本研究以高斯混合模型(Gaussian Mixture Model)為核心建立一套風力機預兆式健康診斷與預測的方法，此方法 包含：採用DBSCAN(Density-Based Spatial Clustering of Applications with Noise)對風力機原始參數進行過濾，高斯混 合模型建立風力機營運性能模型，以信心值來表示風力機的健康狀態，再利用迴歸分析來預測風力機未來營運的健 康信心值。 本研究利用所建立的預兆式診斷方法對台電林口四號風力機的資料進行分析，分析的結果顯示，此風力機 在一般正常運作的情況下，健康狀況信心值約在0.4 至0.8 之間，但風力機營運出現了異常狀況時，信心值大多 低於0.4。但若就長時間的信心值變化而言，此風力機在2013 年至2015 年這三年間是呈現穩定的狀態，即代表 此風力機在這三年間並無太大的性能衰退。另外，透過迴歸分析計算，可預測出此風力機於2033 年8 月8 日後， 整體的健康狀況信心值將會下降到2013 年平均值的兩個標準差以下，代表風力機的性能可能在該時間衰退至不 健康的狀態。

A prognostic and health management method based on the Gaussian mixture model was proposed to analyze and predict the performance of a wind turbine. The proposed method includes preprocessing the raw data of wind turbines by DBCSAN (Density- Based Spatial Clustering of Applications with Noise), building the model of operating performance of wind turbines by GMM (Gaussian Mixture Model), indicating the operating performance by the CV (Confidence Value), and predicting the future CV by regression analysis. The proposed method was applied to analyze the performance data of the Wind Turbine No.4 of Taipower Company at Linkou District. The analysis showed that the CV is between 0.4 and 0.8 in the normal condition and is smaller than 0.4 in the abnormal condition. The CV of the wind turbine is stable between 2013 and 2015. That is, the performance of this wind turbine was not decaying obviously. Furthermore, by regression analysis, the trend of CV will reduce to 0.66 which is out of 2 standard deviations below the mean of 2013 on August 8, 2033. It means that the wind turbine may be unhealthy at that time.