Method and system for utility boiler combustion subspace modeling and multi-objective optimization

Abstract

The invention discloses a method and system for utility boiler combustion subspace modeling and multi-objective optimization, belongs to the field of utility boiler optimization operation, and particularly relates to a method and system for setting up of a high-precision combustion model and solution of multi-objective optimization. The method includes the following steps of determining input variables of a combustion optimization model, determining the variable to be optimized from all the input variables, dividing a load into a plurality of sectors with the neighborhoods overlapped, setting up a combustion subspace ANFIS model for each sector in an off-line mode, collecting data in real time, conducting partial subspace model modification in an on-line mode, conducting on-line multi-objective optimization by taking the constraint of a unit load into consideration, taking maximizing the boiler efficiency and minimizing the nitrogen oxide emission as targets, and utilizing a mature global optimization algorithm and on the basis of comprehensive cost minimization, and separating and implementing the optimization result. The method and the system are suitable for combustion optimized operation of a coal powder utility boiler and have the advantages of being high in modeling accuracy and high in optimization speed.

Description

technical field [0001] The invention belongs to the technical field of power plant boiler optimization operation, and in particular relates to a method and system for establishing a high-precision combustion model and operation optimization, in particular to a power plant boiler combustion subspace modeling and multi-objective optimization method and system. Background technique [0002] Coal-fired power plants are a very important part of my country's electricity production, and their power generation far exceeds the sum of all other power generation, and there will be no major changes in a long period of time. However, the world is facing a serious crisis of energy depletion, the price of coal remains high, and the problem of environmental pollution has increasingly attracted widespread attention from all over the world. Therefore, the strategies adopted by the governments of various countries are: on the one hand, vigorously develop supercritical power generation technolo...

AI Technical Summary

Problems solved by technology

[0004] After searching the public literature of the prior art, it was found that the document "Qiang Xu, Jia Yang and Yanqiu Yang. Identification and control of boiler combustion system based on neural networks and ant colony optimization algorithm. Proceedings of the 7th World Congress on Intelligent Control and Automation , June 25 - 27, 2008, Chongqing, China, pp.765-768 (Identification and Control of Boiler Combustion System Based on Neural Network and Ant Colony Optimization Algorithm, International Conference: Proceedings of the World Conference on Intelligent Control and Automation, 2008: 765- 768)", the combination of neural network and ant colony optimization in the field of computing intelligence is used for combustion modeling and controller design, which can better improve the adjustment quality of the boiler combustion system, but it can only solve the main controlled parameters of the boiler. Tracks a given setpoint without making the system always operate at optimal economic conditions

Document "Hao Zhou , Kefa Cen, Jianren Fan. Modeling and optimization of the NOx emission characteristics of a tangentially fired boiler with artificial neural networks. Energy, 2004,29:167–183 (Nitrogen Oxidation of Tangentially Fired Boiler with Artificial Neural Networks. Modeling and Control of Emission Characteristics, International Journal: Energy, 2004,29:167–183)", using multi-layer forward network for global modeling and control of nitrogen oxide emission characteristics of tangentially fired boilers, for reducing pollutants Emissions are important, but boiler efficiency is not considered, so optimization is incomplete

Literature (An Enke, Song Yao, Yang Xia. Multi-objective combustion optimization of coal-fired power plant boilers based on support vector machines and genetic algorithms, Energy Saving, 2008(10):22–25), using support vector machines for modeling, while Considering boiler efficiency and pollutant discharge, genetic algorithm is used for multi-objective optimization calculation, but the problem is firstly that the optimization time is long, and secondly, the Pareto optimal solution set is obtained, and there is only one set of solutions finally applied to the site. How to obtain the final The only solution implemented in the field is the problem to be solved

Moreover, the common problems in the above literatures are: (1) A neural network or support vector machine is used to model the global working conditions. For the complex boiler combustion system with severe nonlinear characteristics, the approximation performance of the model in the global scope is difficult. Guaranteed, the model training time will be very long, especially when the coal quality and coal type change, there will be a series of problems in the long time and reliability of the model correction; (2) in the discharge of pollutants or / and The optimization of boiler efficiency does not consider the unit load constraint, so the optimization result may be to reduce pollutant emissions or / and improve boiler efficiency, but at the cost of reducing power generation, so considering the unit load constraint becomes important aspects

Images