Fuzzy neural networks for estimation and fuzzy controller design: simulation study for a pulp batch digester

A structural implementation of a fuzzy inference system through connectionist network based on MLP with logical neurons connected through binary and numerical weights is considered. The resulting fuzzy neural network is trained using classical backpropagation to learn the rules of inference of a fuzzy system, by adjustment of the numerical weights. For controller design, training is carried out off line in a closed loop simulation. Rules for the fuzzy logic controller are extracted from the network by interpreting the consequence weights as measure of confidence of the underlying rule. The framework is used in a simulation study for estimation and control of a pulp batch digester. The controlled variable, the Kappa number, a measure of lignin content in the pulp, which is not measurable is estimated through temperature and liquor concentration using the fuzzy neural network. On the other hand a fuzzy neural network is trained to control the Kappa number and rules are extracted from the trained network to construct a fuzzy logic controller.     

Model-based cold-start speed control scheme for spark ignition engines

This paper presents a model-based control scheme to the cold-start speed control in spark ignition (SI) engines. The multi-variable control algorithm is developed with the purpose of improving the transient performance of the starting engine speed: the control inputs are the fuel injection, the throttle and the spark advance (SA), while the engine speed and the air mass flow rate are the measured signals. The fuel injection is performed with a dual sampling rate system: the cycle-based fuel injection command is individually adjusted for each cylinder by using a TDC (top dead center)-based air charge estimation. The desired performance for speed regulation is achieved by using a coordinated control of SA and throttle operation. The speed error convergence of the closed loop system is proved for simplified, second-order model with a time-delay, and the robustness with respect to parameter uncertainties is investigated. The performance and the robustness with respect to modeling uncertainties of the proposed control scheme are tested using an industrial engine simulator with six cylinders.     

模糊CMAC神经网络用于MIMO非线性系统的反馈线性化

针对一类多输入多输出（ＭＩＭＯ）连续时间非线性系统,应用模糊ＣＭＡＣ神经网络,给出一种状态反馈控制器,用于使状态反馈可线笥化的未知的非线性动态系统儿得要求的患 很弱的假设条件下,应用李雅普诺夫稳定性理论严格地证明了闭环系统内的所有信号为一致最终有界（ＵＵＢ）。     

二级倒立摆的Sugeno型模糊神经网络控制

为了提高二级倒立摆系统实时控制的响应速度和稳定性,在设计Mamdani型模糊推理规则控制器控制倒立摆系统稳定的基础上,设计了一种更有效率的基于Sugeno型模糊推理规则的模糊神经网络控制器.该控制器使用BP神经网络和最小二乘法的混合算法进行参数训练.能够准确归纳输入输出量的模糊隶属度函数和模糊逻辑规则.通过与Mamdani型控制器的仿真对比及实际控制实验结果,表明该Sugeno型模糊神经网络控制器时二级倒立摆实验装置的控制具有良好的稳定性、快速性和较高的控制精度.     

不确定多输入非线性系统自适应模糊滑模控制器设计

针对一类不确定多输入非线性系统提出一种新的自适应模糊滑模控制器,该控制器在存在模型逻辑系统逼近误差的情况下使闭环系统跟踪误差小于预先给定常数,消除滑模控制中的抖振,缓解因系统维数增高所致的模糊规则爆炸现象,最后用仿算例验证了所提出方法的有效性。     

三级倒立摆的加权变量模糊神经网络控制

为了提高三级倒立摆系统控制的响应速度和稳定性,在设计Mamdani型摸糊推理规则控制器控制倒立摆系统稳定的基础上,设计了一种更有效率的基于Sugeno型模糊推理规则的模糊神经网络控制器。该控制器使用BP神经网络和最小二乘法的混合算法进行参数训练,能够准确归纳输入输出量的模糊隶属度函数和模糊逻辑规则。通过与Mamdani型控制器的仿真对比,表明该Sugeno型模糊神经网络控制器对三级倒立摆系统的控制具有良好的稳定性和快速性,以及较高的控制精度。     

脉冲GTAW熔池动态过程模糊神经网络建模与控制

展示了模糊推理与神经网络结合在脉冲GTAW熔池动态过程智能控制中的应用研究 结果.建立了脉冲GTAW平板对接动态过程特征:正反面熔池的最大宽度、长度与面积等参数 的神经网络模型,基于实验数据采用模糊辨识方法提取焊接过程的模糊控制规则,进而设计了 具有自学习适应能力的模糊神经网络控制器.建立了脉冲GTAW熔池动态过程智能控制系统, 焊接实验验证了所设计的模糊神经网络控制器具有智能控制效果.     

