基于阻尼最小二乘法的神经网络预测偏差补偿自校正控制器

本文提出一种神经网络预测偏差补偿自校正控 制器,用线性模型的预测控制去控制非线性系统,其预测偏差用神经网络进行补偿．线性模 型的辨识和神经网络的学习均采用阻尼最小二乘法．仿真结果表明,用这种控制器能有效地 控制非线性系统,并具有超调小,鲁棒性好的特点．     

Neural network based model predictive control for a steel pickling process

A multi-layer feedforward neural network model based predictive control scheme is developed for a multivariable nonlinear steel pickling process in this paper. In the acid baths three variables under controlled are the hydrochloric acid concentrations. The baths exhibit the normal features of an industrial system such as nonlinear dynamics and multi-effects among variables. In the modeling, multiple input, single-output recurrent neural network subsystem models are developed using input–output data sets obtaining from mathematical model simulation. The Levenberg–Marquardt algorithm is used to train the process models. In the control (MPC) algorithm, the feedforward neural network models are used to predict the state variables over a prediction horizon within the model predictive control algorithm for searching the optimal control actions via sequential quadratic programming. The proposed algorithm is tested for control of a steel pickling process in several cases in simulation such as for set point tracking, disturbance, model mismatch and presence of noise. The results for the neural network model predictive control (NNMPC) overall show better performance in the control of the system over the conventional PI controller in all cases.     

Predictive LPV control of a liquid–gas separation process

The problem of controlling a liquid–gas separation process is approached by using LPV control techniques. An LPV model is derived from a nonlinear model of the process using differential inclusion techniques. Once an LPV model is available, an LPV controller can be synthesized. The authors present a predictive LPV controller based on the GPC controller [Clarke D, Mohtadi C, Tuffs P. Generalized predictive control – Part I. Automatica 1987;23(2):137–48; Clarke D, Mohtadi C, Tuffs P. Generalized predictive control – Part II. Extensions and interpretations. Automatica 1987;23(2):149–60]. The resulting controller is denoted as GPC–LPV. This one shows the same structure as a general LPV controller [El Gahoui L, Scorletti G. Control of rational systems using linear-fractional representations and linear matrix inequalities. Automatica 1996;32(9):1273–84; Scorletti G, El Ghaoui L. Improved LMI conditions for gain scheduling and related control problems. International Journal of Robust Nonlinear Control 1998;8:845–77; Apkarian P, Tuan HD. Parametrized LMIs in control theory. In: Proceedings of the 37th IEEE conference on decision and control; 1998. p. 152–7; Scherer CW. LPV control and full block multipliers. Automatica 2001;37:361–75], which presents a linear fractional dependence on the process signal measurements. Therefore, this controller has the ability of modifying its dynamics depending on measurements leading to a possibly nonlinear controller. That controller is designed in two steps. First, for a given steady state point is obtained a linear GPC using a linear local model of the nonlinear system around that operating point. And second, using bilinear and linear matrix inequalities (BMIs/LMIs) the remaining matrices of GPC–LPV are selected in order to achieve some closed loop properties: stability in some operation zone, norm bounding of some input/output channels, maximum settling time, maximum overshoot, etc., given some LPV model for the nonlinear system. As an application, a GPC–LPV is designed for the derived LPV model of the liquid–gas separation process. This methodology can be applied to any nonlinear system which can be embedded in an LPV system using differential inclusion techniques.     

神经网络非线性多步预测逆控制方法研究*

提出了基于多步预测控制方法的多变量非线性神经网络逆控制方案。利用预测模型对系统动态特性进行预测,使用一个带有时延因子的前馈神经网络作为控制器,利用多步预测性能指标对其在线训练,实现神经网络逆系统;在多步预测过程中还对每一步的预测误差进行预测,以实现预测误差补偿。将所提出的控制算法用于锅炉这种大滞后非线性对象的控制,仿真实验证明,该控制策略具有良好的解耦和动态跟踪性能。     

非线性系统神经网络预测控制研究进展

摘 要：神经网络由于其在非线性系统建模与优化求解方面的优势,被广泛应用于预测控制中,形成了各种各样的神经网络预测控制算法。本文系统地评述了非线性系统神经网络预测控制系统中的模型选取、控制器优化、控制系统结构设计方法以及收敛性理论等研究现状,分析了非线性系统神经网络预测控制算法存在的问题和今后的研究方向。     

基于神经网络Smith预估器的预测控制

针对非线性系统时滞问题,给出了一种新型的单神经元Smith预测控制算法.神经网络的预测控制器由不完全微分的单神经元自适应PID控制器和神经网络的Smith预估器组成.预估器对输出进行多步预测,控制器超前动作以消除时滞对系统的影响.不完全微分的单神经元自适应PID控制器通过改进的Hebb学习规则实现其权值调节,通过权系数的在线调整实现自适应控制.仿真实验证明了该方法具有较快的响应速度和较好的响应性能.     

