基于改进的典型相关分析的故障检测方法

A fault detection method based on modified canonical correlation analysis

为提高基于典型相关分析的故障检测方法使用效率,对原有的残差产生方式进行改进。通过分析残差信号统计特性,重新选取残差产生方式,使得改进的残差生成方式不依赖于主元个数的选取,从而避免因主元个数选取所带来的故障检测性能影响。通过Tennessee Eastman benchmark process仿真实例,对改进方法的可行性和有效性进行验证。选取4个典型故障的运行数据,分别用所提方法进行故障检测,改进的典型相关分析方法能够有效的检测故障的发生。另外,通过对两个统计量的故障检测率的对比可以看出,两个统计量对于发生在不同子空间的故障敏感度各异,对于不同故障的检测能力不同。

In order to improve the effectiveness of the fault detection （FD） method based on standard canonical correlation analysis （ CCA）, the original residual generation was modified. By analyzing the statistical characteristics of the residual signal and changing the residual generation mode, the improved residual generation method did not depend on the selection of the number of principal components, so that the fault detection performance would be free of such a selection. The proposed method was further applied to the Tennessee Eastman benchmark process, in which four typical faults were simulated. The achieved results showed that the proposed method could successfully detect the faults. Due to the different fault sensitivity of the two test statistics, it could be found that the fault detectability of the two test statistics were different.