Cui Ying, Zou Ye, Jiang Shujun, Zhong Wenqi
School of Automotive and Transportation, Wuxi Institute of Technology, Binhu District, Wuxi, Jiangsu Province 214000, P.R. China.
Key Laboratory of Energy Conversion and Process Measurement and Control Ministry of Education, School of Energy and Environment, Southeast University, Xuanwu District, Nanjing, Jiangsu Province 210096, P.R. China.
ACS Omega. 2023 Mar 8;8(11):10160-10175. doi: 10.1021/acsomega.2c07483. eCollection 2023 Mar 21.
The development of a new and efficient supercritical carbon dioxide (S-CO) power cycle system is one of the important technical ways to break through the bottleneck of coal power development, improve the efficiency of power generation, and realize energy saving and emission reduction. In order to simplify the complicated workload and save the huge time cost of numerical simulations on combustion characteristics, it is of great significance to accurately make the combustion characteristic prediction according to the operating performance of the S-CO CFB boiler. This study proposed a combustion characteristic prediction model corresponding to the S-CO CFB boiler based on the adaptive gray wolf optimizer support vector machine (AGWO-SVM). The parameters of the gray wolf optimizer algorithm were processed adaptively first combined with the boiler characteristics, and then the adaptive gray wolf optimizer algorithm was integrated with the support vector machine to solve the imbalance of local and global search problems of particles being easy to gather in a certain position in the process of pattern recognition. The novel method effectively predicts the boiler in the scaling process from the aspect of boiler capacity, optimizes the combustion characteristic expression by numerical simulations, greatly saves time cost and applicability of enlarged design by altering complex numerical simulations, and lays the application foundation of the S-CO CFB boiler in the industrial field with acceptable operation accuracy.
开发一种新型高效的超临界二氧化碳（S-CO）动力循环系统是突破煤电发展瓶颈、提高发电效率以及实现节能减排的重要技术途径之一。为了简化复杂的工作量并节省燃烧特性数值模拟的巨大时间成本，根据S-CO循环流化床锅炉的运行性能准确进行燃烧特性预测具有重要意义。本研究提出了一种基于自适应灰狼优化器支持向量机（AGWO-SVM）的S-CO循环流化床锅炉燃烧特性预测模型。首先结合锅炉特性对灰狼优化器算法的参数进行自适应处理，然后将自适应灰狼优化器算法与支持向量机相结合，解决模式识别过程中粒子易在某一位置聚集的局部和全局搜索问题的不平衡。该新方法从锅炉容量方面有效地预测了锅炉放大过程，通过数值模拟优化了燃烧特性表达式，极大地节省了时间成本，并通过改变复杂的数值模拟提高了放大设计的适用性，为S-CO循环流化床锅炉在工业领域以可接受的运行精度奠定了应用基础。
