Adaptive output feedback control for nonlinear time-delay systems using neural network

This paper extends the adaptive neural network （NN） control approaches to a class of unknown output feedback nonlinear time-delay systems. An adaptive output feedback NN tracking controller is designed by backstepping technique. NNs are used to approximate unknown functions dependent on time delay, Delay-dependent filters are introduced for state estimation. The domination method is used to deal with the smooth time-delay basis functions. The adaptive bounding technique is employed to estimate the upper bound of the NN approximation errors. Based on Lyapunov- Krasovskii functional, the semi-global uniform ultimate boundedness of all the signals in the closed-loop system is proved, The feasibility is investigated by two illustrative simulation examples.     

基于模糊神经网络的自适应控制系统的设计

自适应控制系统往往结合神经网络技术和模糊理论来实现规则节点和隶属度函数调整。但是这种系统的运行过程往往是顺序的,自适应过程慢。此外,在网络结构中往往存在冗余节点,加大了计算量,降低了控制反应速度。针对以上问题本文设计1个新的模糊神经网络控制系统(FNCC),FNCC在结构学习中引入了减少规则节点的操作,降低了由于过量计算所带来的时间滞后。同时,此系统的参数学习与网络结构学习同步进行,降低了由于顺序操作所带来的时间滞后。通过研究得出FNCC具有以下特点:(1)无需预知系统的模型,(2)无限制的结构设计。在研究中我们将此系统应用到一非线性系统上,通过仿真结果来验证FNNC的可行性和准确性。     

基于神经网络的解耦控制方法

本文介绍了BP算法的基本原理及其实现步骤,并将BP算法应用于神经网络解耦器和PID神经网络的训练中,即本文中各个神经网络的训练算法均采用BP算法,提出了一种神经网络在线解耦控制算法,即将神经网络解耦和神经网络PID控制两者结合,对系统进行解耦控制。将解耦与控制结合,既避免了单独采用自适应PID控制时控制效果不佳的问题,又避免了单独采用解耦时原有控制器不能适应变化后的对象问题。最后对一组双输入双输出耦合系统进行了仿真研究。     

Optimal control of a nonlinear fed-batch fermentation process using model predictive approach

Bioprocesses are involved in producing different pharmaceutical products. Complicated dynamics, nonlinearity and non-stationarity make controlling them a very delicate task. The main control goal is to get a pure product with a high concentration, which commonly is achieved by regulating temperature or pH at certain levels. This paper discusses model predictive control (MPC) based on a detailed unstructured model for penicillin production in a fed-batch fermentor. The novel approach used here is to use the inverse of penicillin concentration as a cost function instead of a common quadratic regulating one in an optimization block. The result of applying the obtained controller has been displayed and compared with the results of an auto-tuned PID controller used in previous works. Moreover, to avoid high computational cost, the nonlinear model is substituted with neuro-fuzzy piecewise linear models obtained from a method called locally linear model tree (LoLiMoT).     

Adaptive motion control using neural network approximations

In this paper, we present a new adaptive technique for tracking control of mechanical systems in the presence of friction and periodic disturbances. Radial Basis Functions (RBFs) are used to compensate for the effects of nonlinearly occurring parameters in the friction and periodic disturbance model. Theoretical analysis, such as stability and transient performance, is provided. Furthermore, the performance of the adaptive RBF controller and its non-adaptive counterpart are compared.     

Remarks on tracking method of neural network weight change for adaptive type neural network feedforward feedback controller

A cost function is useful for a confirmation of neural network controller learning performance, but, this confirmation may not be correct for neural networks. Previous papers proposed a tracking method of neural network weight change and simulated it on the application of both learning and adaptive type neural network direct controllers. This paper applies the tracking method to an adaptive type neural network feedforward feedback controller and simulates it. The simulation results confirm that a track of the neural network weight change is separated into two trajectories. They also discuss the relationship between the feedback gain of the feedback controller and the parameter determining the neural network learning speed. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Constrained multi-variable generalized predictive control using a dual neural network

Multi-variable generalized predictive control algorithm has obtained great success in process industries. However, it suffers from a high computational cost because the multi-stage optimization approach in the algorithm is time-consuming when constraints of the control system are considered. In this paper, a dual neural network is employed to deal with the multi-stage optimization problem, and bounded constraints on the input and output signals of the control system are taken into account. The dual neural network has many favorable features such as simple structure, rapid execution, and easy implementation. Therefore, the computation efficiency, in comparison with the consecutive executions of numerical algorithms on digital computers, is increased dramatically. In addition, the dual network model can yield the exact optimum values of future control signals while many other neural networks only obtain the approximate optimal solutions. Hence the multi-variable generalized predictive control algorithm based on the dual neural network is suitable for industrial applications with the real-time computation requirement. Simulation examples are given to demonstrate the efficiency of the proposed approach.     