Nonlinear model predictive control for the ALSTOM gasifier

In this work a nonlinear model predictive control based on Wiener model has been developed and used to control the ALSTOM gasifier. The 0% load condition was identified as the most difficult case to control among three operating conditions. A linear model of the plant at 0% load is adopted as a base model for prediction. A nonlinear static gain represented by a feedforward neural network was identified for a particular output channel—namely, fuel gas pressure, to compensate its strong nonlinear behaviour observed in open-loop simulations. By linearising the neural network at each sampling time, the static nonlinear model provides certain adaptation to the linear base model at all other load conditions. The resulting controller showed noticeable performance improvement when compared with pure linear model based predictive control.     

基于混沌优化的非线性预测控制器

针对非线性系统的控制问题,本文将神经网络辨识、混沌优化和预测控制思想有机结合,提出了一种新型非线性预测控制器.该控制器以神经网络作为预测模型,混沌优化算法作为滚动优化策略,避免了非线性预测控制中复杂的梯度计算和矩阵求逆问题.另外在训练神经网络过程中,采用了带混沌机制的自适应学习率的BP算法,以提高神经网络的收敛能力和收敛速度.仿真研究说明了该非线性预测控制器的有效性及实时性.     

Predictive neuro-control of uncertain systems: design and use of a neuro-optimizer

We consider the problem of predictive control of uncertain stochastic discrete I/O systems. Given a model identification procedure able to give accurate output system estimates, e.g. a neural network approximation, we use another feedforward neural network to generate at each time step a constrained optimal control. Dynamic backpropagation is used to improve when necessary the controller network parameters. Both system and controller neural structures are first selected off-line by a statistical Bayesian procedure in order to make the predictive control minimizing process more efficient. The issue of stochastic stability of the closed-loop is considered. We developed this approach for the tracking control of such uncertain systems as biotechnological processes. Actual and simulated predictive neuro-control case studies in this field of application are proposed as illustrations. A comparison with a more classic quasi-Newton-based approach is also proposed, showing the interest of this neuro-control approach.     

动态定量称重系统神经网络预测PID控制器研究

采用神经网络预测与PID控制理论相结合,为动态定量称重系统设计了一种神经网络预测PID控制器。该控制器算法简单,通过自学习、记忆功能在线调整PID控制参数KP、Kl、KD。建立了动态定量称重系统的仿真模型,将神经网络预测的PID控制与常规PID进行对比分析,神经网络预测PID控制器具有很好的控制效果。     

机械压力机滑块位置的神经网络控制

分析了机械压力机的滑块在行程的任意位置停止的必要性，在此基础上，论 述了使滑块一次准确停止到位的科学性并建立了相应新型压力机滑块行程的计算机控制系统．明确指出应对滑块停止位置进行神经网络补偿控制，并解决了实施神经网络控制的关键技术问题．通过在JH23-63型机械压力机上的大量试验，验证了该控制方法的有效性．     

Design and performance of an intelligent predictive controller for a six-degree-of-freedom robot using the Elman network

The aim of this paper was to propose a recurrent neural network-based predictive controller for robotic manipulators. A neural network controller for a six-joint Stanford robotic manipulator was designed using the generalized predictive control (GPC) and the Elman network. The GPC algorithm, which is a class of digital control method, requires long computational time. This is a disadvantage in real-time robot control; therefore, the Elman network controller was designed to reduce processing time by avoiding the highly mathematical and computational complexity of the GPC. The main reason for choosing the Elman network, amongst several neural network algorithms, was that the presence of feedback loops have a profound impact on the learning capability of the network. The designed neural network controller was able to recover quickly because of its significant generalization capability, which allowed it to adapt very rapidly to changes in inputs. The performance of the controller was also shown graphically using simulation software, including the dynamics and kinematics of the robot model.     

Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation

In this paper, a continuous time recurrent neural network (CTRNN) is developed to be used in nonlinear model predictive control (NMPC) context. The neural network represented in a general nonlinear state-space form is used to predict the future dynamic behavior of the nonlinear process in real time. An efficient training algorithm for the proposed network is developed using automatic differentiation (AD) techniques. By automatically generating Taylor coefficients, the algorithm not only solves the differentiation equations of the network but also produces the sensitivity for the training problem. The same approach is also used to solve the online optimization problem in the predictive controller. The proposed neural network and the nonlinear predictive controller were tested on an evaporation case study. A good model fitting for the nonlinear plant is obtained using the new method. A comparison with other approaches shows that the new algorithm can considerably reduce network training time and improve solution accuracy. The CTRNN trained is used as an internal model in a predictive controller and results in good performance under different operating conditions.     

