即时学习算法在非线性系统迭代学习控制中的应用

运用即时学习算法来解决一类非线性系统的迭代学习控制初值问题。对于任何类型的迭代学习控制算法，即时学习算法都能有效地估计初始控制量，减小了初始输出误差，加快了算法的收敛速度，使得经过有限次迭代后系统输出能严格跟踪理想信号。对机器人系统的仿真结果表明了该方法的有效性。     

非线性离散系统的迭代学习控制方法及其应用*

本文根据误差收敛准则，提出了非线性离散系统的迭代学习算法，给出了ＰＩＤ型学习控制的收敛条件，并证明了ＰＩＤ型学习控制对预定轨线的逼近特性，在交流变频电机起动过程控制中应用表明，使用本文方法可以得到实用的结果。     

一类未知非线性系统的智能迭代学习控制

从自适应的角度设计迭代学习控制，将神经网络引入迭代学习控制中。学习控制与自适应控制相结合，使得对网络权值的学习和跟踪控制同时进行，克服 了经典迭代学习控制的一些缺陷。基于Lyapunov直接方法，证明了整个控制系统的稳定并实现了任意精度的跟踪。实例仿真结果说明了算法 的有效性及其所具有的优点。     

改进狼群算法的交通子区迭代学习边界控制方法

针对基于固定增益迭代学习的交通子区边界控制方法收敛速度慢、迭代次数过多及控制精度差的问题。提出了一种迭代学习结合改进狼群算法的交通子区边界控制方案。该方案首先根据宏观基本图理论建立交通子区路网的车辆平衡方程，设计出系统的迭代学习控制律。其次分析了迭代学习控制对宏观基本图的影响，引入自适应步长的狼群算法，该算法以上一批次的宏观基本图为模型，离线对迭代学习控制器的比例和微分增益系数进行寻优，再将最优结果代入下一控制周期迭代学习控制中，进而改善收敛速度与精度。最后，对该方案的收敛性提供了数学证明，而仿真实验结果也表明该算法相较于具有固定增益的迭代学习控制器，收敛速度得到提升，对系统期望轨迹也具有较好的跟踪精度，具有较强的可行性与有效性。     

时滞间歇过程迭代学习控制算法研究

针对分批重复过程的模型和延迟具有不确定性，提出具有2自由PI—PD补偿结构的迭代学习控制（ILC）算法。该算法通过埘以前操作过程的迭代学习产生当前的辅助控制输入，从而改进控制质量。过程的动态特性用传递函数加纯滞后捕述，用频域法分析了算法的稳定性，并给出了鲁棒稳定界．仿真验证了算法的有效性。     

一种基于规则和学习算法设计的电力系统智能PID控制器

提出了一种基于规则和学习算法设计的电力系统智能ＰＩＤ控制器的设计方法。通过对固定参数电力系统ＰＩＤ控制器性能的研究，验证并获得了一些关于电力系统电压和稳定性控制协调与鲁棒性的结论。在此基础上，研制出一种智能ＰＩＤ控制器，它由基于规则的开关控制和基于学习控制的算法组成。在单机无穷大电力系统中应用的非线性仿真表明，这种智能ＰＩＤ控制器满足电力系统电压和稳定性协调控制的要求，且具有较强的鲁棒性。     

基于深度强化学习的城市交通信号控制算法

针对城市交通信号控制中如何有效利用相关信息优化交通控制并保证控制算法的适应性和鲁棒性的问题，提出一种基于深度强化学习的交通信号控制算法，利用深度学习网络构造一个智能体来控制整个区域交通。首先通过连续感知交通环境的状态来选择当前状态下可能的最优控制策略，环境的状态由位置矩阵和速度矩阵抽象表示，矩阵表示法有效地抽象出环境中的主要信息并减少了冗余信息；然后智能体以在有限时间内最大化车辆通行全局速度为目标，根据所选策略对交通环境的影响，利用强化学习算法不断修正其内部参数；最后，通过多次迭代，智能体学会如何有效地控制交通。在微观交通仿真软件Vissim中进行的实验表明，对比其他基于深度强化学习的算法，所提算法在全局平均速度、平均等待队长以及算法稳定性方面展现出更好的结果。其中，与基线相比，平均速度提高9%，平均等待队长降低约13.4%。实验结果证明该方法能够适应动态变化的复杂的交通环境。     

