Real-time knowledge discovery method and system for coal-fired boiler process object

Abstract

The invention provides a real-time knowledge discovery method and system for a coal-fired boiler process object, and the method comprises the steps: carrying out the time sequence adjustment of the collected production state parameter data of a boiler, and obtaining correct time sequence data; adopting a data flow clustering method based on a sliding window, storing a clustering center result of each time, comparing clustering results of the last time each time, and if the difference value of every two adjacent clustering results is within a set range, conducting no operation and enabling thenext data flow to continue to be waited; otherwise, modifying and updating the change trend mathematical formula to be suitable for the latest production state; continuously carrying out a subsequentknowledge discovery process to obtain a new formula, carrying out association chain mining through an association rule algorithm to obtain a latest influence relationship and a change rule of each production parameter, and generating an association chain among the parameters; and finally, performing modeling prediction on the data through a flexible neural tree, and outputting a new change trend mathematical formula of the data, thereby assisting in adjusting production process parameters.

Description

technical field [0001] The disclosure relates to the technical field of data processing, in particular to a real-time knowledge discovery method and system for process objects of coal-fired boilers. Background technique [0002] In the distributed control system of the process industry, due to the existence of data in multiple links, there is a certain influence relationship between the links. It is of great practical significance to dig out this implicit correlation from link data so that people can better understand the production status and whether abnormal situations have occurred. [0003] At present, the DCS distributed control system is widely used in process industry production. The system can collect the production status of each link in the process industry production process in real time. The data collected by the process industry control system has been accumulated for a long time to form a large-scale historical database. These data contain a large amount of v...

AI Technical Summary

Problems solved by technology

[0005] For the production link of thermoelectric steam furnace, the production state parameters that can be predicted include air bag pressure, main steam temperature, material layer temperature, return material temperature, flue gas oxygen content, furnace differential pressure, material layer differential pressure, etc., according to the boiler According to the working characteristics of the steam system, due to the complex equipment and many links, there is a large lag in the change of parameters, but the change trend can be maintained for a long time, so "advance adjustment" and "stabilization" will be adopted in equipment adjustment. However, in the actual production, only front-line workers can adjust with their own experience, and cannot find state changes and production failures stably and efficiently, resulting in a reduction in the efficiency of steam boilers.

Images