针对基于SVM（支持向量机）的故障诊断方法中支持向量机的参数难以选取导致诊断结果较差的问题，采用ABC(人工蜂群算法)对支持向量机的惩罚因子C和核函数参数σ进行优化；并构建了ABC-SVM（人工蜂群优化支持向量机）对燃机涡轮叶片故障进行诊断。诊断实例表明，该方法诊断准确率达到96.43%，具有很好的诊断效果，为燃气轮机故障诊断提供了一种新的方法，具有实际应用价值。

Gas turbine fault diagnosis is of great significance to ensure the safe and reliable operation of the gas turbine.In the fault diagnosis methods based on SVM (Support Vector Machine),the problem that the parameters of the support vector machine are so difficult to select may lead to a bad result of diagnosis.In order to solve the problem,ABC (Artificial Bee Colony) algorithm is used to optimize the penalty factor C and the parameter σof kernel function in the support vector machine,and the fault diagnosis of gas turbine is carried out.The diagnostic example shows that the proposed method has a good diagnostic accuracy and diagnostic speed,therefore,it is a new method for the gas turbine fault diagnosis and expected to have practical application value.

TK478

上海市青年科技英才扬帆计划（16YF1404700）