Aim To present a simple and effective method for the design of nonlinear and time varying control system. Methods A new concept of dynamic equilibrium of a system and its stability were presented first. It was poin...Aim To present a simple and effective method for the design of nonlinear and time varying control system. Methods A new concept of dynamic equilibrium of a system and its stability were presented first. It was pointed out that what is controlled directly by the input of a control system is the system's dynamic equilibrium rather than the states. Based on it, a new feedback linearization method for nonlinear system based on the Lyapunov direct method was given. Simulation studies were also carried out. Results The example and simulation show that by use of the method, the controller design becomes very simple and the control effect is quite satisfying. Conclusion The new method unifies the stabilizing problem(regulating problem) with the tracking problem. It is a very simple and effective method for the design of nonlinear and time varying control system.展开更多
This paper presents a flight control design for an unmanned aerial vehicle （UAV） using a nonlinear autoregressive moving average （NARMA-L2） neural network based feedback linearization and output redefinition techn...This paper presents a flight control design for an unmanned aerial vehicle （UAV） using a nonlinear autoregressive moving average （NARMA-L2） neural network based feedback linearization and output redefinition technique. The UAV investigated is non- minimum phase. The output redefinition technique is used in such a way that the resulting system to be inverted is a minimum phase system. The NARMA-L2 neural network is trained off-line for forward dynamics of the UAV model with redefined output and is then inverted to force the real output to approximately track a command input. Simulation results show that the proposed approaches have good performance.展开更多
时间序列预测在能源管理、交通流量和气象分析等多个实际场景中具有重要应用价值。然而,时间序列数据中存在的分布漂移(Distribution Shift)与长程依赖(Long-term Dependency)仍限制了传统方法与现有深度学习模型在长期预测中的表现。为...时间序列预测在能源管理、交通流量和气象分析等多个实际场景中具有重要应用价值。然而,时间序列数据中存在的分布漂移(Distribution Shift)与长程依赖(Long-term Dependency)仍限制了传统方法与现有深度学习模型在长期预测中的表现。为此,提出了一种名为D-LINet(Dual-Normalization and Linear Integration Network)的创新模型。该模型结合了Dish-TS(Distribution Shift in Time Series Forecasting)框架的分布归一化能力与线性映射的高效性,并采用双向归一化与双线性层的设计,有效缓解输入与输出空间的分布偏移,增强了对周期性与趋势性特征的捕捉能力。在多个真实数据集上对D-LINet的预测性能进行了全面评估。结果显示,在短期与长期预测中,D-LINet的均方误差和平均绝对误差均显著优于主流模型(如Transformer,Informer,Autoformer和DLinear)。此外,实验还探讨了输入窗口长度及先验知识的引入对预测性能的影响,为后续模型优化提供了重要指导。该研究针对复杂分布漂移问题提出了新的解决思路,并有助于提升时间序列预测的精度与稳健性。展开更多
文摘Aim To present a simple and effective method for the design of nonlinear and time varying control system. Methods A new concept of dynamic equilibrium of a system and its stability were presented first. It was pointed out that what is controlled directly by the input of a control system is the system's dynamic equilibrium rather than the states. Based on it, a new feedback linearization method for nonlinear system based on the Lyapunov direct method was given. Simulation studies were also carried out. Results The example and simulation show that by use of the method, the controller design becomes very simple and the control effect is quite satisfying. Conclusion The new method unifies the stabilizing problem(regulating problem) with the tracking problem. It is a very simple and effective method for the design of nonlinear and time varying control system.
文摘This paper presents a flight control design for an unmanned aerial vehicle （UAV） using a nonlinear autoregressive moving average （NARMA-L2） neural network based feedback linearization and output redefinition technique. The UAV investigated is non- minimum phase. The output redefinition technique is used in such a way that the resulting system to be inverted is a minimum phase system. The NARMA-L2 neural network is trained off-line for forward dynamics of the UAV model with redefined output and is then inverted to force the real output to approximately track a command input. Simulation results show that the proposed approaches have good performance.
文摘时间序列预测在能源管理、交通流量和气象分析等多个实际场景中具有重要应用价值。然而,时间序列数据中存在的分布漂移(Distribution Shift)与长程依赖(Long-term Dependency)仍限制了传统方法与现有深度学习模型在长期预测中的表现。为此,提出了一种名为D-LINet(Dual-Normalization and Linear Integration Network)的创新模型。该模型结合了Dish-TS(Distribution Shift in Time Series Forecasting)框架的分布归一化能力与线性映射的高效性,并采用双向归一化与双线性层的设计,有效缓解输入与输出空间的分布偏移,增强了对周期性与趋势性特征的捕捉能力。在多个真实数据集上对D-LINet的预测性能进行了全面评估。结果显示,在短期与长期预测中,D-LINet的均方误差和平均绝对误差均显著优于主流模型(如Transformer,Informer,Autoformer和DLinear)。此外,实验还探讨了输入窗口长度及先验知识的引入对预测性能的影响,为后续模型优化提供了重要指导。该研究针对复杂分布漂移问题提出了新的解决思路,并有助于提升时间序列预测的精度与稳健性。
