排序方式: 共有9条查询结果,搜索用时 15 毫秒
1
1.
2.
针对近水面机动情况下潜器的深度及纵倾控制问题提出一种不基于模型的非线性自适应控制策略。其中,一种称为模糊FCMAC的特殊神经网络被用于补偿潜器动态模型的非线性部分。基于李雅普诺夫原理而推导出的在线学习算法用于更新FCMAC的权值。仿真结果表明此控制策略能较好地适应潜器质量、航速及海浪变化,在较大的工况变化范围内保持良好的控制性能。 相似文献
3.
An improved learning algorithm for hyperball CMAC was presented. Only one parameter is needed to determine the learning rate, and the parameter can be obtained by a self-optimizing method. The convergence of the improved learning algorithm was proved. The simulation research shows that the learning speed and the learning accuracy are both improved. 相似文献
4.
,PART Ⅱ:CONTROLLER DESIGNTX@段培永@李成东@邵惠鹤IntroductionInrecentyears,NeuralNetworks(NNs)havefoundgrowingsuccessindiverseinindustrialc?.. 相似文献
5.
电动助力转向系统(EPS)已经成为世界汽车技术发展的研究热点,然而对EPS控制策略的研究大多仅限于传统的控制方式。比较了单纯PID控制和CMAC与PID复合控制下电动助力转向系统对各种输入信号的响应,证明复合控制对非线性信号有很强的跟踪能力,并且具有很好的抗干扰性。 相似文献
6.
本文通过分析CMAC神经网络的学习机制和连续搅拌反应釜的结构,提出了一种自动选择学习率的CMAC自学习控制方法。给出了自学习控制器的结构和算法。并以连续搅拌反应釜模型为对象进行了仿真研究。这种网络每次学习少量参数,算法简单。仿真结果表明所提出的控制器优于传统的PID控制器。 相似文献
7.
8.
提出了将CMAC网络与PD控制器相结合的机器人在线自学习控制器,通过引入高阶网络的概念,采用简单的叠加处理法将多维输入空间的CMAC神经网络化为多个一维输入子网络,从而简化系统的网络结构.同时对进行叠加的一维输入CMAC网络选取不同的学习步长,提高了学习的收敛速度和模型的逼近能力.计算机仿真结果表明,所提出的新型机器人自学习控制器具有很好的控制性能. 相似文献
9.
This work deals with the nonlinear control of a marine diesel engine by use of a robust intelligent control strategy based on cerebellar model articulation controller (CMAC). A mathematical model of diesel engine propulsion system is presented. In order to increase the accuracy of dynamical speed, the mathematical model of engagement process based on the law of energy conservation is proposed. Then, a robust cerebellar model articulation controller is proposed for uncertain nonlinear systems. The concept of active disturbance rejection control (ADRC) is adopted so that the proposed controller has more robustness against uncertainties. Finally, the proposed controller is applied to engine speed control system. Both the model of the diesel engine propulsion system and of the control law are validated by a virtual detailed simulation environment. The prediction capability of the model and the control efficiency are clearly shown. 相似文献
1