Soft computing methods applied to the control of a flexible robot manipulator

The paper describes use of soft computing methods (fuzzy logic and neural network techniques) in the development of a hybrid fuzzy neural control (HFNC) scheme for a multi-link flexible manipulator. A manipulator with multiple flexible links is a multivariable system of considerable complexity due to the inter-link coupling effects that are present in both rigid and flexible motions. Modelling and controlling the dynamics of such manipulators is therefore difficult. The proposed HFNC scheme generates control actions combining contributions form both a fuzzy controller and a neural controller. The primary loop of the proposed HFNC contains a fuzzy controller and a neural network controller in the secondary loop to compensate for the coupling effects due to the rigid and flexible motion along with the inter-link coupling. It has been ascertained from the present investigation that the proposed soft-computing-based controller works effectively in the tracking control of such a multi-link flexible manipulator. The results are extendable to other multivariable systems of similar complexity.     

Unmanned bicycle balancing via Lyapunov rule-based fuzzy control

Guaranteed stability fuzzy controller for stabilization the motion of an unmanned bicycle is proposed. First, a fuzzy control system capable of automatically balancing an unmanned bicycle through tracking desired roll angle is developed. Fuzzy logic controller membership functions are defined utilizing scaling factors. To guarantee the stability of the closed loop system, similar to previous approaches reported in the literature, fuzzy If–Then rules are constructed based on Lyapunov stability criterion. It is indicated that the proposed fuzzy controller violates Lyapunov stability criterion. The reason of such a violation is argued in detail. To cope with this shortcoming, some modifications are made to the control strategy to assure stability. Through these modifications, the modified fuzzy controller is developed which simultaneously balances the bicycle and guarantees stability while minimizing roll angle tracking error and its derivative. It is indicated that the improved fuzzy controller can adapt to a variety of initial conditions. Moreover, robustness of the controller against parameter variation is verified through its implementation on different bicycle designs (different sets of bicycle parameters). Simulation results confirm the efficacy of the proposed fuzzy controller in terms of settling time and overshoot in comparison with previous studies. Sensitivity analysis of the controller efficiency with respect to system parameters is also assessed.     

基于模糊神经网络PID控制器的EEC数字化设计

为实现航空发动机模拟式电子控制器(EEC)的数字化设计,以其低压压气机导流叶片调节通道为主要研究对象,提出一种模糊神经网络PID控制器,将模糊控制、神经网络、PID控制相结合,利用模糊控制专家经验优势和神经网络的自学习、自适应能力,优化PID控制参数,实现控制性能提升。仿真结果显示,基于模糊神经网络的PID控制器控制性能有较大提高,具有比常规神经网络PID控制器更小的超调量和更好的抗干扰性;适用于定常系统和非定常系统,具有更好的自适应性与鲁棒性;可应用于航空发动机模拟式电子控制器(EEC)的数字化设计。     

Application of Fuzzy Logic Controlled Cathodic Protection on Iraq-Turkey Crude Oil Pipeline

Impressed current cathodic protection is widely used to prevent corrosion of structural steels. The major constituents, which accelerate corrosion, are resistivity, chlorides, sulfatesand the acidity (pH) of the soil. Because of these variations, the transformer-rectifier units must control and tune the output voltage depending on desired reference voltage steadily. Usually, classical controls such as PI and PID, have been widely used with their gains manually tuned based on the desired reference voltage. But, classical controls require different gains at the lower and higher end of the output voltage range to avoid overshoot and oscillation. In this study, a closed loop control system incorporating fuzzy logic has been developed for tuning output voltage of the transformer-rectifier units. The algorithm based on fuzzy logic was implemented on a modern microcontroller (PIC16F877) allowing great flexibility for various real time applications. The desired reference voltage has been given by using keypad and output values have been displayed on an LCD. It is achieved by implementing an adaptation mechanism based on fuzzy logic controller to compensate for the variations and the dynamic changes in the environment. The proposed fuzzy logic controller was applied to two different areas on Iraq-Turkey crude oil pipeline. When the performance of the proposed fuzzy logic controller was observed, it has been seen that the output voltage of transformer-rectifier unit controlled by fuzzy logic controller has no overshoot and oscillation in the both areas.     

