Thermal process alarm data filtering method and system based on AHC-GP hybrid model

Abstract

The invention discloses a thermal process alarm data filtering method and system based on an AHC-GP hybrid model, and belongs to the technical field of data processing. According to an existing data processing scheme, redundant alarm cannot be effectively eliminated, alarm overflow cannot be inhibited in time, and the problem of alarm overflow caused by abnormal propagation is aggravated. The invention provides a thermal process alarm data filtering method based on an AHC-GP hybrid model, and the method can carry out the preprocessing of a data set, determines the optimal clustering number through employing an affinity propagation algorithm, carries out the clustering of the data set through employing a condensed hierarchical clustering algorithm, and distinguishes different working conditions. And secondly, performing data classification by using a Gaussian process model, and constructing a data filtering model in combination with a posterior alarm probability estimated value to realize accurate filtering of thermal process alarm data. Furthermore, key alarm data in a data set can be accurately positioned, and redundant alarm is eliminated; the method is low in omission ratio and misjudgment rate, and has good data filtering accuracy.

Description

technical field [0001] The invention relates to a thermal process alarm data filtering method and system based on an AHC-GP hybrid model, belonging to the technical field of data processing. Background technique [0002] With the continuous adjustment of my country's energy structure, thermal power generation is facing a series of new difficulties and challenges, such as low-emission transformation, new energy power generation integration and deviation from coal operation, which lead to frequent fluctuations in the operation of the unit, which is inevitable. Generate a large amount of alarm data. In the centralized control center of the power plant, system operators usually need to process a large amount of real-time alarm information and make important decisions on the operation of the power generation system. These alarms may be related to equipment failure, misoperation of protective devices, etc. Due to the complexity of the control system of thermal power units, the la...

AI Technical Summary

Problems solved by technology

Due to the complexity of the control system of thermal power units, the large number of production equipment and parameters, and the close relationship between variables, and the low efficiency of the existing alarm system, the problem of "alarm flooding" is very common

[0003] Furthermore, due to the characteristics of nonlinearity, strong coupling, high dimensionality and time-varying nature of thermal process alarm data, simple models are difficult to fit

At the same time, the data set usually contains multiple complex working conditions, which increases the difficulty of data processing, causing operators to be unable to accurately locate important alarm data and eliminate alarms in time, and unable to suppress alarm overflow in time, exacerbating the " "alarm flooding" problem

Images