由于模型预测控制器对模型失配等不确定因素具有较强的鲁棒性,因此现有的多步预测误差方法不能及时显著地检测到由模型失配导致的MPC控制器性能潜能的变化。针对上述问题,提出一种改进的多步预测误差方法和实时性能监控策略。考虑到MPC...由于模型预测控制器对模型失配等不确定因素具有较强的鲁棒性,因此现有的多步预测误差方法不能及时显著地检测到由模型失配导致的MPC控制器性能潜能的变化。针对上述问题,提出一种改进的多步预测误差方法和实时性能监控策略。考虑到MPC控制器的模型预测残差能有效反映模型失配等信息,利用预测残差对现有多步预测误差方法进行改进,改进的方法能够更好地检测由模型失配引起的MPC控制器性能潜能的改变。在连续搅拌槽加热器(continuous stirred tank heater,CSTH)系统上的仿真实验验证了该方法的可行性与有效性。展开更多
针对当前MPC控制回路性能评价方法无法准确定位性能下降源的问题,提出一种基于加权L2-Hausdorff子空间距离的控制回路性能诊断方法。该方法引用恶化性能子空间表征各个性能恶化工况下的回路特征,通过基于模型预测残差的闭环潜能指标实...针对当前MPC控制回路性能评价方法无法准确定位性能下降源的问题,提出一种基于加权L2-Hausdorff子空间距离的控制回路性能诊断方法。该方法引用恶化性能子空间表征各个性能恶化工况下的回路特征,通过基于模型预测残差的闭环潜能指标实时监测控制回路性能。当发现性能下降时,构造加权L2-Hausdorff子空间距离来度量当前回路性能模式与已知性能模式的相似度,通过距离聚类来定位回路性能下降的恶化源。最后,通过连续搅拌加热器(continuous stirred tank heater,CSTH)上的仿真实验,验证了所提方法的有效性及可靠性。展开更多
To predict the economic loss of crops caused by acid rain,we used partial least squares(PLS) regression to build a model of single dependent variable -the economic loss calculated with the decrease in yield related to...To predict the economic loss of crops caused by acid rain,we used partial least squares(PLS) regression to build a model of single dependent variable -the economic loss calculated with the decrease in yield related to the pH value and levels of Ca2+,NH4+,Na+,K+,Mg2+,SO42-,NO3-,and Cl-in acid rain. We selected vegetables which were sensitive to acid rain as the sample crops,and collected 12 groups of data,of which 8 groups were used for modeling and 4 groups for testing. Using the cross validation method to evaluate the performace of this prediction model indicates that the optimum number of principal components was 3,determined by the minimum of prediction residual error sum of squares,and the prediction error of the regression equation ranges from -2.25% to 4.32%. The model predicted that the economic loss of vegetables from acid rain is negatively corrrelated to pH and the concentrations of NH4+,SO42-,NO3-,and Cl-in the rain,and positively correlated to the concentrations of Ca2+,Na+,K+ and Mg2+. The precision of the model may be improved if the non-linearity of original data is addressed.展开更多
Polar motion depicts the slow changes in the locations of the poles due to the earth's internal instantaneous axis of rotation. The LS+AR model is recognized as one of the best models for polar motion prediction.T...Polar motion depicts the slow changes in the locations of the poles due to the earth's internal instantaneous axis of rotation. The LS+AR model is recognized as one of the best models for polar motion prediction.Through statistical analysis of the time series of the LS+AR model's short-term prediction residuals,we found that there is a good correlation of model prediction residuals between adjacent terms.These indicate that the preceding model prediction residuals and experiential adjustment matrixes can be used to correct the next prediction results,thereby forming a new LS+AR model with additional error correction that applies to polar motion prediction.Simulated predictions using this new model revealed that the proposed method can improve the accuracy and reliability of polar motion prediction.In fact,the accuracies of ultra short-term and short-term predictions using the new model were equal to the international best level at present.展开更多
文摘由于模型预测控制器对模型失配等不确定因素具有较强的鲁棒性,因此现有的多步预测误差方法不能及时显著地检测到由模型失配导致的MPC控制器性能潜能的变化。针对上述问题,提出一种改进的多步预测误差方法和实时性能监控策略。考虑到MPC控制器的模型预测残差能有效反映模型失配等信息,利用预测残差对现有多步预测误差方法进行改进,改进的方法能够更好地检测由模型失配引起的MPC控制器性能潜能的改变。在连续搅拌槽加热器(continuous stirred tank heater,CSTH)系统上的仿真实验验证了该方法的可行性与有效性。
文摘针对当前MPC控制回路性能评价方法无法准确定位性能下降源的问题,提出一种基于加权L2-Hausdorff子空间距离的控制回路性能诊断方法。该方法引用恶化性能子空间表征各个性能恶化工况下的回路特征,通过基于模型预测残差的闭环潜能指标实时监测控制回路性能。当发现性能下降时,构造加权L2-Hausdorff子空间距离来度量当前回路性能模式与已知性能模式的相似度,通过距离聚类来定位回路性能下降的恶化源。最后,通过连续搅拌加热器(continuous stirred tank heater,CSTH)上的仿真实验,验证了所提方法的有效性及可靠性。
基金Funded by the Natural Basic Research Program of China under the grant No. 2005CB422207.
文摘To predict the economic loss of crops caused by acid rain,we used partial least squares(PLS) regression to build a model of single dependent variable -the economic loss calculated with the decrease in yield related to the pH value and levels of Ca2+,NH4+,Na+,K+,Mg2+,SO42-,NO3-,and Cl-in acid rain. We selected vegetables which were sensitive to acid rain as the sample crops,and collected 12 groups of data,of which 8 groups were used for modeling and 4 groups for testing. Using the cross validation method to evaluate the performace of this prediction model indicates that the optimum number of principal components was 3,determined by the minimum of prediction residual error sum of squares,and the prediction error of the regression equation ranges from -2.25% to 4.32%. The model predicted that the economic loss of vegetables from acid rain is negatively corrrelated to pH and the concentrations of NH4+,SO42-,NO3-,and Cl-in the rain,and positively correlated to the concentrations of Ca2+,Na+,K+ and Mg2+. The precision of the model may be improved if the non-linearity of original data is addressed.
基金supported by the National Natural Science Foundation of China(Grant Nos.41021061&41174012)
文摘Polar motion depicts the slow changes in the locations of the poles due to the earth's internal instantaneous axis of rotation. The LS+AR model is recognized as one of the best models for polar motion prediction.Through statistical analysis of the time series of the LS+AR model's short-term prediction residuals,we found that there is a good correlation of model prediction residuals between adjacent terms.These indicate that the preceding model prediction residuals and experiential adjustment matrixes can be used to correct the next prediction results,thereby forming a new LS+AR model with additional error correction that applies to polar motion prediction.Simulated predictions using this new model revealed that the proposed method can improve the accuracy and reliability of polar motion prediction.In fact,the accuracies of ultra short-term and short-term predictions using the new model were equal to the international best level at present.
