Method and system for optimizing and controlling combustion performance of circulating fluidized bed boiler in real time

Abstract

The invention provides a method and system for optimizing and controlling combustion performance of a circulating fluidized bed boiler in real time. The method for optimizing and controlling combustion performance of the circulating fluidized bed boiler in real time includes the steps that based on historical data of combustion of the boiler, a first neural network used for being matched with a nonlinear mapping relation between the input and the output of an existing fluidized bed boiler system is established; according to the first neural network, the adjustable input variable of the input of the fluidized bed boiler system is determined; and the adjustable input variable serves as the bottom layer control input, the trends of corresponding deviation and the deviation change rate are calculated, and a second neural network is established for training and acquiring the process variable control output. By the adoption of the method and system, the boiler efficiency is improved, the power supply coal consumption is lowered, coking and slag bonding are prevented or treated, NOx emission is reduced, and the safety, the reliability and the economical efficiency of operation of the boiler are further improved.

Description

technical field [0001] The invention relates to the technical field of boilers, in particular to a real-time optimization control method and system for combustion performance of a circulating fluidized bed boiler (CFB). Background technique [0002] Circulating fluidized bed boiler is an important thermal equipment in my country, with a large amount of use and a wide distribution area. However, the fluidized bed boiler is a multi-variable control object, and the controlled variable has the characteristics of nonlinearity, time-varying, large delay and strong coupling. It is difficult to establish a more accurate and practical mathematical model, and it is difficult to achieve it with conventional PID control. Ideal control effect, so the automation degree of CFB boiler operation is generally not high at present. For a long time, boiler operation has relied on experience design, and the air distribution is often adjusted by the boiler operator according to experience. There i...

AI Technical Summary

Problems solved by technology

[0004] 1. The primary air volume of the boiler, or the left and right sides of the secondary air volume are not uniform, which may easily cause pressure deviations between the two beds, resulting in instability

At the same time, it brings difficulties to the reasonable air distribution of the boiler, and changes the combustion ratio of the dense phase area and the dilute phase area.

[0005] 2. The primary and secondary air volumes are too large or too small. On the one hand, too large will cause excessive loss of bed material, and at the same time reduce the bed temperature and increase coal consumption.

How to effectively use these historical big data to establish a mathematical model that can be used for optimization, there is no specific feasible and effective method in the current technology

[0010] Second, the existing control methods have poor control effects

In view of the characteristics of large lag, large inertia, and strong nonlinearity in the fluidized bed boiler system, the currently widely used PID and its improved algorithm cannot achieve accurate and fast control, and the control effect is not good, so it cannot be optimized for boiler on-line rolling. The implementation of the strategy provides reliable guarantee

[0012] Third, the problem of model mismatch or failure after running for a period of time

There are two problems in this way: a. The existence of the inverse model of the boiler combustion process is difficult to ensure, and the inverse solution may produce no solution or multiple solutions

b. The change between the optimized solution and the current value is too large, which means that the input adjustment range of the combustion system is too large, which may threaten the combustion stability

Images