Radio Frequency (RF) analog circuit failures often occur in broadband, high voltage and high temperature environment, so how to determine fault location and forecast the time which failure is going to occur is an important topic. Based on actual working data of RF Low Noise Amplifier (LNA), a kind of RF circuit fault diagnosis method is put forward with the combination of K-means Clustering, Support Vector Machine (SVM) and Hidden Markov Model (HMM).Simulation results show that the combined method has (3 ~ 4)% recognition accuracy higher than that of the single algorithm. The proposed prognosis method is highly efficient in RF analog circuit fault diagnosis.

射频（RF）模拟电路故障经常发生在宽带、高压和高温环境中，因此如何确定故障位置并预测故障发生的时间是一个重要的课题。基于射频低噪声放大器（LNA）的实际工作数据，提出了一种结合K-means聚类、支持向量机（SVM）和隐马尔可夫模型（HMM）的射频电路故障诊断方法。 仿真结果表明组合方法的识别准确率比单一算法高(3~4)%。所提出的预测方法在射频模拟电路故障诊断中非常有效。