCA-based ANFIS model
is easy to implement and accurately predicts the health indices. The present work is beneficial for diagnostic experts looking to take appropriate remedial actions on the current health status of transformer insulation.
M. Gopi, C. Ranga, K. Jagtap· Insight - Non-Destructive Te...· 0 citations
Condition assessment of a transformer provides information about the overall health status of the insulation. Accurate health index (HI) prediction at regular intervals prevents catastrophic failures. In this study, a novel multi-hierarchically weighted neural network is proposed to estimate the HI of power transformers. It is designed with 12 distinct features of an oil- and paper-insulation system. Initially, collected attributes are normalized using multi-criterion analysis (MCA). The correlation and appropriate weight prioritization of each attribute are determined using the analytical hierarchy process (AHP). The combined MCA-AHP facilitates the calculation of weighted scores and converts the 12 attributes into 3 quality grades. These grades are used as inputs to the hybrid artificial neural network (ANN), and the output is the overall HI. The model is trained and tested using 350 data samples collected from the Himachal Pradesh State Electricity Board, India. The performance of the proposed hybrid model is validated by root mean square error, mean absolute error, mean relative error, and correlation coefficient. Furthermore, a comprehensive comparison is conducted using 300 data samples with pre-known health conditions (HCs), and other expert models in the literature achieved 97% of accuracy. The proposed hybrid model effectively addresses the general issues raised by intelligent models, such as reliance on expert rule-based approaches in Fuzzy models, greater computational demand in ANN and ANFIS models, and increased complexity due to diagnostic attributes. Based on the predicted HCs, preventive maintenance actions are proposed to ensure effective maintenance of the asset.
M. Gopi, C. Ranga, K. Jagtap· Engineering Research Express· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
