Non-linearity and parameter time-variety are inherent properties of lateral motions of a vehicle. How to effectively control intelligent vehicle (IV) lateral motions is a challenging task. Controller design can be reg...Non-linearity and parameter time-variety are inherent properties of lateral motions of a vehicle. How to effectively control intelligent vehicle (IV) lateral motions is a challenging task. Controller design can be regarded as a process of searching optimal structure from controller structure space and searching optimal parameters from parameter space. Based on this view, an intelligent vehicle lateral motions controller was designed. The controller structure was constructed by T-S fuzzy-neural network (FNN). Its parameters were searched and selected with genetic algorithm (GA). The simulation results indicate that the controller designed has strong robustness, high precision and good ride quality, and it can effectively resolve IV lateral motion non-linearity and time-variant parameters problem.展开更多
为进一步提高光伏发电功率超短期预测的准确度,提出一种基于混沌理论(Chaos)-集合经验模态分解(ensemble empirical mode decomposition,EEMD)-峰值频段划分(peak frequency band division,PFBD)和GA-BP神经网络的光伏发电功率组合预测...为进一步提高光伏发电功率超短期预测的准确度,提出一种基于混沌理论(Chaos)-集合经验模态分解(ensemble empirical mode decomposition,EEMD)-峰值频段划分(peak frequency band division,PFBD)和GA-BP神经网络的光伏发电功率组合预测法。首先,在光伏发电功率序列相空间重构的基础上,采用EEMD和PFBD对隐含混沌特征进行优化提取,以深度挖掘数据隐含波动信息,提取平稳性好、可预测性强的聚合分量;然后,利用GA优化BP神经网络(BPNN)的初始权值与阈值,构建GA-BP神经网络预测模型,进行光伏发电功率单步和三步预测;最后基于实测功率数据进行有效性验证。仿真结果表明:所提预测法通过数据分解重构和GA优化可实现预测准确度的提高,显示出良好预测性能。展开更多
文摘Non-linearity and parameter time-variety are inherent properties of lateral motions of a vehicle. How to effectively control intelligent vehicle (IV) lateral motions is a challenging task. Controller design can be regarded as a process of searching optimal structure from controller structure space and searching optimal parameters from parameter space. Based on this view, an intelligent vehicle lateral motions controller was designed. The controller structure was constructed by T-S fuzzy-neural network (FNN). Its parameters were searched and selected with genetic algorithm (GA). The simulation results indicate that the controller designed has strong robustness, high precision and good ride quality, and it can effectively resolve IV lateral motion non-linearity and time-variant parameters problem.
文摘为进一步提高光伏发电功率超短期预测的准确度,提出一种基于混沌理论(Chaos)-集合经验模态分解(ensemble empirical mode decomposition,EEMD)-峰值频段划分(peak frequency band division,PFBD)和GA-BP神经网络的光伏发电功率组合预测法。首先,在光伏发电功率序列相空间重构的基础上,采用EEMD和PFBD对隐含混沌特征进行优化提取,以深度挖掘数据隐含波动信息,提取平稳性好、可预测性强的聚合分量;然后,利用GA优化BP神经网络(BPNN)的初始权值与阈值,构建GA-BP神经网络预测模型,进行光伏发电功率单步和三步预测;最后基于实测功率数据进行有效性验证。仿真结果表明:所提预测法通过数据分解重构和GA优化可实现预测准确度的提高,显示出良好预测性能。
