Based On Image Processing, The Prediction Of Unburned The Ember Carbon And Nox Emissions And Combustion Furnace Operation Guidance System

That a power plant runs safely, economically and cleanly is very important to enterprise and environment. It is the optimism of the combustion in furnaces that can effectively approach this goal. What's more, combustion optimism can not only save the fuel, but also avoid tube explosion in furnaces. In this way, the efficiency and safety of power plant boilers can be ensured. For exact and available combustion adjustment, a reliable monitoring method, which requires the Real-time available parameters for combustion diagnosis, is needed. The purpose of this thesis is to establish a new combustion monitoring and control system based on the image processing and artificial intelligence technology to carry out the combustion visualization and diagnosis, and then give the instruction information for power plant staff.Firstly, we have researched for how oxygen pressure, pulverized coal particle diameter, heating velocity and atmosphere affecting on pulverized coal combustion velocity, and summarized various factors and affection what affecting the content of combustible in fly-ash; we have researched for the NOx formation mechanism and the emission discipline. These affecting factors are the academic base of predicting parameters selecting.Secondly, we use advanced computer image processing technology, based on flame image luminosity information, chroma information and radiant transfer equation, to inverse-figure and calculate the temperature distribution in a boiler. We have carried on experiments at a lab and at a utility boiler respectively, and have validated the feasibility and rationality of the arithmetic.Thirdly, we used the researched results above, combining the utility boiler function parameters and coal property data to diagnose the pollutant emission and the content of combustible in fly-ash. We acquired credible emulation model. The researched results show that the content of combustible in fly-ash, NOx emission can be predicted by the utility boiler function parameters. The results can be analysed the relation of the parameters and the content of combustible in fly-ash- NOx emission, and can be the base of the combustion diagnosis and running guidance.Finally, the thesis illustrated the primary application of flame image processing system to the 300MWe power plant boiler. The design idea, hardware system, and software function was described in details. With this system, the research on the combustion visualization and diagnosis will be testified and advanced.