Data Fusion and Machine Learning Integration for Transformer Loss of Life Estimation

Abstract

Rapid growth of machine learning methodologies and their applications offer new opportunity for improved transformer asset management. Accordingly, power system operators are currently looking for data-driven methods to make better-informed decisions in terms of network management. In this paper, machine learning and data fusion techniques are integrated to estimate transformer loss of life. Using IEEE Std. C57.91-2011, a data synthesis process is proposed based on hourly transformer loading and ambient temperature values. This synthesized data is employed to estimate transformer loss of life by using Adaptive Network-Based Fuzzy Inference System (ANFIS) and Radial Basis Function (RBF) network, which are further fused together with the objective of improving the estimation accuracy. Among various data fusion techniques, Ordered Weighted Averaging (OWA) and sequential Kalman filter are selected to fuse the output results of the estimated ANFIS and RBF. Simulation results demonstrate the merit and the effectiveness of the proposed method. Index Terms-Data fusion, Machine learning, transformer asset management, loss of life estimation.

Distribution asset management through coordinated microgrid scheduling

“…Hourly generation of dispatchable DGs is constrained by the maximum and minimum capacity limits (15), where the unit commitment state variable I would be 1 when the unit is committed and 0 otherwise. Constraints (16)- (19) represent ramp up and ramp down constraints of dispatchable DG units, where (16) and (18) belong to intra-day intervals and (17) and (19) represent ramping constraints for inter-day intervals. Dispatchable DG units are subject to the minimum up and down time limits, represented by (20)- (23).…”

“…A fuzzy modelling in [14] is applied for transformer asset management while improvement in the remaining life of a transformer is achieved by a fuzzy model system. Application of different machine learning methods, such as Adaptive Network-Based Fuzzy Inference System (ANFIS), Multi-Layer Perceptron (MLP) network and Radial Basis Function (RBF) network, in estimating transformer loss of life is presented in [15], where further these methods are fused together to improve the estimation accuracy [16]. In [17], an artificial neural network is modelled to predict top oil temperature in a transformer, where ambient temperature and load current are considered as the input layer and top oil temperature as the output layer.…”

Monte Carlo Simulation Based Structural Part Life Estimation According to Small Sample of Right-censored Data

“…T. H. Loutas et al [6] reported a data-driven approach for the remaining useful life estimation of rolling element bearings based on -Support Vector Regression. In another paper [7], L. L. Li et al [8] presented a general data-driven, similarity-based approach for residual useful life estimation for industrial components or systems.…”