基于核Fisher子空间特征提取的汽轮发电机组过程监控与故障诊断

提出了基于核Fisher子空间特征提取的汽轮发电机组过程监控和故障诊断新方法。该方法首先利用非线性核函数将数据从原始空间映射到高维特征空间，然后在高维特征空间中利用线性Fisher判别分析法提取数据最优的核Fisher特征矢量和判别矢量来实现过程监控。若系统出现故障，则根据当前的判别矢量与历史故障数据集中所含故障的最优核Fisher判别矢量的相似度进行故障诊断。该方法能有效地捕获过程变量之间的非线性关系，过程监控和故障诊断效果明显好于线性Fisher判别法。汽轮发电机组历史故障特征数据集仿真试验证明了该方法的有效性。

Process Monitoring and Fault Diagnosis of Turbine Generator Unit Based on Feature Extraction in Kernel Fisher Subspace

A novel process monitoring and fault diagnosis method of turbine generator unit based on feature extraction in kernel Fisher subspace was proposed.The basic idea of this method is to fast map the original space into high-dimensional feature space via nonlinear kernel function and then extract the optimal kernel Fisher feature vector and discriminant vector to perform process monitoring.If faults occurred,it uses the similar degree between the present discriminant vector and the optimal vector of fault in historical dataset to diagnosis.The proposed method can effectively capture the nonlinear relationship in process variables.Simulation results of turbine generator's fault data prove that the method is effective.