Real-time multi-step prediction control for BP network with delay

Real time multi step prediction of BP network based on dynamical compensation of system characteristics is suggested by introducing the first and second derivatives of the system and network outputs into the network input layer, and real time multi step prediction control is proposed for the BP network with delay on the basis of the results of real time multi step prediction, to achieve the simulation of real time fuzzy control of the delayed time system.

Nonlinear Decoupling PID Control Using Neural Networks and Multiple Models

For a class of complex industrial processes with strong nonlinearity, serious coupling and uncertainty, a nonlinear decoupling proportional-integral-differential （PID） controller is proposed, which consists of a traditional PID controller, a decoupling compensator and a feedforward compensator for the unmodeled dynamics. The parameters of such controller is selected based on the generalized minimum variance control law. The unmodeled dynamics is estimated and compensated by neural networks, a switching mechanism is introduced to improve tracking performance, then a nonlinear decoupling PID control algorithm is proposed. All signals in such switching system are globally bounded and the tracking error is convergent. Simulations show effectiveness of the algorithm.

Study on Adaptive Control with Neural Network Compensation

A scheme of adaptive control based on a recurrent neural network with a neural network compensation is presented for a class of nonlinear systems with a nonlinear prefix. The recurrent neural network is used to identify the unknown nonlinear part and compensate the difference between the real output and the identified model output. The identified model of the controlled object consists of a linear model and the neural network. The generalized minimum variance control method is used to identify parameters, which can deal with the problem of adaptive control of systems with unknown nonlinear part, which can not be controlled by traditional methods. Simulation results show that this algorithm has higher precision, faster convergent speed.

Design of a Networked Tracking Control System With a Data-based Approach

Tracking control is a very challenging problem in the networked control system(NCS), especially for the process with blurred mechanism and where only input-output data are available. This paper has proposed a data-based design approach for the networked tracking control system(NTCS). The method utilizes the input-output data of the controlled process to establish a predictive model with the help of fuzzy cluster modelling(FCM)technology. Then, the deduced error and error change in the future are treated as inputs of a fuzzy sliding mode controller(FSMC) to obtain a string of future control actions. These candidate control actions in the controller side are delivered to the plant side. Thus, the network induced time delays are compensated by selecting appropriate control action. Simulation outputs prove the validity of the proposed method.

具有随机通讯延迟和噪声干扰的网络系统控制

针对网络控制系统中普遍存在的通讯延迟问题 ,在有动态噪声及测量噪声存在的情况下 ,提出一种延迟补偿器结构 ,实现了对随机通讯延迟的补偿和对信号的最小方差预测。分析了闭环系统的稳定性 ,并给出实验结果 ,证实了所提出理论的正确性。

一类非线性不确定系统的最小方差神经控制

针对一类非线性不确定系统 ,提出一种新的基于神经网络动态补偿的最小方差控制方法(MVNNC)。这种控制系统将传统的最小方差控制技术与神经网络优良的非线性逼近能力相结合 ,从而能有效地消除不确定性引起的控制误差。仿真实验表明 。

基于神经网络的一类非线性系统的自适应控制

基于递归神经网络给出了仅含一个非线性环节的一类非线性系统的自适应控制方案。该方案采用递归神经网络辨识非线性系统中的未知非线性环节。沿用广义最小方差自校正控制方法，可以解决非线性环节未知和工作点变化时传统方法无法控制的自适应控制问题。理论分析和仿真结果表明，该方法具有很好的控制效果。

基于变神经网络的非线性最小方差预测控制器

提出基于变神经网络学习动态系统参数的最小方差预测控制器。其目的是通过在线学习 ,使控制器(MVPC)能适应被控对象参数变化和非确定性。提出的变神经网络由两部分组成 ,一部分是线性神经网络 (LNN) ,作为被控对象局部线性动态模型 ,另一部分是多层交叉回归神经网络 (DRNN) ,它近似为非线性动态模型。由于引进递推最小方差算法 ,本控制器运算速度相当快。