电液位置伺服系统的多滑模神经网络控制

针对电液位置伺服系统存在的强非线性、控制增益未知和非匹配不确定性.通过引入神经网络和带饱和层的多滑模面,提出了一种多滑模神经网络控制方法.该方法运用神经网络的万能逼近特性和滑模控制优良的抗干扰特点,采用构造性方法设计控制器.运用光滑投影算法和积分李雅普诺夫技术,避免了参数漂移和控制器奇异问题.理论证明了系统跟踪误差收敛于任意设定的滑模面饱和层内.仿真实验表明了理论结果的有效性.     

Application of an expert system using neural network to control the coagulant dosing in water treatment plant

The coagulation process is one of the most important stages in water treatment plant, which involves many complex physical and chemical phenomena. Moreover, coagulant dosing rate is non-linearly correlated to raw water characteristics such as turbidity, conductivity, PH, temperature, etc. As such, coagulation reaction is hard or even impossible to control satisfactorily by conventional methods. Based on neural network and rule models, an expert system for determining the optimum chemical dosage rate is developed and used in a water treatment work, and the results of actual runs show that in the condition of satisfying the demand of drinking water quality, the usage of coagulant is lowered.     

Discrete-time neural network output feedback control of nonlinear discrete-time systems in non-strict form

An adaptive neural network (NN)-based output feedback controller is proposed to deliver a desired tracking performance for a class of discrete-time nonlinear systems, which are represented in non-strict feedback form. The NN backstepping approach is utilized to design the adaptive output feedback controller consisting of: (1) an NN observer to estimate the system states and (2) two NNs to generate the virtual and actual control inputs, respectively. The non-causal problem encountered during the control design is overcome by using a dynamic NN which is constructed through a feedforward NN with a novel weight tuning law. The separation principle is relaxed, persistency of excitation condition (PE) is not needed and certainty equivalence principle is not used. The uniformly ultimate boundedness (UUB) of the closed-loop tracking error, the state estimation errors and the NN weight estimates is demonstrated. Though the proposed work is applicable for second order nonlinear discrete-time systems expressed in non-strict feedback form, the proposed controller design can be easily extendable to an nth order nonlinear discrete-time system.     

Multivariable predictive control of a pressurized tank using neural networks

The behavior of a multivariable predictive control scheme based on neural networks applied to a model of a nonlinear multivariable real process, consisting of a pressurized tank is investigated in this paper. The neural scheme consists of three neural networks; the first is meant for the identification of plant parameters (identifier), the second one is for the prediction of future control errors (predictor) and the third one, based on the two previous, compute the control input to be applied to the plant (controller). The weights of the neural networks are updated on-line, using standard and dynamic backpropagation. The model of the nonlinear process is driven to an operation point and it is then controlled with the proposed neural control scheme, analyzing the maximum range over the neural control works properly.     

Consensus-based distributed cooperative learning control for a group of discrete-time nonlinear multi-agent systems using neural networks

This paper focuses on the cooperative learning capability of radial basis function neural networks in adaptive neural controllers for a group of uncertain discrete-time nonlinear systems where system structures are identical but reference signals are different. By constructing an interconnection topology among learning laws of NN weights in order to share their learned knowledge on-line, a novel adaptive NN control scheme, called distributed cooperative learning control scheme, is proposed. It is guaranteed that if the interconnection topology is undirected and connected, all closed-loop signals are uniform ultimate bounded and tracking errors of all systems can converge to a small neighborhood around the origin. Moreover, it is proved that all estimated NN weights converge to a small neighborhood of their common optimal value along the union of all state trajectories, which means that the estimated NN weights reach consensus with a small consensus error. Thus, all learned NN models have the better generalization capability than ones obtained by the deterministic learning method. The learned knowledge is also adopted to control a class of uncertain systems with the same structure but different reference signals. Finally, a simulation example is provided to verify the effectiveness and advantages of the distributed cooperative learning control scheme developed in this paper.     

A self-evolving functional-linked wavelet neural network for control applications

The structure of a neural network is determined by time-consuming trial-and-error tuning procedure in advance for the reason that it is difficult to consider the balance between the neuron number and the desired performance. To attack this problem, a self-evolving functional-linked wavelet neural network (SFWNN) is proposed. Without the need for preliminary knowledge, a self-evolving approach demonstrates that the properties of generating and pruning the hidden neurons automatically. Then, an adaptive self-evolving functional-linked wavelet neural control (ASFWNC) system which is composed of a neural controller and a supervisory compensator is proposed. The neural controller uses a SFWNN to online estimate an ideal controller and the supervisory compensator is designed to eliminate the effect of the approximation error introduced by the neural controller upon the system stability in the Lyapunov sense. To investigate the capabilities of the proposed ASFWNC approach, it is applied to a chaotic system and a DC motor. The simulation and experimental results show that favorable control performance can be achieved by the proposed ASFWNC scheme.     

活套系统的神经网络离散变结构控制

针对带钢热连轧中活套系统的解耦控制问题,提出了神经网络交结构多变量解耦控制方法.通过将活套高 度和张力复合控制系统看成高度和张力两个独立的控制系统,将二者的耦合关系当作扰动来处理,根据全阶滑模交 结构控制理论,分别对这两个系统设计控制器.利用两个径向基神经网络来保证滑态可达条件的满足.最后用 Matlab对活套多变量耦合控制系统进行仿真研究,结果表明解耦后的活套控制系统可获得更好的控制效果.     

