...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Chemical Engineering of Japan >Modeling and Optimization of NOx Emission from a 660?MW Coal-Fired Boiler Based on the Deep Learning Algorithm
【24h】

Modeling and Optimization of NOx Emission from a 660?MW Coal-Fired Boiler Based on the Deep Learning Algorithm

机译：基于深度学习算法的660？MW燃煤锅炉NOx排放的建模与优化

获取原文
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

With the increasingly strict environmental protection policies, restrictions on NOx emissions are becoming increasingly stringent. This paper focuses on modeling and optimizing NOx emission for a coal-red boiler with advanced deep learn ing approaches. Three types of deep recurrent neural network models, including recurrent neural network (RNN), long short-term memory (LSTM), and gate recurrent unit (GRU), are developed to model the relationship between operational parameters and NOx emission of a 660 MW boiler. The hyperparameters of the models are selected by grid search and the e ects of the hyperparameters on the prediction results are analyzed. Compared with the traditional back propagation neural network (BP), support vector machine (SVM) models and deep belief network (DBN), the deep recurrent neural network models have higher prediction accuracy. The experimental results show that the GRU-based NOx prediction model has the best prediction performance among the proposed models. Then, the predicted NOx emission is used as the objective of searching the optimal parameters for the boiler combustion through the grey wolf optimization (GWO) algorithm. The searching process of GWO is convergent. According to the simulation results, the declines in the NOx emis sions in the two selected cases were 19.49% and 17.96%, which are reasonable achievements for the boiler combustion process.
机译：随着环境保护政策越来越严格，对NOX排放的限制正在变得越来越严格。本文侧重于建模和优化具有先进深入学习方法的煤红色锅炉的NOx排放。开发了三种类型的深度复发性神经网络模型，包括经常性神经网络（RNN），长短期记忆（LSTM）和栅极复制单元（GRU），以模拟操作参数与660 MW的NOx排放之间的关系锅炉。通过网格搜索选择模型的超级参数，并分析了预测结果上的超参数的E ECES。与传统的后传播神经网络（BP）相比，支持向量机（SVM）模型和深度信仰网络（DBN），深度反复性神经网络模型具有更高的预测精度。实验结果表明，基于GRU的NOx预测模型在所提出的模型中具有最佳的预测性能。然后，预测的NOx发射被用作通过灰狼优化（GWO）算法来搜索锅炉燃烧最佳参数的目的。 GWO的搜索过程是收敛的。根据仿真结果，两种选定病例中NOx EMIS分部的下降为19.49％和17.96％，这是锅炉燃烧过程的合理成果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号