Coal as fired calorific value prediction and correction control method combined with flame temperature

Abstract

The invention relates to the technical field of soft measurement, and discloses an as-fired coal calorific value prediction and correction control method in combination with flame temperature, which comprises the following steps: providing an LSTM-based on-line soft measurement model of the as-fired coal calorific value, realizing dynamic modeling of the as-fired coal calorific value in a long-time sequence, and predicting the calorific value of coal in real time. And the change of coal quality in the hearth is quickly tracked. On the other hand, the invention further provides a coal as fired calorific value real-time correction method combined with the flame temperature, flame data information embodied by fuel combustion in a hearth is fully excavated, the relation between coal as fired calorific value changes and flame temperature field distribution is established, and then the coal as fired calorific value obtained through prediction of the LSTM model is corrected. According to the method, dynamic modeling of the calorific value of the coal as fired is carried out on each layer of coal pulverizing system, the change of the calorific value of the fuel of each mill can be distinguished, the online soft measurement result of the calorific value of the coal as fired is more accurate, and the method fully adapts to the conditions of remarkable coal quality change and coal blending combustion of a current power plant.

Description

technical field [0001] The invention relates to the technical field of soft measurement, in particular to a method for predicting and correcting the calorific value of coal entering a furnace combined with flame temperature. Background technique [0002] At present, under the influence of the electricity market environment and rising coal prices, power generation companies are in short supply of coal and have various types of coal, resulting in a big difference between the coal entering the furnace and the original design coal. The consumption of coal is huge. Affected by factors such as region, cost, traffic, etc., power plants cannot burn a single type of coal in large quantities for a long time. In addition, power plants often blend low-quality coal with low calorific value and many impurities, and the blending cannot be guaranteed. The current control strategies are all designed for a single coal type and a single combustion method, with great limitations. The uniformit...

AI Technical Summary

Problems solved by technology

[0007] As a class of soft sensor technology, the present invention aims to overcome the deficiencies of the prior art, and propose a method for predicting and correcting the calorific value of the furnace coal combined with the flame temperature, so as to solve the problem of frequent changes in online coal quality and unstable calorific value of the furnace coal. The problem of inaccurate prediction of the soft sensor model in the case of

Images