Abstract
Background: Dissolved Gas Analysis (DGA) is an effective method to detect the potential fault of oil immersed transformer, while the ratio method based on DGA technology has some defects.
Objective: This study aims to timely comprehend the transformer condition and accurately predict the incipient fault.
Methods: By investigating the recently published papers and patents relating to transformer fault diagnosis, a novel diagnosis model based on the enhanced cuckoo search algorithm combined with BP neural network (ECSBP) is designed. In the proposed approach, the adaptive adjustment strategy of step size is employed to enhance the convergence rate and solution quality. Furthermore, the dimension by dimension improvement mechanism is also utilized to balance the exploration and exploitation. Subsequently, the transformer fault diagnosis model using ECSBP approach is built.
Results: By evaluating the optimization performance on a set of benchmark functions, the enhanced cuckoo search algorithm is apparently superior to the original CS and its 2 variants. Simultaneously, compared with the other 4 transformer fault diagnosis models, ECSBP method has the highest diagnostic accuracy.
Conclusion: The proposed ECSBP model integrates the advantages of artificial intelligence and DGA technology, and then can be used in the fault diagnosis of power transformer.
Keywords: Cuckoo search, transformer, fault diagnosis, dissolved gas analysis, neural network, optimization.
Graphical Abstract
Call for Papers in Thematic Issues
Advanced Experimental, Computational Fluid Dynamics and Intelligent Computing Techniques on Complex Multiphase Flow Problems
Computational fluid dynamics (CFD) and Intelligent computing are very emerging technology in various industrial applications. Multiphase flow problems are very dominant in hydro as well as power plants, mining, marine, cementing, food processing, and ore-processing industries. Multiphase flows include gas-solid as well as liquid-solid flows. The solid like ores, ash, ...read more
Advanced materials for energy production, transmission, and utilization
Hydrogen storage and production materials: Developing high-performance hydrogen generation and storage materials, as well as researching the mechanism of hydrogen-material interaction. The emphasis for supercapacitors is on carbon-based materials derived from various biomass carbonization methods, as well as carbon-containing electrode materials such as metal sulfide, oxides, and other similar compounds. ...read more
Advancements in Machine Learning for Medical Applications in Material Science
The fusion of machine learning with medical applications and material science has ushered in a new era of innovation, offering transformative solutions to complex healthcare challenges. "Advancements in Machine Learning for Medical Applications in Material Science," a special issue, serves as a crucible for exploring the remarkable synergy between these ...read more
Computational Methods in Engineering
In recent decades, computational methods have revolutionized the field of engineering, playing a pivotal role in enhancing efficiency, accuracy, and innovation across various disciplines. This proposed thematic issue aims to explore and showcase the latest advancements, challenges, and applications of computational methods in engineering. As technology continues to evolve, computational ...read more
Related Books
Intelligent Technologies for Automated Electronic Systems
Modern Radio Signals Filtering Devices Methods, Technologies, & Structures
Functional Bio-based Materials for Regenerative Medicine: From Bench to Bedside (Part 2)
Mechanical Engineering Technologies and Applications
Multistage Interconnection Network Design for Engineers
Mechanical Engineering Technologies and Applications
Semi-rotary and Linear Actuators for Compressed Air Energy Storage and Energy Efficient Pneumatic Applications
Waste Valorization for Value-added Products
One-Dimensional Transient Flow in Pipelines Modelling and Simulation
Principles of Automation and Control
26