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.     

Interval type 2 hierarchical FNN with the H-infinity condition for MIMO non-affine systems

To develop a controller that deals with noise-corrupted training data and rule uncertainties for interconnected multi-input–multi-output (MIMO) non-affine nonlinear systems with unmeasured states, an interval type-2 fuzzy system is integrated with an observer-based hierarchical fuzzy neural controller (IT2HFNC) in this paper. Also, an H_∞ control technique and a strictly positive real Lyapunov (SPR-Lyapunov) design approach are employed for attenuating the influence of both external disturbances and fuzzy logic approximation error on the tracking of errors. Moreover, the proposed hierarchical fuzzy structure can greatly reduce the number of adjusted parameters of the IT2HFNC, and then, the problem of online computational burden can be solved. According to the design of the interval type-2 fuzzy neural network and H_∞ control technique, the IT2HFNN controller can improve its robustness to noise, uncertainties, approximation errors, and external disturbances. Simulation results are reported to show the performance of the proposed control system mode and algorithms.     

Robust adaptive fuzzy control of twin rotor MIMO system

This paper considers designing an adaptive fuzzy controller to position the yaw and pitch angles of a twin rotor MIMO system (TRMS) in two degrees of freedom. The goal of the controller is to stabilize the TRMS in a desired position or track a specified trajectory. The parameters of the fuzzy controller are updated using the gradient descent algorithm in order to increase its robustness against external disturbances and/or changes in system parameters. Moreover, the stability of the overall closed-loop system is guaranteed based on the Lyapunov stability theory. The proposed controller is applied to a TRMS with heavy cross coupling between its axes. Experimental results show good performance of the proposed controller as compared to the non-adaptive fuzzy and PID controllers, especially when there are system uncertainties and external disturbances.     

Online adaptive fuzzy neural identification and control of a class of MIMO nonlinear systems

This paper presents a robust adaptive fuzzy neural controller (AFNC) suitable for identification and control of a class of uncertain multiple-input-multiple-output (MIMO) nonlinear systems. The proposed controller has the following salient features: 1) self-organizing fuzzy neural structure, i.e., fuzzy control rules can be generated or deleted automatically; 2) online learning ability of uncertain MIMO nonlinear systems; 3) fast learning speed; 4) fast convergence of tracking errors; 5) adaptive control, where structure and parameters of the AFNC can be self-adaptive in the presence of disturbances to maintain high control performance; 6) robust control, where global stability of the system is established using the Lyapunov approach. Simulation studies on an inverted pendulum and a two-link robot manipulator show that the performance of the proposed controller is superior.     

Modelling,control, and stability analysis of non-linear systems using generalized fuzzy neural networks

This paper presents an adaptive fuzzy neural controller (AFNC) suitable for modelling and control of MIMO non-linear dynamic systems. The proposed AFNC has the following salient features: (1) fuzzy neural control rules can be generated or deleted dynamically and automatically; (2) uncertain MIMO non-linear systems can be adaptively modelled on line; (3) adaptation and learning speed is fast; (4) expert knowledge can be easily incorporated into the system; (5) the structure and parameters of the AFNC can be self-adaptive in the presence of uncertainties to maintain a high control performance; and (6) the asymptotical stability of the system is established using the Lyapunov approach. Simulation studies on a two-link robot manipulator show that the performance of the proposed controller is better than that of some existing fuzzy/neural methods.     

欠驱动AUV模糊神经网络L2增益鲁棒跟踪控制

提出基于模糊神经网络欠驱动水下自主机器人(AUV)的L2增益鲁棒跟踪控制方法,该方法通过在线学习逼近动力学模型的不确定项.控制器克服了由于缺少横向推力对跟踪误差的影响,在考虑未知海流干扰情况下,实现了系统对模糊神经网络逼近误差的L2增益小于γ.利用Lyapunov稳定性理论证明了闭环控制系统误差信号一致最终有界.最后,通过精确模型参数和参数扰动仿真实验验证了该控制方法具有很好的跟踪效果和较强的鲁棒性.     

