摘要
提出一种小波包分析与最小二乘支持向量机相结合的汽轮机故障诊断模型.对故障信号功率谱进行小波分解,简化了故障特征向量的提取.用二次损失函数取代支持向量机中的不敏感损失函数,将不等式约束条件变为等式约束,从而将二次规划问题转变为线性方程组的求解.选用RBF函数作为核函数,并提出对核函数的参数进行动态选取,提高了诊断的准确率.仿真结果表明该模型具有较强的非线性处理和抗干扰能力.
A steam turbine fault diagnosis model, in which machine （LSSVM） are combined effectively, is proposed wavelet packet analysis and least squares support vector The power spectrums of fault signals are decomposed by using wavelet analysis, which simplifies choosing method of fault eigenvectors. The non-sensitive loss function is replaced by quadratic loss function and the inequality constraints are replaced by equality constraints. Consequently, quadratic programming problem is simplified as the problem of solving linear equation groups. RBF function is used as kernel function, and it is proposed to choose the parameter of kernel function dynamicly, which enhances the preciseness rate of diagnosis. The simulation results show that the model has strong non-linear solution and antijamming ability.
出处
《控制与决策》
EI
CSCD
北大核心
2007年第7期778-782,共5页
Control and Decision
基金
国家自然科学基金项目(60572062)
中国博士后科学基金项目(2005038515).
关键词
小波包分析
故障诊断
最小二乘支持向量机
概率神经网络
汽轮机
Wavelet packet analysis
Fault diagnosis
Least squares support vector machine
Probabilistie neural networks
Steam turbine
