强制循环蒸发系统的非线性自适应解耦PID控制

本文结合现场的实际过程数据,首先应用能量平衡建立了强制循环蒸发过程的动态模型.针对该过程的多变量、非线性以及强耦合特性,在常规增量式PID控制器的基础上提出基于神经网络与多模型切换的非线性自适应解耦PID控制策略.该控制器是由线性自适应解耦PID控制器和基于神经网络的非线性自适应解耦PID控制器以及切换机构组成.其中线性自适应解耦PID控制器可以保证系统的稳定,而基于神经网络的非线性自适应解耦PID控制器则可以有效地提高系统的性能.上述过程的PID参数是通过广义预测的方法得到,最后通过仿真表明,上述控制方法不仅消除了回路间的耦合,在稳定生产的同时提高了蒸发的效率.     

Performance assessment of single-loop industrial controllers

The most common metric for controller performance assessment is a comparison of the process output variance to that which would have been obtained if some optimal controller had been applied to the process over the same time frame. Usually this optimal controller is a minimum variance controller, as a metric based on this controller requires a minimum of process knowledge and no plant tests. While minimum variance controllers by definition contain an accurate disturbance model, industrial controllers contain a simple fixed disturbance model, which may or may not be an accurate representation of the actual disturbance. Shown in this paper is the effect that this simple disturbance model has on performance indices, and methodologies for controller performance assessment that accounts for this simple model. In addition, a performance metric for non-deadtime-compensated (i.e., PID) controllers is shown.     

A neural network-based proportional integral derivative controller

A new method of designing direct controllers of the PID type for nonlinear plants by using RBF neural networks is proposed, and its satisfactory performance is demonstrated through simulations. This method does not put too much restriction on the type of plant to be controlled, and it has a stable performance for the type of inputs for which it has been trained. Unlike backpropagation or other supervised methods of training, this approach does not require knowledge of the appropriate form of controller output for each given input, and neither does it require identification of the plant or its inverse model. The PID controller design methodology presented here has certain advantages over conventional methodologies.     

Control-affine fuzzy neural network approach for nonlinear process control

An internal model control strategy employing a fuzzy neural network is proposed for SISO nonlinear process. The control-affine model is identified from both steady state and transient data using back-propagation. The inverse of the process is obtained through algebraic inversion of the process model. The resulting model is easier to interpret than models obtained from the standard neural network approaches. The proposed approach is applied to the tasks of modelling and control of a continuous stirred tank reactor and a pH neutralization process which are not inherently control-affine. The results show a significant performance improvement over a conventional PID controller. In addition, an additional neural network which models the discrepancy between a control-affine model and real process dynamics is added, and is shown to lead to further improvement in the closed-loop performance.     

Adaptive neural sliding mode compensator for a class of nonlinear systems with unmodeled uncertainties

This paper addresses the problem of adaptive neural sliding mode control for a class of multi-input multi-output nonlinear system. The control strategy is an inverse nonlinear controller combined with an adaptive neural network with sliding mode control using an on-line learning algorithm. The adaptive neural network with sliding mode control acts as a compensator for a conventional inverse controller in order to improve the control performance when the system is affected by variations in its entire structure (kinematics and dynamics). The controllers are obtained by using Lyapunov's stability theory. Experimental results of a case study show that the proposed method is effective in controlling dynamic systems with unexpected large uncertainties.     

基于模糊专家模型的神经控制器及应用研究

针对具有严重非线性特性的pH中和过程,提出了一种基于模糊专家模型的神经控制策略,这种方法将神经网络逆控制器与神经元PID控制器相结合,并利用模糊专家模型所得到的预报结果来调整神经元PID的权值。仿真试验表明该方法能有效改善控制性能,所提出的方法实现了对pH过程的有效控制,并且有很强的适应性。     

模糊PID控制器的稳定性分析

构造出一种PID型模糊控制器，并证明了这种模糊控制器近似于一种变参数的PID控制器，以PID模型为基础，基于无源性定量对模型PID控制器的稳定性进行分析，导出了使模糊PID控制器稳定的充分条件，为设计稳定的模糊PID控制器提供了理论指导。     

基于神经网络的恒温控制系统的研究与设计

由于恒温控制的数学模型很难建立,针对这一难题提出了基于神经网络的PID控制器,侧重介绍了BP神经网络PID控制器算法的基本知识以及控制器的设计原理,通过实验仿真证明了神经网络PID控制器的控制效果比传统的PID控制在静态特性和动态特性方面都有所提高,而且具有较好的鲁棒性,该控制器在工业控制中将会发挥越来越大的作用.     

