A smart combustion control method for thermal power plants based on cloud data and cloud computing

Abstract

A method for intelligent combustion control of thermal power plants based on cloud data and cloud computing. Firstly, a cloud database is constructed, and abnormal value processing is performed on the input data and output data in the cloud database, and then principal component analysis is performed. The heat exchange surface wall temperature prediction model, the NOx concentration distribution prediction model at the inlet of the denitrification reactor and the boiler efficiency prediction model are trained, and the training results are compared with the data of the model calibration system. If the root mean square error is within 15%, the integrated prediction The predicted value of heat exchange surface wall temperature, NOx concentration predicted value and boiler efficiency predicted value provided by the model are calculated through the intelligent operation control module to obtain the optimal operating parameters and realize the dynamic optimization control of boiler combustion and pollutant generation. The invention improves the efficiency of the boiler and the adaptability to the change of coal types, reduces the average emission of NOx by more than 10%, and realizes the maximization of power generation benefits.

Description

technical field [0001] The invention belongs to the field of thermal automatic control, and relates to an optimized operation technology of a power station boiler combustion system, in particular to a thermal power plant intelligent combustion control method based on cloud data and cloud computing. Background technique [0002] Thermal power plants generally use combustion adjustment tests to optimize operation. By carrying out combustion experiments under different loads, boiler efficiency and NOx are taken as optimization goals, and the operating variables corresponding to the optimal combustion conditions are saved in the DCS setting module, so as to determine the actual operation of the boiler. control. However, changes in boundary conditions such as boiler load, coal type, and ambient temperature lead to a large difference between the actual operating conditions of the boiler and the experimental conditions, and the combustion adjustment test rule does not meet the actu...

AI Technical Summary

Problems solved by technology

[0004] Due to the complexity of the flow field and combustion chemical reactions in the boiler furnace, there are complex coupling relationships among many operating parameters, which brings great difficulties to the modeling and optimization of boiler combustion.

The boiler has a large time-varying characteristic. With the passage of time and changes in the operating conditions of the boiler, the learning model of the boiler combustion process will have large errors. The model established offline cannot adapt to this change, resulting in model mismatch.

Images