基于模糊免疫的风电机组异常状态识别

Wind turbine abnormal state identification based on fuzzy immune

风电机组处于高空中,工作环境比较恶劣,导致故障频发。为此,设计一种基于模糊免疫的风电机组异常状态识别方法。结合BM4D与小波去噪设计去噪方法,对初选的特征参量数据进行去噪。利用Relief方法,提取具有较强相关性的风电机组运行状态特征参量。采用模糊免疫算法,设计模糊免疫检测器,检测提取到的特征参量,完成风电机组的异常状态识别。测试结果表明,该方法在异常状态识别中的均方误差低于1%,平均迭代次数低于80次,具有良好的异常识别效果。

The wind turbine unit is located at high altitude,and the working environment is relatively bad,resulting in frequent failures.For this reason,a method of abnormal state identification of wind turbine based on fuzzy immune is designed.Design a denoising method combining BM4D and wavelet denoising to denoise the initially selected feature parameter data.Using the Relief method,extract characteristic parameters of wind turbine operation status with strong correlation.Using fuzzy immune algorithm,design a fuzzy immune detector to detect the extracted feature parameters and complete the identification of abnormal states of wind turbines.The test results show that the mean square error of the method is less than 1%,and the average number of iterations is less than 80 times in the recognition of abnormal state,which has a good recognition effect.