An Adaptive Neural Sliding Mode Controller for MIMO Systems

Here, a novel adaptive neural sliding mode controller (ANSMC) is proposed to handle the coupling and dynamic uncertainty of MIMO systems. The structure of this model-free new controller is based on a radial basis function neural network (RBFNN) which is derived from Lyapunov stability theory and relaxing Kalman–Yacubovich lemma to monitor the system for tracking a user-defined reference model. The weights of RBFNN can be initialized at zero, then, a novel online tuning algorithm is developed based on Lyapunov stability theory. A boundary layer function is introduced into the updating law to cover the parameter errors and modeling errors, and to guarantee the state errors converge into a specified error bound. An e-modification is added into the updating law to release the assumption of persistent excitation and obtain the appropriate values of the connecting weights of a RBFNN. To evaluate the control performance of the proposed controller, a two-link robot system is chosen as the simulation case. The numerical simulations results show that this novel controller has very good tracking accuracy, stability and robustness.     

一类多变量非线性动态系统的鲁棒自适应模糊控制

对一类非线性多变量未知动态系统,提出了一种自适应模糊控制策略.策略中采用IF-THEN推理规则来构造模糊逻辑系统,实现对系统中未知函数的估计,在建模误差为零的条件下设计状态反馈控制器及参数的自适应律.分析了当存在建模误差时,闭环系统的稳定性和鲁棒性.     

Fault tolerant control based on neural network interval type-2 fuzzy sliding mode controller for octorotor UAV

In this paper, a robust controller for a six degrees of freedom (6 DOF) octorotor helicopter control is proposed in presence of actuator and sensor faults. Neural networks (NN), interval type-2 fuzzy logic control (IT2FLC) approach and sliding mode control (SMC) technique are used to design a controller, named fault tolerant neural network interval type-2 fuzzy sliding mode controller (FTNNIT2FSMC), for each subsystem of the octorotor helicopter. The proposed control scheme allows avoiding difficult modeling, attenuating the chattering effect of the SMC, reducing the number of rules for the fuzzy controller, and guaranteeing the stability and the robustness of the system. The simulation results show that the FTNNIT2FSMC can greatly alleviate the chattering effect, tracking well in presence of actuator and sensor faults.     

多变量模糊神经网络控制器的研究

提出一种MIMO系统的模糊神经网络控制器结构,阐述了基本设计思想和具体算法过程。应用实例仿真结果表明,它可用于控制强耦合带时延多变量系统,并使系统具有良好的动态和静态性能。     

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）。     

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.     

A novel neural approximate inverse control for unknown nonlinear discrete dynamical systems.

A novel neural approximate inverse control is proposed for general unknown single-input-single-output (SISO) and multi-input-multi-output (MIMO) nonlinear discrete dynamical systems. Based on an innovative input/output (I/O) approximation of neural network nonlinear models, the neural inverse control law can be derived directly and its implementation for an unknown process is straightforward. Only a general identification technique is involved in both model development and control design without extra training (online or offline) for the neural nonlinear inverse controller. With less approximation made on controller development, the control will be more robust to large variations in the operating region. The robustness of the stability and the performance of a closed-loop system can be rigorously established even if the nonlinear plant is of not well defined relative degree. Extensive simulations demonstrate the performance of the proposed neural inverse control.     

Hybrid Adaptive Type‐2 Fuzzy Tracking Control of Chaotic Oscillation Damping of Power Systems

In this paper a novel hybrid direct/indirect adaptive fuzzy neural network (FNN) moving sliding mode tracking controller for chaotic oscillation damping of power systems is developed. The proposed approach is established by providing a tradeoff between the indirect and direct FNN controllers. It is equipped with a novel moving sliding surface (MSS) to enhance the robustness of the controller against the present system uncertainties and unknown disturbances. The major contribution of the paper arises from the new simple tuning idea of the sliding surface slope and intercept of the MSS. This study is novel because the approach adopted tunes the sliding surface slope and intercept of MSS using two simple rules simultaneously. One advantage of the proposed approach is that the restriction of knowing the bounds of uncertainties is also removed due to the adaptive mechanism. Moreover, the stability of the control system is also presented. The proposed controller structure is successfully employed to damp the complicated chaotic oscillations of an interconnected power system, when such oscillations can be made by load perturbation of a power system working on its stability edges. Comparative simulation results are presented, which confirm that the proposed hybrid adaptive type‐2 fuzzy tracking controller shows superior tracking performance.     

