Prediction of the Degree of Polymerization in Transformer Cellulose Insulation Using the Feedforward Backpropagation Artificial Neural Network

Abstract

The life expectancy of power transformers is primarily determined by the integrity of the insulating oil and cellulose paper between the conductor turns, phases and phase to earth. During the course of their in-service lifetime, the solid insulating system of windings is contingent on long-standing ageing and decomposition. The decomposition of the cellulose paper insulation is strikingly grievous, as it reduces the tensile strength of the cellulose paper and can trigger premature failure. The latter can trigger premature failure, and to realize at which point during the operational life this may occur is a daunting task. Various methods of estimating the DP have been proposed in the literature; however, these methods yield different results, making it difficult to accurately estimate a reliable DP. In this work, a novel approach based on the Feedforward Backpropagation Artificial Neural Network has been proposed to predict the amount of DP in transformer cellulose insulation. Presently, no ANN model has been proposed to predict the remaining DP using 2FAL concentration. A databank comprising 100 data sets—70 for training and 30 for testing—is used to develop the proposed ANN using 2-furaldehyde (2FAL) as an input and DP as an output. The proposed model yields a correlation coefficient of 0.958 for training, 0.915 for validation, 0.996 for testing and an overall correlation of 0.958 for the model.

Evaluation method for insulation degradation of power transformer windings based on incomplete internet of things sensing data

“…Degradation evaluation methods relying on traditional indicators [4] Proposed a method based on spectral analysis and pattern recognition using furfural content as an index Cannot be applied to online deterioration evaluation [5] Investigated a method based on the methanol content [6] Explored the correlation between water content in oil data and transformer degradation [7] Developed a model based on feedforward neural networks using the degree of polymerization as an indicator [8] Studied the impact of electrical conductivity on insulation aging Degradation evaluation methods relying on a single type of IoT data [10] Proposed a method based on statistical indices of partial discharge Lack of consideration for multiple degradation factors and data incompleteness [11,12] Proposed two methods to eliminate partial discharge in transformers by preparing nanofluid to absorb gases such as acetylene in oil [13] Proposed a degradation prediction model based on temperature data [14] Investigated the method based on leakage current [15] Studied the electrical damage trend by incrementally increasing the voltage Consider multiple degradation factors but rely on traditional indicators [17] Constructed a dynamic model under the influence of electrical and thermal stress Cannot be applied to online deterioration evaluation [18] Explored the changing trends of indicators under thermal and mechanical stresses [19] Investigated the trends of the indicators under electrical, thermal and mechanical stresses [20] Studied the method based on tensile strength and dielectric constant under thermal-mechanical stresses Data completion for a single type of IoT sensing data [21] Completed voltage data using deep learning and unscented Kalman filtering Lack of consideration of spatiotemporal correlation between multiple IoT sensing data [22] Investigated data filling method in photovoltaic power using recursive long short-term memory network [23] Used the normal distribution method for filling power data of smart meters [24] Proposed a filling method for household load data based on noisy interpolation Abbreviation: IoT, Internet of Things.…”

“…Thango et al developed a degradation evaluation model based on feedforward neural networks, relying on the degree of polymerization. [7]. Dumitran et al examined the ability of conductivity to indicate the degree of insulation aging [8].…”

“…developed a degradation evaluation model based on feedforward neural networks, relying on the degree of polymerization. [7]. Dumitran et al.…”

Modeling and Predicting the Mechanical Behavior of Standard Insulating Kraft Paper Used in Power Transformers under Thermal Aging

“…These structures, which are known as universal approximators, are capable of accurately approximating any sort of continuous or nonlinear function. Through an adjustable learning rate, the Levenberg-Marquardt training algorithm, also benefits from faster training for the multilayer feed-forward architecture [23,24]. The three layers that comprise the developed ANN model are the input, hidden, and output layers, respectively (Figure 4).…”

Evaluation of the Relative Wear of the Insulation of the Power Oil Immersed According to the Data of the IEC60076-7 Standard

“…Processing of information arrays and prediction of the residual life of cellulose insulation can be carried out using fuzzy inference systems, fuzzy neural networks, etc. [15,16,17]. It should be noted that these methods for measuring the DP are indirect, which negatively affects their accuracy.…”