Method, device and equipment for predicting sedimentation of dust remover, storage medium and program product

Abstract

The invention discloses a method and device for predicting sedimentation of a dust remover, equipment, a storage medium and a program product, and the method comprises the steps: obtaining a first data set which comprises data values of M monitoring indexes of the dust remover at N moments; determining a target space-time matrix of M rows and N columns according to the first data set; the target space-time matrix is subjected to empirical orthogonal function EOF decomposition, K first time coefficients corresponding to K EOF modes are obtained, and the K EOF modes are K EOF modes with higher eigenvalues in M EOF modes corresponding to the target space-time matrix; performing singular spectrum analysis on the K first time coefficients to obtain K second time coefficients after SSA reconstruction; using the K second time coefficients to train a first support vector machine (SVM) model; and predicting the sedimentation condition of the dust remover by using the trained first SVM model. Therefore, the precision of settlement prediction is effectively improved, the model prediction speed is obviously improved, and the settlement risk of the dust remover is reduced.

Images