Fault Diagnosis of Industrial Systems Utilizing Meta-Heuristic Techniques
No Thumbnail Available
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In this research, we employ the Enhanced Discrete Grey Wolf Optimization (EDGWO)
algorithm to identify faults in a simulated Photovoltaic (PV) power plant. Our objective is
to enhance fault detection accuracy and efficiency by utilizing a novel movement algorithm
that optimizes the path for grey wolves. Given the growing importance of Photovoltaic
power plants in sustainable energy production, reliable fault detection mechanisms are
crucial to ensure optimal system operation and longevity.
The Enhanced Discrete Grey Wolf Optimization (EDGWO) algorithm is an improved
iteration of the conventional Grey Wolf Optimization (GWO) algorithm, specifically tailored
for discrete binary optimization challenges. In our work, the grey wolves symbolize
potential solutions for fault detection, where each wolf’s position is encoded as a rule
classification vector. Each element in this vector corresponds to a specific parameter or
feature within the PV power plant system. The optimization process seeks to identify the
optimal feature combination that maximizes fault detection accuracy while minimizing
false alarms.