基于执行器–评价器学习的自适应PID控制

针对传统PID控制器无法在线自整定参数的不足,提出了一种基于执行器一评估器（Actor-Critic,AC）学习的自适应PID控制器结构与学习算法．该控制器利用AC学习实现PID参数的自适应整定,采用一个径向基函数网络同时对Actor的策略函数和Critic的值函数进行逼近．径向基函数网络的输入为系统误差、误差的一次差分和二次差分,Actor实现系统状态到PID参数的映射,Critic则对Actor的输出进行评判并且生成时序差分（temporaldifference,TD）误差信号．基于AC学习的体系结构和TD误差性能指标,给出了控制器设计的步骤流程图．两个仿真实验表明：与传统的PID控制器相比,基于AC学习的PID控制器在响应速度和自适应能力方面要优于传统PID控制器．     

基于NBPID的回滞系统控制

回滞现象广泛存在于许多领域，其不可积的非线性特性给控制设计带来了困难。提出的NBPID控制器是基于神经网络逆模型前馈控制(N)，加上改进的Bang—Bang控制(B)的PID控制器。首先通过神经网络逆模型的前馈控制来削弱回滞带来的影响，然后在PID控制器的基础上，为了进一步控制误差，加上改进的Bang—Bang控制。通过设计出的NBPID对回滞系统进行控制，仿真结果表明控制方法是有效的。     

Intelligent control of exit temperature in a gas-fuel can-type combustor

The dynamical characteristics of a gas-fuel can-type combustor are highly nonlinear and are too complicated to be modeled precisely. Consequently, it is very difficult to control the exit temperature in a combustor using a conventional feedback controller. This paper investigates the models, describing the dynamics of exit temperature for a gas-fuel can-type combustor, and designs the intelligent controllers, based on the characteristics of the constructed models, to control the exit temperature in the combustor. An identified neural network (INN) was utilized to construct the dynamical models because of its powerful learning and handling ability for nonlinear systems. According to the open-loop responses of the investigated models, two controllers, a self-tuning fuzzy proportional–integral–derivative controller and a neural network controller, were developed for the exit temperature control. Experiments were conducted to evaluate the constructed models and the designed controllers.     

基于自适应模糊神经网络控制器的网络控制系统

网络控制系统中存在着时延、丢包、网络干扰等问题。针对网络控制系统中存在恶化系统的控制性能,甚至导致系统不稳定的因素,提出了一种基于自适应模糊神经网络控制器的网络控制系统,它能根据系统的实际输出与期望输出误差,利用自适应模糊控制和神经网络自学习的原理进行控制参数的自行调整,以符合控制系统的实际要求,同时,分析了网络延时,丢包率及网络干扰因素对系统性能的影响。利用TrueTime工具箱建立了包含自适应模糊神经网络控制器的网络控制系统的仿真模型,并将其分别与基于常规PID控制器的网络控制系统和基于模糊参数PID控制器的网络控制系统进行了比较。实验结果表明,在相同的网络环境下,基于自适应模糊神经网络控制器的网络控制系统的控制效果比基于常规的PID控制器和基于模糊参数PID控制器的要好,且具有较好的抗干扰能力和鲁棒性能。     

基于合作粒子群算法的PID神经网络非线性控制系统

PID神经元网络 (PIDNN)模型为一种新型的神经网络模型,兼有PID与神经网络的共同优点,应用于复杂的控制系统.取得优良控制性能,但其后向传播算法 (BP)限制了该模型的应用范围.为实现对非线性多变量系统的有效控制,扩展神经网络的应有范围,本文采用PIDNN神经网络设计了多变量PIDNN神经网络 (MPIDNN)控制器,并用本文作者提出的合作粒子群算法 (CPSO)取代了传统BP后向传播算法,通过比较MPIDNN_CPSO、MPIDNNCRPSO、MPIDNN_PSO和MPIDNN_BP4种控制器的控制性能,仿真结果表明,基于CPSO算法的MPIDNN控制器实现了对非线性多变量不对称系统的有效控制.与传统的BP算法相比,CPSO算法提高了控制系统的稳定性、精确性与鲁棒性.     

直升机智能PID控制研究

针对直升机俯仰角度控制和旋转轴速度控制需求,对模糊PID控制、神经网络PID控制和免疫PID控制在不同控制规律下的系统控制效果进行了对比研究。仿真实验表明,神经网络PID控制器准确性最高,系统响应无误差,稳定性较好,但响应时间较长;模糊PID控制器系统动态响应时间较快,系统稳定性相对最好,但存在微量误差;免疫PID控制器控制直升机旋转轴时,系统响应速度和稳定性明显优于其他两类控制器,但对俯仰角控制效果差。     

微型燃气轮机的新型神经网络控制的研究

燃机控制系统是一种多变量、非线性、时变的系统,对微型燃气轮机的转速控制器进行了深入研究.PID控制应用广泛,但在实际应用中,其参数整定仍未得到较好的解决.因此,设计了一种新的神经网络PID控制器作为主控制器,通过神经网络所具有的任意非线性表达能力,可以通过对系统性能的学习来实现具有最佳组合的PID控制,确保系统的稳定性、快速性和准确性.大量的仿真证明,该算法具有良好的控制效果.     