A self-learning fuzzy logic controller using genetic algorithmswith reinforcements

This paper presents a new method for learning a fuzzy logic controller automatically. A reinforcement learning technique is applied to a multilayer neural network model of a fuzzy logic controller. The proposed self-learning fuzzy logic control that uses the genetic algorithm through reinforcement learning architecture, called a genetic reinforcement fuzzy logic controller, can also learn fuzzy logic control rules even when only weak information such as a binary target of “success” or “failure” signal is available. In this paper, the adaptive heuristic critic algorithm of Barto et al. (1987) is extended to include a priori control knowledge of human operators. It is shown that the system can solve more concretely a fairly difficult control learning problem. Also demonstrated is the feasibility of the method when applied to a cart-pole balancing problem via digital simulations     

Control of dynamic systems using fuzzy logic and neural networks

The use of artificial neural network is proposed for high-speed processing of rules in fuzzy logic controller (FLC). the logic element of an FLC is replaced by a single hidden layer feedforward network. the input and output fuzzy subsets are expressed it of numerical patterns. the network is trained using the back-propagation algori to establish fuzzy associations between the input and output fuzzy subsets. the inference mechanism of the network is compared with that of compositional law of inference. In the proposed implementation of FLC, all the rules are processed in paralle. This implementation has potential for high-speed processing of rules if the network is realized in hardware. the use of neural networks in fuzzy logic self-organizing is also ivestigated. © 1993 John Wiley & Sons, Inc.     

基于模糊逻辑的高速网络自适应拥塞控制研究

基于模糊逻辑 ,利用自适应拥塞控制机制来预测高速网络 (如Internet中 )的拥塞问题 .把路由器的缓冲系统看作一个非线性离散动态系统 ,利用基于模糊逻辑的控制器来预测源端发送速率的确切值以防止拥塞的发生 .通过对参数向量的调节来估计无法预测的和具有统计波动性的网络通信量 ,并利用Lyapunov分析方法来验证闭环系统的稳定性 .最后 ,以一个仿真例子说明了所提出方法的有效性 .     

A self-learning and tuning fuzzy logic controller based on genetic algorithms and reinforcements

This article presents a new method for learning and tuning a fuzzy logic controller automatically. A reinforcement learning and a genetic algorithm are used in conjunction with a multilayer neural network model of a fuzzy logic controller, which can automatically generate the fuzzy control rules and refine the membership functions at the same time to optimize the final system's performance. In particular, the self-learning and tuning fuzzy logic controller based on genetic algorithms and reinforcement learning architecture, which is called a Stretched Genetic Reinforcement Fuzzy Logic Controller (SGRFLC), proposed here, can also learn fuzzy logic control rules even when only weak information, such as a binary target of “success” or “failure” signal, is available. We extend the AHC algorithm of Barto, Sutton, and Anderson to include the prior control knowledge of human operators. It is shown that the system can solve a fairly difficult control learning problem more concretely, the task is a cart–pole balancing system, in which a pole is hinged to a movable cart to which a continuously variable control force is applied. © 1997 John Wiley & Sons, Inc.     

附加力外环的机器人力／位置自适应模糊控制

提出一种由神经网络训练模糊控制规则的自适应模糊控制器,并应用附加力外环的机器人力／位置控制。在不改变一般工业机器人原有位置控制的前提下,实现力／位置自适应模糊控制。实验结果表明,该方法可使机器人控制系统对工作环境接触刚度的自适应能力得到显著改善。     

基于CPN的模糊控制器系统设计及其应用研究

本文给出一种基对于向传播网络ＣＰＮ的模糊控制器设计。该网络经训练后能得到模糊规则并且具有自动学习功能，在控制性能上较普通控制器有所改进。最后给出加压钢前箱系统的应用实例。     

K-聚类的模糊神经网络对DO的控制研究

运用一种基于K-聚类算法的模糊径向基函数（RBF）神经网络对污水处理中的溶解氧质量浓度进行控制,该方法结合了模糊控制的推理能力强与神经网络学习能力强的特点,将模糊控制、RBF神经网络以及K-聚类学习算法相结合以在线调整隶属函数,优化控制规则。通过对阶跃输入仿真分析,其结果表明基于RBF的模糊神经网络控制器具有良好的动态性能、较强的鲁棒性和抗干扰能力,使其快速、准确地达到期望水平。     

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.     

Nonlinear fuzzy controller

We consider a fuzzy controller with two inputs, triangular fuzzy numbers, Zadeh logic to evaluate linear control rules, and a center of gravity defuzzifier. We derive a closed form expression for the defuzzified output and show it is a nonlinear controller. We then analyze the nonlinearities of the fuzzy controller with respect to the PI controller.