带神经网络补偿的极点配置广义最小方差自校正控制

首先用一个常规线性模型对被控对象进行辨识，再对线性模型辨识的余差用一个神经网络进行补偿．线性模型和神经网络共同构成对象的辨识模型，并基于这一模型提出了一种显式极点配置广义最小方差自校正控制．该方法适用于非线性对象，且具有较高精度和较快的收敛速度，具有较强的鲁棒性．

网络化制造环境下离散供应链系统预测控制策略

针对离散供应链系统中客户需求的高度不确定性,提出最小方差控制方法。该方法相对于传统的预测控制策略,更适合于追踪需求变化,减少或消除"牛鞭效应"。首先,将具有z变换的各单元传递函数整合成一个闭环传递函数,以此为整个供应链网络建模,采用自回归移动平均模型描述客户需求趋势,并通过客户需求预测确定两种库存目标水平。其次,建立基于订单策略的目标函数,利用最小方差预测器处理客户需求,提出了供应链的性能指标函数和"牛鞭效应"的分析方程,并通过设定最小方差控制器参数调节超额库存和未交付订货。最后,仿真结果表明最小方差控制在预测市场变化、追踪客户动态需求和保持合理库存水平上是可行和有效的。

基于分布式电网中DVR的补偿控制策略研究

针对动态电压恢复器DVR(Dynamic Voltage Restorer)在分布式电网中进行电压暂降补偿时出现的延时和控制不稳定等问题,提出一种无串联变压器型DVR的预测电压控制策略,该方法在不需要线性控制器或调制技术下,通过DVR跟踪参考电压有效预测控制,保持负载电压在各种扰动下稳定输出正弦电压值。在DVR补偿控制策略方面,采用最小有功功率补偿控制策略,该方法更为有效地延长DVR补偿时间,降低DVR输出的有功功率,仿真与实验结果验证了所提方法的可行性。

改进广义预测算法的NCS时延补偿

针对传统广义预测控制算法在以太网网络控制系统中存在的计算量大、系统复杂、实时性不足等缺点,文中采用了一种基于最小方差控制的广义预测控制算法,避免了Diophantine方程的求解,减少了计算时间,保证了网络控制系统的实时性。实验仿真表明,改进的广义预测控制算法能够很好地补偿时延对系统性能的影响,提高了系统的控制精度。

有线/无线网络中最小方差拥塞控制算法

为了满足流媒体等新型应用对网络服务质量的需求,该文提出了基于最小方差理论的网络拥塞控制算法。针对有线/无线网络特性,利用平衡点线性化方法将拥塞控制模型转换为离散传递函数,并考虑系统噪声和随机性的影响,将广义最小方差控制理论引入有线/无线网络的拥塞控制中,设计了基于最小方差的网络拥塞控制算法。仿真实验表明,在变化网络环境下,所设计的网络拥塞控制算法是有效和鲁棒的,能够维持期望的队列长度,有效抑制队列长度波动和延时的影响,提高有线/无线网络服务质量。

一种改进的GPC算法在网络控制系统中的应用

首先对传统的GPC算法进行理论推导和分析,然后针对传统GPC控制算法在大延迟过程中无法快速跟随参考轨迹的问题,提出了一种基于最小方差控制的广义预测控制,并以网络控制系统为控制对象,用MATLAB对其进行仿真分析,结果表明改进的广义预测控制算法能很好地跟踪系统轨迹,获得了良好的效果。

Analysis of the Most Likely Regions of Stability of an NCS and Design of the Corresponding Event-driven Controller

In this paper, some issues related to design and analysis of real networked control systems （NCS） under the focus of the most likely region of stability are addressed. Such a system is cumbersome due to its inherent variable time delays, ranging from microseconds to hours. To show the influence of such huge variations in the control performance, a laboratory-scale luminosity system has been setup using the Internet as part of the control loop with dominant time constant in the order of milliseconds. Proportional and integral （PI） control strategies with and without explicit compensation for the time-delay variations were implemented using an event-driven controller. Using the well-known Monte Carlo method and subsequent analyses of time responses, it has been possible to identify the most likely region of stability. Some experimental results show the influence of the statistical parameters of the delays on the determination of the most likely regions of stability of the NCS and how these can be used in assessment and redesign of the control system. The experiments show that much larger delays than one sample period can be supported by real NCSs without becoming unstable.