PD型模糊学习控制及其在可重复轨迹跟踪问题中的应用

针对可重复轨迹跟踪问题,提出了一种PD型模糊学习算法.该算法集成两种控 制:作为基础的PD型模糊逻辑算法和改善系统性能的学习算法.模糊学习控制在模糊控制 基础上引入迭代学习算法,使得模糊PD控制器可以精确地跟踪可重复轨迹以及消除周期性 扰动.本文在能量函数和泛函分析的基础上,通过严格的推导表明PD型模糊学习算法可达 到:1)系统跟踪误差一致收敛到零;2)学习控制序列几乎处处收敛到理想的控制信号.     

伺服系统的高斯基函数CMAC学习控制研究

在高精度伺服系统中，由于摩擦力及负载扰动等因素的影响，常规PID控制难以满足越来越高的控制精度、跟踪性能等指标要求。本文提出了基于商新基函数CMAS在线学习的控制方案，并给出了相应的学习算法。仿真结果表明．该方法不仅有较好的控制精度，而且具有学习速度快等优点。     

一类基于几何分析的迭代学习控制算法

基于几何分析，对迭代学习控制方法的几何框架进行探索．首先通过对Arimoto算法所构成的向量图进行几何分析，导出了一类新的迭代学习算法结构；然后从理论上对所导出的算法进行完整的收敛性分析．该算法结构与已有算法完全不同，但其收敛速度和精度明显提高．仿真结果表明了新算法的有效性和优越性．     

基于经验数据的学习控制在负载模拟器中的应用

本文针对以往单纯采用迭代学习控制引起的系统初始转矩冲击和收敛时间过长的问题,提出了一种新的基于经验数据的学习控制算法。指出影响系统输出的关键因素是舵机的转速。然后根据这个特点,应用迭代学习控制的经验,设计了一种简单的算法来确定迭代学习控制的初始输入量,再利用神经网络学习算法修正偏差。仿真结果表明基于经验数据的学习控制很好的解决了单纯采用迭代学习控制而引起的初始转矩冲击和收敛时间过长的问题。     

具有迭代初始误差的高相对度线性离散系统的迭代学习控制

本文针对具有迭代初始误差的高相对度线性多变量离散系统,提出了一种P型的迭代学习控制算法.通过将迭代学习控制系统的二维运动过程描述为一维的线性离散系统,证明了该迭代学习控制算法的收敛性及其收敛的充要条件.该迭代学习控制算法通过对系统前次重复运动过程中的输入和跟踪误差信号进行学习,来不断地调整输入量,使得系统在经过一定次数的学习以后,在初始时间点以外的实际输出趋于期望输出.数值仿真结果表明了所提出算法的有效性.     

非线性迭代学习控制问题的延拓修正牛顿法

对于非线性迭代学习控制问题,提出基于延拓法和修正Newton法的具有全局收敛性的迭代学习控制新方法.由于一般的Newton型迭代学习控制律都是局部收敛的,在实际应用中有很大局限性.为拓宽收敛范围,该方法将延拓法引入迭代学习控制问题,提出基于同伦延拓的新的Newton型迭代学习控制律,使得初始控制可以较为任意的选择.新的迭代学习控制算法将求解过程分成N个子问题,每个子问题由换列修正Newton法利用简单的递推公式解出.本文给出算法收敛的充分条件,证明了算法的全局收敛性.该算法对于非线性系统迭代学习控制具有全局收敛和计算简单的优点.     

Robust learning control for a class of nonlinear systems with periodic and aperiodic uncertainties

This paper addresses the robust learning control problem for a class of nonlinear systems with structured periodic and unstructured aperiodic uncertainties. A recursive technique is proposed which extends the backstepping idea to the robust repetitive learning control systems. A learning evaluation function instead of a Lyapunov function is formulated as a guideline for derivation of the control strategy which guarantees the asymptotic stability of the tracking system. A design example is given.     

