针对深耦合系统误差监测的需求, 根据深耦合系统中观测量的统计特性, 提出了基于PCA的深耦合误差监测方法, 该方法采用正常观测数据构建PCA模型, 再利用该模型的参数实时监控深耦合系统中的观测数据, 使用该方法检测与消除深耦合系统中的误差, 同时运用小波降噪提升误差检测的性能。最后通过仿真验证了所提方法的可行性和有效性。

Aiming at the demand of monitoring deep coupling system errors, this paper presents a method based on Principal Component Analysis (PCA) for the error monitoring according to the statistical characteristics of view measurement of deep coupling system.The normal observation data is used to construct the PCA model, and the parameters of the model is used for monitoring the observed data in the deep coupling system in real time.This method is used to detect and mitigate the errors in the deep coupling system, while the wavelet denoising is adopted to improve the performance of error detection.Finally, the result of simulation verifies the feasibility and effectiveness of the method.