|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | 一种改进的近似动态规划方法及其在SVC的应用显示文摘近似动态规划的基本思想是通过近似计算代价函数,从而避免动态规划中的'维数灾'问题。随机选取初值使得近似动态规划方法需要多次的学习才能最终收敛,极大地限制了在实际系统中的应用。针对上述问题,提出一种基于改进PID神经网络的直接启发式动态规划算法,将初始执行网络与PID控制器之间建立起一种等价关系,因此可以利用已经设计好的PID控制器来指导其初值选取,从而使算法收敛性大大提高。改进的神经网络与常规PID神经网络相比,结构简单且具有更好的扩展性,性能上具有更强的鲁棒性。对4机2区系统的静止无功补偿器附加阻尼控制进行仿真测试,仿真结果表明基于改进PID神经网络的直接启发式动态规划算法和初值选取方法的有效性,并且在部分状态反馈和延时两种情况下有着很好的控制效果。 | 孙健 刘锋 SI Jennie 郭文涛 梅生伟 | 2011 | 电机与控制学报2011，15，5： | 11 |
| 2 | Direct heuristic dynamic programming based on an improved PID neural network显示文摘在这份报纸,改进 PID 神经的网络(IPIDNN ) 结构被建议并且适用于批评家和直接启发式的动态编程(DHDP ) 的行动网络。作为在网上听说算法近似动态编程(自动数据处理) 之一, DHDP 表明了它的适用性到大状态和控制问题。理论上, DHDP 算法要求存取到完整的州的反馈以便获得答案到鸣钟者 optimality 方程。不幸地,在一个真实系统存取所有状态不总是是可能的。这份报纸由建议一种 IPIDNN 配置构造批评家和行动网络完成输出反馈控制建议一个解决方案。因为这结构能估计可测量的产量的积分和衍生物,更多的系统状态被利用,这样更好的控制性能被期望。与传统的 PIDNN 相比,这种配置灵活、容易膨胀。基于这结构,一个坡度为这基于 IPIDNN 的 DHDP 的体面的算法被介绍。集中问题在单个学习时间步以内并且为全部学习过程被处理。一些重要卓见被提供指导算法的实现。建议学习控制器被用于一个大车杆系统验证结构和算法的有效性。 | Jian SUN Feng LIU Jennie SI Shengwei MEI | 2012 | 控制理论与应用(英文版)2012，10，4： | 2 |
| 3 | Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-Critic Reinforcement Learning显示文摘We address a state-of-the-art reinforcement learning(RL)control approach to automatically configure robotic pros-thesis impedance parameters to enable end-to-end,continuous locomotion intended for transfemoral amputee subjects.Specifically,our actor-critic based RL provides tracking control of a robotic knee prosthesis to mimic the intact knee profile.This is a significant advance from our previous RL based automatic tuning of prosthesis control parameters which have centered on regulation control with a designer prescribed robotic knee profile as the target.In addition to presenting the tracking control algorithm based on direct heuristic dynamic programming(dHDP),we provide a control performance guarantee including the case of constrained inputs.We show that our proposed tracking control possesses several important properties,such as weight convergence of the learning networks,Bellman(sub)optimality of the cost-to-go value function and control input,and practical stability of the human-robot system.We further provide a systematic simulation of the proposed tracking control using a realistic human-robot system simulator,the OpenSim,to emulate how the dHDP enables level ground walking,walking on different terrains and at different paces.These results show that our proposed dHDP based tracking control is not only theoretically suitable,but also practically useful. | Ruofan Wu Zhikai Yao Jennie Si He(Helen)Huang | 2022 | IEEE/CAA Journal of Automatica Sinica2022，9，1： | 1 |
| 4 | Online learning control by association and reinforcement 显示文摘 | SI Jennie WANG Yutsung | 2001 | IEEE Transactions on Neural Networks2001，12，2： | 1 |
| 5 | Apache helicopter stabilization using neurodynamic programming显示文摘 | ENNS Russell SI Jennie | 2002 | AIAA Journal of Guidance Con- trol and Dynamics2002，25，1： | 1 |
| 6 | Helicopter trimming and tracking con- trol using direct neural dynamic programming显示文摘 | ENNS Russell SI Jennie | 2003 | IEEE Transac- tions on Neural Networks2003，14，4： | 1 |
| 7 | Direct heuristic dynamic programming for damping oscillations in a large power system 显示文摘 | LU Chao SI Jennie XIE Xiaorong | 2008 | IEEE Transactions on Systems Man and Cybernetics Part B: Cybernetics2008，38，4： | 1 |
| 8 | Per- formance evaluation of direct heuristic dynamic programming u- sing control-theoretic measures 显示文摘 | YANG Lei SI Jennie TSAKALIS Konstantinos S | 2009 | Journal of Intelligent and Ro- botic Systems : Theory and Applications2009，55，23： | 1 |
| 9 | On-line Learning Control by Association and Reinforcement显示文摘 | Si Jennie Wang Yu-Tsung | 2001 | IEEE Transactions on neural Networks2001，12，2： | 1 |
| 10 | On-Line Learning Control by Association and Reinforcement显示文摘 | Jennie Si Yu-Tsung Wang | 2001 | IEEE TRANSACTIONS ON NEURAL NETWORKS2001，12，2： | 1 |
| 11 | On-line learning by association and reinforcement显示文摘 | Jennie Si Wang Yutseng | 2001 | IEEE Transactions on Neural Networks2001，12，2： | 1 |
| 12 | On-Line Learning Control by Association and Reinforcement显示文摘 | Jennie Si Yu-Tsung Wang | 2001 | IEEE TRANSACTIONS ON NEURAL NETWORKS2001，12，2： | 1 |
| 13 | On-Line Learning Control by Association and Reinforcement显示文摘 | Jennie Si Yu-Tsung Wang | 2001 | IEEE TRANSACTIONS ON NEURAL NETWORKS2001，12，2： | 1 |
| 14 | On-Line Learning Control by Association and Reinforcement 显示文摘 | Jennie Si Yu-Tsung Wang | 2001 | IEEE TRANSACTIONS ON NEURAL NETWORKS2001，12，2： | 1 |
| 15 | Corporate Social Responsibility Reporting in China: An Overview and Comparison with Major Trends显示文摘 | Carlos Noronha Si Tou M. I. Cynthia Jenny J. Guan | 2012 | Corp. Soc. Responsib. Environ. Mgmt2012，，1： | 1 |
| 16 | Modeling and simulation of c-e deep bowl pulverizer显示文摘 | ZHOU Guian SI Jennie TAFT Cw | 2000 | IEEE Transactions on Energy Conversion2000，15，3： | 1 |
| 17 | Prediction of top-oil temperature for transformers using neural networks显示文摘 | Si Jennie | 2000 | IEEE Transactions on Power Delivery2000，15，4： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员