Combustion timing control of HCCI engine based on NNPC and Elman-NN model under complex conditions

Homogeneous Charge Compression Ignition (HCCI) combines the characteristics of gasoline engine and diesel engine with high thermal efficiency and low emissions. However, since there is no direct initiator of combustion, it is difficult to control the combustion timing in HCCI engines under complex working conditions. In this paper, Neural Network Predictive Control (NNPC) for combustion timing of the HCCI engine is designed and implemented. First, the black box model based on Elman neural network is designed and developed to estimate the combustion timing. The fuel equivalence ratio, intake valve closing timing, intake manifold temperature, intake manifold gas pressure, and engine speed are chosen as the system inputs. Then, a NNPC controller is designed to control combustion timing by controlling the intake valve closing timing. Simulation results show that the Elman neural network black box model is capable of estimating the HCCI engine combustion timing. In addition, regardless of whether the HCCI engine is in constant or complex condition, the designed NNPC controller is capable of keeping the combustion timing within the ideal range. In particular, under New European Driving Cycle (NEDC) working conditions, the maximum overshoot of the controller is 28.95% and the average error is 1.03 crank angle degree. It is concluded that the controller has good adaptability and robustness.     

瓦斯突出模型预测控制的应用研究

煤体瓦斯涌出量的动态变化是一个复杂的非线性系统,传统的瓦斯监测方法准确率较低。针对该问题,文章提出了一种基于BP人工神经网络模型的瓦斯突出危险性预测控制方法。该方法运用BP人工神经网络预测模型对输入的多组样本进行训练学习、建立预测准则,并以此辨识瓦斯突出危险性类型。仿真结果表明,该方法有效解决了传统的瓦斯突出预测模型在事故预测中误差大、稳定性差的缺陷,提高了预测精度。     

Identification and predictive control of a multistage evaporator

A recurrent neural network-based nonlinear model predictive control (NMPC) scheme in parallel with PI control loops is developed for a simulation model of an industrial-scale five-stage evaporator. Input–output data from system identification experiments are used in training the network using the Levenberg–Marquardt algorithm with automatic differentiation. The same optimization algorithm is used in predictive control of the plant. The scheme is tested with set-point tracking and disturbance rejection problems on the plant while control performance is compared with that of PI controllers, a simplified mechanistic model-based NMPC developed in previous work and a linear model predictive controller (LMPC). Results show significant improvements in control performance by the new parallel NMPC–PI control scheme.     

非线性预测控制在塞棒伺服系统中的应用

由于连铸机塞棒位置伺服系统中存在着伺服阀流量非线性、液压缸阀芯摩擦非线性等因素,造成了伺服精度的降低。为改善控制质量,首先建立了含非线性因素的塞棒位置伺服系统模型,然后引入非线性预测控制方法进行伺服控制器设计。该控制器采用RBF神经网络对系统在线辨识并作为预测模型和实现在线校正功能;采用黄金分割法实现控制量滚动优化。最后,在Matlab6．5环境下进行了仿真试验。结果表明,采用该方法能有效提高塞棒位置控制质量,验证了设计方法的有效性。     

溶解氧浓度的直接自适应动态神经网络控制方法

针对污水处理过程溶解氧浓度的控制问题,提出一种直接自适应动态神经网络控制方法(direct adaptive dynamic neural network control,DADNNC).构建的控制系统主要包括神经网络控制器和补偿控制器.神经网络控制器由自组织模糊神经网络实现系统状态与控制量之间的映射;提出一种基于规则无用率的结构修剪算法,并给出结构调整后网络收敛的理论证明.同时,为保证系统稳定,设计补偿控制器减小网络逼近误差,参数调整由Layapunov理论给出.国际基准仿真平台上的实验表明,与固定结构神经网络控制器、PID和模型预测控制等已有控制方法相比,DADNNC方法具有更高的控制精度和更强的适应能力.     

基于神经网络与多模型的非线性自适应广义预测控制

针对一类不确定非线性离散时间动态系统, 提出了基于神经网络与多模型的非线性广义预测自适应控制方法. 该自适应控制方法由线性鲁棒广义预测自适应控制器, 神经网络非线性广义预测自适应控制器和切换机制三部分构成. 线性鲁棒广义预测自适应控制器保证闭环系统的输入输出信号有界, 神经网络非线性广义预测自适应控制器能够改善系统的性能. 切换策略通过对上述两种控制器的切换, 保证系统稳定的同时, 改善系统性能. 给出了所提自适应方法的稳定性和收敛性分析. 最后通过仿真实例验证了所提方法的有效性.     

基于有序神经网络的神经模糊预测控制

本文使用有序神经网络和改进的模糊控制器构成了一种新型的神经模糊预测控制方法，有序网络学习速度快，所需神经数目少，用事先训练好的有序网络代替传统的预测模型，以期增强输出预测的准确性；同时，用一种改进的模糊控制器原有的PID控制器，增强系统的鲁棒性。仿真结果表明，所提出的神经模糊预测控制方法可以获得理想的控制效果。