A Stable Output Feedback Position Control With Integral Action For Robot Manipulators

In this paper, the problem of robust regulation of robot manipulators using only position measurements is addressed. The main idea of the control design methodology is to use an observer to estimate simultaneously the velocity and the modeling error signal induced by model/system mismatches. The controller is obtained by replacing the velocity and the modeling error in an inverse dynamics feedback by their estimates, which leads to a certainty equivalence controller. The resulting controller has a PID‐type structure which, under least prior knowledge, reduces to the PI₂D regulator studied in [20]. Moreover, the controller is endowed with a natural antireset windup (ARW) scheme to cope with control torque saturations. Regarding the closed‐loop behavior, it is proven that the region of attraction can be arbitrarily enlarged with high observer gains only, thus we prove semiglobal asymptotic stability. Our result supersedes previous works in the direction of performance estimates; specifically, it is also proven that the performance induced by a saturated inverse dynamics controller can be recovered by our PID‐type controller. In this sense, our work reveals some connections between PID‐type and inverse dynamics controllers.     

Wavelet neural adaptive proportional plus conventional integral-derivative controller design of SSSC for transient stability improvement

Although the PI or PID (PI/PID) controllers have many advantages, their control performance may be degraded when the controlled object is highly nonlinear and uncertain; the main problem is related to static nature of fixed-gain PI/PID controllers. This work aims to propose a wavelet neural adaptive proportional plus conventional integral-derivative (WNAP+ID) controller to solve the PI/PID controller problems. To create an adaptive nature for PI/PID controller and for online processing of the error signal, this work subtly employs a one to one offline trained self-recurrent wavelet neural network as a processing unit (SRWNN-PU) in series connection with the fixed-proportional gain of conventional PI/PID controller. Offline training of the SRWNN-PU can be performed with any virtual training samples, independent of plant data, and it is thus possible to use a generalized SRWNN-PU for any systems. Employing a SRWNN-identifier (SRWNNI), the SRWNN-PU parameters are then updated online to process the error signal and minimize a control cost function in real-time operation. Although the proposed WNAP+ID is not limited to power system applications, it is used as supplementary damping controller of static synchronous series compensator (SSSC) of two SSSC-aided power systems to enhance the transient stability. The nonlinear time-domain simulation and system performance characteristics in terms of ITAE revealed that the WNAP+ID has more control proficiency in comparison to PID controller. As additional simulations, the features of the proposed controller are compared to those of the literature while some of its promising features like its fast noise-rejection ability and its high online adapting ability are also highlighted.     

一种神经网络自适应PID控制器

应用人工神经网络的原理,设计了一种神经网络的职能PID控制器。仿真结果表明,此PID控制器对非线性时不变系统有比传统的PID好的控制效果。该控制器将神经网络和PID控制规律融为一体,既具有常规PID控制器结构简单、参数物理意义明确之优点,又具有神经网络自学习、自适应之能力,控制效果明显提高。     

A new design for a PID plus feedforward controller

In this paper, a new design and tuning procedure for a PID plus feedforward controller is proposed. It consists of determining a feedforward signal in order to achieve a predefined process output transition time assuming a first order plus dead time model of the process. Then, the PID parameters are tuned by any conventional method in order to assure a good load disturbance rejection and the reference signal to the closed-loop system is obtained by filtering appropriately the set-point step signal. Simulation and experimental results show that the method outperforms the typical (inverse) model-based approach despite its simplicity and it is therefore suitable to implement in Distributed Control Systems as well as in single-station controllers.     

基于并行自学习的神经网络内模控制及其应用研究

基于在线并行自学习的神经网络内模控制,该方法是借助于神经网络对复杂系统的辩识能力对被控对象进行正模型及逆模型的辩识,用NNM辩识对象的正模型,通过一个并行自学习系统训练的NNC辩识对象的逆模型,然后用做内模控制器去控制对象。将该种控制策略应用于火电厂热工对象中具有大迟延、大惯性和时变等特性的主汽温对象,仿真研究表明,该控制方案适应对象参数的变化并表现出良好的控制特性,具有较强的鲁棒性和自适应能力。在实际应用中具有一定的实用价值。