首页|基于数据驱动660MW循环流化床锅炉多目标燃烧优化

基于数据驱动660MW循环流化床锅炉多目标燃烧优化

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
为降低某电厂循环流化床锅炉污染物排放，同时提高锅炉燃烧运行经济性，本文采用数据驱动技术实现循环流化床锅炉多目标燃烧优化。基于改进粒子群优化长短期记忆神经网络建立循环流化床锅炉NOx/SO2排放数学模型和锅炉排烟温度数学模型，以相对误差为预测性评估指标以确定最佳网络参数;其次，基于改进粒子群优化长短期记忆神经网络(IPSO-LSTM)、长短期记忆神经网络(LSTM)、广义回归神经网络(GRNN)和反向传播神经网络(BPNN)分别构建NOx/SO2排放数学模型和锅炉排烟温度数学模型，通过比较预测性评估指标，证明本文构建预测模型有效性;最后，基于非支配排序遗传算法(NSGA-Ⅱ)获取不同运行工况下循环流化床锅炉燃烧优化调整方案，以降低NOx/SO2排放浓度，同时维持排烟温度稳定性。结果表明:相比优化前，优化后NOx排放浓度平均降低了10。58%，SO2排放浓度平均降低了25。81%，最大降低了650 mg/m3，且排烟温度平均降低0。14%。
Multi-objective combustion optimization for 660 MW circulating fluidized bed boiler based on data-driven approach
In order to reduce the pollutant emissions of a circulating fluidized bed boiler in a certain power plant and improve the economy of the boiler combustion operation,this article adopts the data-driven technology to achieve the multi-target combustion optimization for circulating fluidized bed boilers.Improved particle swarm optimization-based long short-term memory neural networks is used to establish the boiler's mathematic model with NOx emission,SO2 emission and exhaust gas temperature as outputs,respectively.The relative error is regarded as a predictive evaluation index to determine the optimal network parameters.Secondly,the NOx emission prediction model,the SO2 emission prediction model and exhaust gas temperature prediction model are constructed based on improved particle swarm optimization-based long short-term memory neural network,long short-term memory neural network(LSTM),generalized regression neural network(GRNN),and a backpropagation neural network(BPNN).By comparing the evaluation indicators,the effectiveness of the predictive models constructed was testified in this paper;Finally,based on the non-dominated sorting genetic algorithm(NSGA-II),the combustion optimization adjustment schemes for CFBB under different operating conditions are obtained so as to reduce NOx/SO2 emission and maintain the stability of exhaust gas temperature at the same time.The results showed that compared with before optimization,the average NOx emission was decreased by 10.583%,the average SO2 emission was reduced by 25.812%,and the maximum reduction of SO2 emission was 650 mg/m3.In addition,the average exhaust gas temperature was decreased by 0.143%.

circulating fluidized bed boilermulti-objective combustion optimizationNOx/SO2 emissionsexhaust gas temperatureimproved particle swarm optimizationlong-short term memory

张文祥、徐文韬、黄亚继、金保昇

展开 >

苏晋朔州煤矸石发电有限公司,山西 朔州 036000

能源热转换及其过程测控教育部重点实验室(东南大学),江苏 南京 210096

循环流化床锅炉 多目标燃烧优化 NOx/SO2排放 排烟温度 改进粒子群优化 长短期记忆神经网络

江苏省科技成果转化专项资金项目

BA2020001

2024

10.19944/j.eptep.1674-8069.2024.02.001

电力科技与环保
国电科学技术研究院

电力科技与环保

影响因子：0.653
ISSN：1674-8069
年,卷(期)：2024.40(2)
  • 33