A Preprocessing Method of Process Data Based on Morphology-EMD Filtering

In view of the features of chemical process data,a morphology empirical mode decomposition(EMD) preprocessing method is presented to filter noises and remove gross errors.A generalized morphological filter is designed as a pre-filter process unit to reduce the effects of gross errors,and a denoising scheme based on empirical mode decomposition is used to remove white noises from process data.The features of process data are extracted which are used to improve the performance of process monitoring.Compared with the traditional filtering method,the morphology-EMD filtering does not need to define the coefficients of filter,so it is fully data-driven and adaptive.The simulation and experimental results show that the method can not only increase the rate of signal to noise ratio(SNR) effectively,and improve the accuracy of fault detection greatly.