Iterative learning control: A survey and new results

Learning control is an iterative approach to the problem of improving transient behavior for processes that are repetitive in nature. In this article, we present some results on iterative learning control. A complete review of the literature is given first. Then, a general formulation of the problem is given. Next, we present a complete analysis of the learning control problem for the case of linear, time-invariant plants and controllers. This analysis offers: (1) insight into the nature of the solution of the learning control problem by deriving sufficient convergence conditions; (2) an approach to learning control for linear systems based on parameter estimation; and (3) an analysis that shows that for finite-horizon problems it is possible to design a learning control algorithm that converges, with memory, in one step. Finally, a time-varying learning controller is given for controlling the trajectory of a nonlinear robot manipulator. A brief simulation example is presented to illustrate the effectiveness of this scheme.     

注塑机注射速度的模型预测迭代学习控制

针对注射过程具有重复运行和非线性的特性,在对预测控制与迭代学习控制进行综合应用并加以改进的基础上,给出一种模型预测迭代学习复合控制新算法,研究了控制器的设计方案.同时,将迭代学习思想引入到预测步长的在线调整,提出了预测步长的迭代学习方法.仿真结果表明,该方法是有效的,其控制性能优于PID迭代学习控制系统.     

Autonomous reconfiguration of robot shape by using Q-learning

A modular robot can be built with a shape and function that matches the working environment. We developed a four-arm modular robot system which can be configured in a planar structure. A learning mechanism is incorporated in each module constituting the robot. We aim to control the overall shape of the robot by an accumulation of the autonomous actions resulting from the individual learning functions. Considering that the overall shape of a modular robot depends on the learning conditions in each module, this control method can be treated as a dispersion control learning method. The learning object is cooperative motion between adjacent modules. The learning process proceeds based on Q-learning by trial and error. We confirmed the effectiveness of the proposed technique by computer simulation.     

Dynamically focused fuzzy learning control

A "learning system" possesses the capability to improve its performance over time by interacting with its environment. A learning control system is designed so that its "learning controller" has the ability to improve the performance of the closed-loop system by generating command inputs to the plant and utilizing feedback information from the plant. Learning controllers are often designed to mimic the manner in which a human in the control loop would learn how to control a system while it operates. Some characteristics of this human learning process may include: (i) a natural tendency for the human to focus their learning by paying particular attention to the current operating conditions of the system since these may be most relevant to determining how to enhance performance; (ii) after learning how to control the plant for some operating condition, if the operating conditions change, then the best way to control the system may have to be re-learned; and (iii) a human with a significant amount of experience at controlling the system in one operating region should not forget this experience if the operating condition changes. To mimic these types of human learning behavior, we introduce three strategies that can be used to dynamically focus a learning controller onto the current operating region of the system. We show how the subsequent "dynamically focused learning" (DFL) can be used to enhance the performance of the "fuzzy model reference learning controller" (FMRLC) and furthermore we perform comparative analysis with a conventional adaptive control technique. A magnetic ball suspension system is used throughout the paper to perform the comparative analyses, and to illustrate the concept of dynamically focused fuzzy learning control.     

A composite energy function-based learning control approach for nonlinear systems with time-varying parametric uncertainties

A new learning control approach is developed in this note to address a class of nonlinear systems with time-varying parametric uncertainties. The concept of composite energy function (CEF), which provides the system information along both time and learning repetition horizons, is introduced in the analysis of learning control. CEF consists of two parts. The first part is a standard Lyapunov function,. which is used to access system behavior along time horizon during each learning cycle. The second part is an L/sup 2/ norm of parametric learning errors which reflects the variation of the system status when the control system is updated on the basis of learning cycles. The proposed learning control algorithm achieves asymptotical convergence along a learning repetition horizon. At the same time, the boundedness and pointwise convergence of the tracking error along time horizon is guaranteed. The proposed learning control strategy is applicable to quite general classes of nonlinear systems without requiring the global Lipschitz continuity condition and zero relative degree condition.     

基于AOCA仿生学习模型的两轮机器人自主平衡学习研究

以两轮机器人的自主平衡学习控制为研究对象,针对传统控制方法无法实现机器人类似人或动物的渐进学习过程,依据斯金纳的操作条件反射理论建立了一种自治操作条件反射自动机（Autonomous operant conditioning automaton,AOCA）模型,设计一种基于AOCA的仿生学习算法,并进行机器人姿态平衡学习实验仿真研究. 实验结果表明,基于AOCA的仿生学习方法能有效地实现机器人的自主平衡学习控制,机器人系统的平衡能力在学习控制过程中自组织地渐进形成,并得以发展和完善.