Abstract
Prognostics and Health Management (PHM) is an emerging technique which can improve the availability and efficiency of equipment. A series of related optimization of the PHM system has been achieved due to the growing need for lowering the cost of maintenance. The PHM system highly relies on data collected from its components. Based on the theory of machine learning, this paper proposes a bio-inspired PHM model based on a dissolved gas-in-oil dataset (DGA) to diagnose faults of transformes in power grids. Specifically, this model applies Bat algorithm (BA), a metaheuristic population-based algorithm, to optimize the structure of the Back-propagation neural network (BPNN). Furthermore, this paper proposes a modified Bat algorithm (MBA); here the chaos strategy is utilized to improve the random initialization process of BA in order to avoid falling into local optima. To prove that the proposed PHM model has better fault diagnostic performance than others, fitness and mean squared error (MSE) of Bat-BPNN are set as reference amounts to compare with other power grid PHM approaches including BPNN, Particle swarm optimization (PSO)-BPNN, as well as Genetic algorithm (GA)-BPNN. The experimental results show that the BA-BPNN model has increased the fault diagnosis accuracy from 77.14% to 97.14%, which is higher than other power transformer PHM models.
Highlights
Prognostics and Health Management (PHM) is an emerging technology related to system life-cycle support that enables conspicuously lower expenses on maintenance, usage, and support, and enhances the reliability and availability of the system
This paper is recommended by the SDPC 2018 committee; concerning the limitation in the previous paper, several modifications have been made in this paper including updating the rule of population initialization and the visualization of some results in the classification process from real oil-immersed power transformer data collected by sensors in a power grid
The major contributions are listed as follows: (1) To validate the Bat algorithm (BA) for the power transformer fault diagnosis problem and utilitie the mean squared error (MSE) function to test it. (2) In order to avoid falling into local optima, this paper is based on the chaos strategy proposes modified BA (MBA), which introduces the sinusoidal map instead of the random initialization to modify the population of the standard BA. (3) The evaluation of the proposed machine learning-based PHM model is based on real operational data collected from an oil-immersed transformer in a power grid
Summary
Prognostics and Health Management (PHM) is an emerging technology related to system life-cycle support that enables conspicuously lower expenses on maintenance, usage, and support, and enhances the reliability and availability of the system. A PHM model based on the theory of machine learning that is combined with BA and BPNN is proposed in this paper It is employed in a power transformer to test its reliability. This paper is recommended by the SDPC 2018 committee; concerning the limitation in the previous paper, several modifications have been made in this paper including updating the rule of population initialization and the visualization of some results in the classification process from real oil-immersed power transformer data collected by sensors in a power grid. (3) The evaluation of the proposed machine learning-based PHM model is based on real operational data collected from an oil-immersed transformer in a power grid. The corresponding result proves the better performance of the proposed model for transformer fault diagnosis compared to other traditional PHM methods. MBA-BPNN to power transformer fault diagnosis, tests the model with a DGA dataset from a real oil-immersed power transformer to demonstrate the effectiveness.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
