针对燃煤机组锅炉主再热汽温控制中存在的滞后性、多变量耦合及动态工况适应难题,文章提出一种融合数字孪生技术与最小二乘支持向量机(Least Squares Support Vector Machine,LS-SVM)的汽温寻优方法。通过构建锅炉三维数字孪生模型实现...针对燃煤机组锅炉主再热汽温控制中存在的滞后性、多变量耦合及动态工况适应难题,文章提出一种融合数字孪生技术与最小二乘支持向量机(Least Squares Support Vector Machine,LS-SVM)的汽温寻优方法。通过构建锅炉三维数字孪生模型实现设备状态实时映射,结合LS-SVM建立多变量动态预测模型,并引入多目标微分进化算法(MODE)进行参数优化。实际应用表明,该方法使主汽温波动范围从±7℃缩小至±2.5℃,再热汽温预测误差稳定在±1.5℃以内,年节约燃煤成本超400万元,为火电机组深度调峰与能效提升提供技术支撑。展开更多
Commonly used grain yield forecasting models were briefly reviewed, and a yield prediction model of irrigation district was established based on least squares support vector machines （LS-SVM）. The grain yield in irr...Commonly used grain yield forecasting models were briefly reviewed, and a yield prediction model of irrigation district was established based on least squares support vector machines （LS-SVM）. The grain yield in irrigation district was analog calculated. And the test samples were used to compare with gray prediction, and neural network model. The maximum predicted error of least squares SVM was 7.12%, with an average error of 4.81%. The results showed that LS-SVM model has high prediction accuracy and strong generalization ability. So it could be used as a new method for irrigation district yield prediction展开更多
文摘针对燃煤机组锅炉主再热汽温控制中存在的滞后性、多变量耦合及动态工况适应难题,文章提出一种融合数字孪生技术与最小二乘支持向量机(Least Squares Support Vector Machine,LS-SVM)的汽温寻优方法。通过构建锅炉三维数字孪生模型实现设备状态实时映射,结合LS-SVM建立多变量动态预测模型,并引入多目标微分进化算法(MODE)进行参数优化。实际应用表明,该方法使主汽温波动范围从±7℃缩小至±2.5℃,再热汽温预测误差稳定在±1.5℃以内,年节约燃煤成本超400万元,为火电机组深度调峰与能效提升提供技术支撑。
基金Supported by 863 Plan Project of China(2006AA100213)And theSupport Plan Project of National Science and Technology(2007BAD38B04)~~
文摘Commonly used grain yield forecasting models were briefly reviewed, and a yield prediction model of irrigation district was established based on least squares support vector machines （LS-SVM）. The grain yield in irrigation district was analog calculated. And the test samples were used to compare with gray prediction, and neural network model. The maximum predicted error of least squares SVM was 7.12%, with an average error of 4.81%. The results showed that LS-SVM model has high prediction accuracy and strong generalization ability. So it could be used as a new method for irrigation district yield prediction
