On March 14,2025,the Centre for China and Globalisation(CCG)held its first VIP Luncheon of the year at the Beijing International Club.The event was moderated by CCG President Wang Huiyao and brought together over 50 C...On March 14,2025,the Centre for China and Globalisation(CCG)held its first VIP Luncheon of the year at the Beijing International Club.The event was moderated by CCG President Wang Huiyao and brought together over 50 Chinese and international vips,including ambassadors from 17 countries,senior diplomats from 8 countries,as well as representatives from international organisations and chambers of commerce,corporate executives,and prominent media professionals.展开更多
碳排放连续在线监测法作为一种高效、可溯源的方法,在我国碳计量领域中逐渐应用。然而,由于烟囱管道的大直径、复杂烟气流场,以及流量计检修维护、粉尘堵塞导致的监测数据中断与异常,烟气流量的准确监测成为一大挑战。为此,提出一种融...碳排放连续在线监测法作为一种高效、可溯源的方法,在我国碳计量领域中逐渐应用。然而,由于烟囱管道的大直径、复杂烟气流场,以及流量计检修维护、粉尘堵塞导致的监测数据中断与异常,烟气流量的准确监测成为一大挑战。为此,提出一种融合变量投影重要性分析(variable importance in projection,VIP)、最大信息系数(maximal information coefficient,MIC)及后向搜索(sequential backward selection,SBS)算法的联合筛选方法,结合支持向量机(support vector machine,SVM)构建烟气流量软测量模型。基于某F级燃气-蒸汽联合循环发电机组,通过VIP值评估辅助变量显著性,并结合MIC和SBS算法,进行变量冗余消除与优化选择,从而提升模型的预测精度和泛化能力。实验结果显示:SVM的表现优于长短时间记忆网络模型,与反向传播神经网络相比具有较好的泛化能力;当辅助变量数量为12时,模型性能最佳,测试集的均方根误差和平均绝对百分比误差均较低,验证了变量筛选方法的有效性;在稳态和非稳态工况下,模型预测值的平均绝对百分比误差小于0.7%,并有一定的滤波作用。展开更多
文摘On March 14,2025,the Centre for China and Globalisation(CCG)held its first VIP Luncheon of the year at the Beijing International Club.The event was moderated by CCG President Wang Huiyao and brought together over 50 Chinese and international vips,including ambassadors from 17 countries,senior diplomats from 8 countries,as well as representatives from international organisations and chambers of commerce,corporate executives,and prominent media professionals.
文摘碳排放连续在线监测法作为一种高效、可溯源的方法,在我国碳计量领域中逐渐应用。然而,由于烟囱管道的大直径、复杂烟气流场,以及流量计检修维护、粉尘堵塞导致的监测数据中断与异常,烟气流量的准确监测成为一大挑战。为此,提出一种融合变量投影重要性分析(variable importance in projection,VIP)、最大信息系数(maximal information coefficient,MIC)及后向搜索(sequential backward selection,SBS)算法的联合筛选方法,结合支持向量机(support vector machine,SVM)构建烟气流量软测量模型。基于某F级燃气-蒸汽联合循环发电机组,通过VIP值评估辅助变量显著性,并结合MIC和SBS算法,进行变量冗余消除与优化选择,从而提升模型的预测精度和泛化能力。实验结果显示:SVM的表现优于长短时间记忆网络模型,与反向传播神经网络相比具有较好的泛化能力;当辅助变量数量为12时,模型性能最佳,测试集的均方根误差和平均绝对百分比误差均较低,验证了变量筛选方法的有效性;在稳态和非稳态工况下,模型预测值的平均绝对百分比误差小于0.7%,并有一定的滤波作用。
