Prediction method of NOx emission concentration in boilers with wide load based on model transfer

Abstract

The invention discloses a model migration-based method for predicting the NOx emission concentration of a wide-load boiler, including a numerical simulation calculation center, a basic model training center, an operation data communication interface, a basic model migration and update mechanism, and a NOx emission prediction model communication interface; The invention takes the design coal type as the benchmark within the feasible range of the main operating parameters of the boiler, obtains the full working condition sample of the boiler under the design coal type through off-line simulation, and uses machine learning to establish the NOx emission prediction base model; A small number of samples of typical working conditions are obtained through off-line simulation, and then Gaussian process regression is used to transfer the base model of the designed coal type to the non-design coal type working condition to form a base model library that adapts to the changes of multiple coal types; considering the difference between the actual working condition and the simulated working condition First, select the base model according to the actual coal quality, and then project the base model to the actual operation state of the boiler through transfer learning based on the operating data, so as to realize the accurate prediction of NOx emission concentration under the wide load of the boiler.

Description

technical field [0001] The invention belongs to the field of thermal power generation, and in particular relates to a model migration-based method for predicting the NOx emission concentration of a wide-load boiler. Background technique [0002] NOx is one of the main pollutants generated by the combustion of coal-fired boilers. The accurate prediction of the NOx emission concentration of the boiler can provide decision support for the adjustment of the boiler operation mode, so as to meet the increasingly strict environmental protection requirements. However, pulverized coal combustion in a boiler is a complex process coupled with multiple fields, and there are many factors affecting the NOx emission concentration. In addition, with the continuous improvement of the penetration rate of new energy, coal-fired units are more involved in in-depth peak shaving tasks, and boilers often operate under ultra-low loads that deviate from the design conditions, which brings new challe...

AI Technical Summary

Problems solved by technology

However, since the units with deep peak regulation often operate under ultra-low loads that deviate from the design conditions, the data sample coverage is small, and the applicability of the model is difficult to guarantee

In order to solve the above problems, the patent CN107726358A adds CFD simulation samples to the modeling samples to expand the coverage of the samples, but there is a certain difference between the CFD numerical test results and the actual operating characteristics of the boiler, so the obtained model is difficult to accurately predict the NOx emission concentration

Although the NOx emission concentration prediction method disclosed in the patent CN109670625A can realize online updating of training samples to adapt to changes in boiler operating characteristics, it does not consider the influence of coal quality characteristics on NOx emission concentration, so the applicability of the method is limited

Images