Coal mill fault early warning method based on DPC-MND and multivariate state estimation

Abstract

The invention relates to a coal mill fault early warning method based on DPC-MND and multivariate state estimation, and the method comprises the following steps: 1), building a training matrix K through operation data, corresponding to observation parameters related to a coal mill fault, in historical operation data of a coal mill, enabling the training matrix K to cover all dynamic change conditions of each observation parameter during normal operation of the coal mill; 2) adopting a density peak clustering algorithm based on mutual proximity to extract and construct a memory matrix D in thetraining matrix K, and constructing an MSET early warning model based on the memory matrix D; 3) obtaining an observation matrix Xobs in a to-be-estimated time period, inputting the observation matrixXobs into the MSET early warning model, and adopting multivariate state estimation to obtain an estimation matrix Xest; and 4) obtaining a residual matrix RL = Xobs-Xest between the estimation matrixXest and the observation matrix Xobs, setting a fault early warning threshold, and performing fault early warning through a sliding window method. Compared with the prior art, the method has the advantages of accurate early warning, real-time monitoring, accordance with actual operation, high fault early warning sensitivity and the like.

Description

technical field [0001] The invention relates to the field of coal mill failure detection, in particular to a coal mill failure early warning method based on DPC-MND and multivariate state estimation. Background technique [0002] At present, with the continuous development and application of high-parameter and large-capacity units for thermal power generation, the corresponding auxiliary coal pulverizers are gradually becoming larger, and their role in the production process of thermal power plants is becoming more and more important. As a thermal power unit An important part, the failure of the auxiliary coal pulverizer will directly affect the safe and economical operation of the entire unit. As an important auxiliary coal mill in a thermal power plant, the coal mill is the core coal mill of the coal-fired power plant pulverization system, and its operating status will affect the safety and economy of the entire generating set. However, due to the complex structure and ha...

AI Technical Summary

Problems solved by technology

Peng Jian and Zhang Yanxia used spatially equidistant sampling to construct the process memory matrix. The disadvantage of this method is that it is easy to miss special normal working conditions. At this time, the historical matrix cannot cover all normal working conditions, which may cause large errors in estimation. ; Yang Tingting et al. used the two-norm probability density to construct the history matrix. The disadvantage of this method is that multiple parameters need to be manually specified, and the construction effect of the history matrix is ​​greatly affected by humans. The memory matrix of various operating conditions can not only reduce the influence of human factors, but also make the selected historical matrix more representative. The density peak fast clustering algorithm DPC with adaptive characteristics can be used, but the disadvantage of the DPC algorithm is that the sample is localized. The density does not take into account the structural differences within the data. When the data density difference between clusters is large, DPC cannot obtain a better clustering effect.

Images