Depolarization Current Prediction of Transformers OPI System Affected From Detrapped Charge Using LSTM
- 8 June 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 71 (00189456) , 1-11
Abstract
The depolarization current is critical for the computation of insulation-sensitive parameters of the transformer. Prolonged polarization–depolarization current (PDC) measurement times, on the other hand, can increase the likelihood of obtaining distorted original data as a result of environmental factors and electromagnetic noise. Therefore, techniques for measuring PDC data over a short period of time, such as forecasting depolarization current, are required. Additionally, unlike polarization current, which is easily predictable, depolarization current is affected by charging duration and detrapping current. Consequently, an extremely accurate prediction method is required. This paper proposes a multivariate recurrent neural network model based on long short-term memory (LSTM) network for depolarization current prediction using only polarization data. It reduces measurement time and treats the model with time-varying parameters (MTVP) elements as features. Therefore, the influence of the detrapped charge effect while forecasting depolarization current is also considered. The performance of LSTM is compared to that of Linear, Multi-dense, and 1D-Conv (one-dimensional convolutional neural network) to determine the optimum model for forecasting depolarization current. Thereafter, a permutation-based explainability method is used in python to describe model behavior by assessing the variable importance through drop-out loss. The presented results demonstrate that forecasting with the LSTM model produces the lowest mean absolute error and maintains prediction consistency throughout the testing period.Keywords
This publication has 29 references indexed in Scilit:
- Effect of charge accumulated at oil–paper interface on parameters considered for power transformer insulation diagnosisIET Science, Measurement & Technology, 2018
- Transformer Ageing2017
- Assessment of interfacial charge accumulation in oil-paper interface in transformer insulation from polarization-depolarization current measurementsIEEE Transactions on Dielectrics and Electrical Insulation, 2017
- Failure analysis of power transformer for effective maintenance planning in electric utilitiesEngineering Failure Analysis, 2015
- Effect of thermal transient on the polarization and depolarization current measurementsIEEE Transactions on Dielectrics and Electrical Insulation, 2011
- Investigations of Temperature Effects on the Dielectric Response Measurements of Transformer Oil-Paper Insulation SystemIEEE Transactions on Power Delivery, 2007
- Dielectric response of mineral oil impregnated cellulose and the impact of agingIEEE Transactions on Dielectrics and Electrical Insulation, 2007
- Deriving an Equivalent Circuit of Transformers Insulation for Understanding the Dielectric Response MeasurementsIEEE Transactions on Power Delivery, 2005
- Analysis and modeling of dielectric responses of power transformer insulation2003
- Research note: Dielectric diagnosis of water content in transformer insulation systemsEuropean Transactions on Electrical Power, 2001