论文部分内容阅读
提出了用主成分分析法建立系统的模型,通过检测测量数据在残差子空间内的投影大小来检测故障.分析认为造成传感器小故障难于检测的原因在于测量数据的噪声太大,并提出采用指数加权滑动平均滤波器来提高系统小故障检测能力的方法.实验表明,方法是有效的.图3,参8.
The principal component analysis (PCA) was used to establish the model of the system, and the fault was detected by measuring the projection size of the measured data in the residual subspace. The reason for the difficulty in detecting sensor glitches was that the noise of the measured data was too large, Exponential Weighted Moving Average Filter to improve the ability of system glitch detection.Experiments show that the method is effective.