Nonlinear model predictive control of fed-batch fermentations using dynamic flux balance models

Fed-batch fermentation is an important production technology in the biochemical industry. Using fed-batch Saccharomyces cerevisiae fermentation as a prototypical example, we developed a general methodology for nonlinear model predictive control of fed-batch bioreactors described by dynamic flux balance models. The control objective was to maximize ethanol production at a fixed final batch time by adjusting the glucose feeding rate and the aerobic–anaerobic switching time. Effectiveness of the closed-loop implementation was evaluated by comparing the relative performance of NMPC and the open-loop optimal controller. NMPC was able to compensate for structural errors in the intracellular model and parametric errors in the substrate uptake kinetics and cellular energetics by increasing ethanol production between 8.0% and 14.7% compared with the open-loop operating policy. Minimal degradation in NMPC performance was observed when the biomass, glucose, and ethanol concentration and liquid volume measurements were corrupted with Gaussian white noise. NMPC based on the dynamic flux balance model was shown to improve ethanol production compared to the same NMPC formulation based on a simpler unstructured model. To our knowledge, this study represents the first attempt to utilize a dynamic flux balance model within a nonlinear model-based control scheme.     

非线性仿射控制系统的C0镇定性

通过Lyapunov函数设计反馈控制器使得非线性仿射控制系统全局渐进稳定是一种有效的方法．为了使得反馈控制器具有连续性,Sontag提出控制Lyapunov函数应具有小控制性,即要求在原点连续反馈控制器存在,该条件在实际中无法应用．针对这一问题本文提出了聚点条件来保证反馈控制器具有连续性,该条件直接对选择的控制Lyapunov函数进行检验,并且聚点条件还是必要的;文章将控制Lyapunov函数的严格不等式放宽为非严格的不等式,提出非严格控制Lyapunov函数,利用LaSalle定理得到：采用满足聚点条件的非严格控制Lyapunov函数来设计连续反馈控制器,非线性仿射控制系统是全局渐进稳定,扩大了控制Lyapunov函数的寻找范围：最后通过对一种带摩擦的弹簧系统进行验证．     

基于神经网络的火电机组负荷预见控制方法及其仿真研究

利用多个自适应神经元构造了火电单元机组负荷预见控制系统，研究了用神经网络实现多变量系统的预见协调控制，神经网络输入量应该怎样选取。仿真结果证明了这种控制方案的正确性。与原有的负荷最优预见控制方法相比，该方法不依赖于对象的精确模型，也不涉及权重矩阵的选取。     

全局稳定的分散自适应神经网络反推跟踪控制

针对一类不确定大规模系统,研究其全局稳定的分散自适应神经网络反推跟踪控制问题.在假设不匹配的未知关联项满足部分已知的非线性Lipschitz条件下,采用神经网络作为前馈补偿器,逼近参考信号作为输入的未知关联函数;设计者可根据参考信号的界预先确定神经网络逼近域,同时保证了闭环系统的全局稳定性.仿真实例验证了控制算法的有效性.     

Integration of feedforward neural network and finite element in the draw-bend springback prediction

To achieve accurate results, current nonlinear elastic recovery applications of finite element (FE) analysis have become more complicated for sheet metal springback prediction. In this paper, an alternative modelling method able to facilitate nonlinear recovery was developed for springback prediction. The nonlinear elastic recovery was processed using back-propagation networks in an artificial neural network (ANN). This approach is able to perform pattern recognition and create direct mapping of the elastically-driven change after plastic deformation. The FE program for the sheet metal springback experiment was carried out with the integration of ANN. The results obtained at the end of the FE analyses were found to have improved in comparison to the measured data.     

A modified Smith predictive scheme based back-propagation neural network approach for FOPDT processes control

In this paper, a novel control scheme to deal with process uncertainties in the form of disturbance loads and modelling errors, as well as time-varying process parameters is proposed by applying the back-propagation neural network (BPNN) approach. A BPNN predictive controller that replaces the entire Smith predictor structure is initially trained offline. Lyapunov direct method is used to prove that the convergence of this BPNN is guaranteed by selecting a suitable learning rate during the learning process. However, the Smith predictor based BPNN control is an off-line training based algorithm, which is a time consuming method and requires a known process plant input from the controller. A desired control input to the process is difficult to obtain for the training of the network. As a result a group of proper training data (target control inputs and outputs) can hardly be provided. In order to overcome this problem, a BPNN with an on-line training algorithm is introduced for the control of a First Order plus Dead Time (FOPDT) process. The stability analysis is carried out using the Lyapunov criterion to demonstrate the network convergence ability. Simulation results show that this proposed online trained neural Smith predictor based controller provides excellent robustness to process modelling errors and disturbance loads, and high adaptability to time varying processes parameters.