Wind Turbine Fire Prevention System Using Fuzzy Rules and WEKA Data Mining Cluster Analysis

Abstract

With the rapid expansion of the supply of renewable energy in accordance with the global energy transition policy, the wind power generation industry is attracting attention. Subsequently, various wind turbine control technologies have been widely developed and applied. However, there is a lack of research on optimal pitch control, which detects wind direction and changes the rotation angle of the blade in real time. In areas where the wind speed is not strong, such as South Korea, it is necessary to maintain the optimal angle in real time so that the rotating surface of the blade can face the wind direction. In this study, optimal pitch control was performed through real-time analysis of wind speed, direction, and temperature, which is the core of wind turbine maintenance, using fuzzy rules using FIS (Fuzzy Interface System) and WEKA data mining cluster analysis techniques. In order to prevent fires caused by the over-current of wind turbines, over-current control methods such as VCB (Vacuum Circuit Breaker) utilization, prototype utilization such as a modular MCB (Main Circuit Breaker) incorporating VI (Vacuum Interrupter), and vacuum degree change analysis methods using a PD (Partial Discharge) signal were proposed. The optimal control technique for wind turbine parts and facilities was put forth after judging and predicting the annual average wind distribution suitable for wind power generation using HRWPRM (Korea’s High-Resolution Wind Power Resource Maps). Finally, the various wind turbine control methods carried out in this study were confirmed through computer simulation, such as remote diagnosis and early warning issuance, prediction of power generation increase and decrease situation, and automatic analysis of wind turbine efficiency.

Keywords

• pitch/yaw/stall control
• fuzzy rules
• WEKA data mining cluster analysis
• wind turbine over-current
• wind power big data
• fire risk analysis algorithm