Thermal power generating unit denitration system based on deep learning and optimal control method

Abstract

The invention discloses a thermal power generating unit denitration system based on deep learning, and the system comprises a NOx concentration target value setting unit, a dynamic matrix control DMCcontrol unit, a PID control unit, an ammonia injection valve, an SCR reactor, a hearth outlet NOx concentration prediction module unit and an intelligent feedforward controller unit. According to theoptimization control method, data modeling is carried out on the basis of historical data and real-time data of target power plant operation, boiler side adjustable parameters serve as input, SCR outlet NOx concentration measured values serve as output, and a prediction model is constructed through a least square support vector machine algorithm. According to the thermal power generating unit denitration system and the optimal control method, precise ammonia spraying control over the SCR system is achieved, the problems that the system response time is short, and parameter fluctuation is largeare solved, and the control quality of the system is ensured.

Description

technical field [0001] The present invention relates to a thermal power unit denitrification system and an optimal control method, more specifically, to a thermal power unit denitrification system and an optimal control method based on deep learning. Background technique [0002] Nitrogen oxides are one of the main sources of air pollution, and the nitrogen oxides emitted by thermal power plants account for about 35% to 40% of the national nitrogen oxide emissions. The energy conservation and emission reduction of thermal power units is in line with the current development trend of energy conservation and environmental protection. With the increasing awareness of environmental protection, the treatment of flue gas from thermal power units has attracted social attention. NOx is one of the main harmful substances in flue gas. [0003] In this context, my country's environmental protection department has issued a series of plans to curb NOx emissions from thermal power plants. ...

AI Technical Summary

Problems solved by technology

There is a lag in the detection of flue gas parameter signals at the inlet and outlet of the SCR system, and there is a large delay in the reaction process of the SCR reactor. PID control can not get satisfactory control effect

Excessive ammonia injection will lead to increased ammonia escape, causing scaling and corrosion of the air preheater, and too little ammonia injection will cause outlet NO x emissions to fail to meet national emission requirements

Images