车载惯性稳定平台的神经网络滑模控制

三轴车载惯性稳定平台为复杂的MIMO非线性系统,针对其在不确定扰动下的伺服控制问题,本文设计了一种神经网络反演滑模控制器(NNBSMC).首先,选用反演法对其解耦,同时引入滑模控制律增加系统的抗干扰性;其次针对框架间的非线性摩擦力与系统耦合选用RBF神经网络作为扰动估计器,以便实时估计与补偿;然后采用前向增稳通道应对建...     

非线性互联系统的分散混合自适应智能控制

针对一类高阶互联MIMO非线性系统，利用TS模糊系统和神经网络的通用逼近能力，在神经网络控制器中引入模糊基函数，提出一种分散混合自适应智能控制器设计的新方案．基于等价控制思想，设计分散自适应控制器，无需计算TS模型．通过对不确定项进行自适应估计，取消了其存在已知上界的假设．通过理论分析，证明了闭环智能控制系统所有信号有界，跟踪误差收敛到零．     

Double EWMA controller using neural network-based tuning algorithm for MIMO non-squared systems

The double exponentially weighted moving average (dEWMA) control method is a popular algorithm for adjusting a process from run to run in semiconductor manufacturing. For MIMO non-squared statistic systems, the singular value decomposition (SVD) method is used for decoupling and the SVD-based dEWMA control scheme is treated as a MIMO extension of dEWMA control design. To enhance the performance and robustness of the linear system in the presence of ramp disturbances and white noises, the neural network-based adaptive algorithm is used to automatically tune the dEWMA controller parameters. Under the specified input patterns, the early stop criterion for the training-validation neural networks, and the stability constraints added in the tuning mechanism, the simulations show that the proposed control technique can effectively improve the means and standard deviations of the process outputs.     

Recurrent wavelet neural backstepping controller design with a smooth compensator

Recurrent wavelet neural network (RWNN) has the advantages in its dynamic responses and information storing ability. This paper develops a recurrent wavelet neural backstepping control (RWNBC) scheme for multiple-input multiple-output (MIMO) mechanical systems. This proposed RWNBC comprises a neural controller and a smooth compensator. The neural controller using an RWNN is the principal tracking controller utilized to mimic an ideal backstepping control law; and the parameters of RWNN are online tuned by the derived adaptation laws from the Lyapunov stability theorem. The smooth compensator is designed to dispel the approximation error introduced by the neural controller, so that the asymptotic stability of the closed-loop system can be guaranteed. Finally, two MIMO mechanical systems, a mass-spring-damper system and a two-inverted pendulum system, are performed to verify the effectiveness of the proposed RWNBC scheme. From the simulation results, it is verified that the proposed RWNBC scheme can achieve favorable tracking performance without any chattering phenomenon.     

基于干扰观测器的一类不确定非线性系统自适应二阶动态terminal滑模控制

针对一类不确定非线性系统的跟踪控制问题,在考虑建模误差、参数不确定和外部干扰情况下,以其拥有良好的跟踪性能以及强鲁棒性为目标,提出基于回归扰动模糊神经网络干扰观测器(recurrent perturbation fuzzy neural networks disturbance observer,RPFNNDO)的鲁棒自适应二阶动态terminal滑模控制策略.将回归网络、模糊神经网络和sine-cosine扰动函数各自优势相结合,给出一种回归扰动模糊神经网络结构,提出RPFNNDO设计方法,保证干扰估计准确性;构造基于带有指数函数滑模面的二阶快速terminal滑模面,给出其控制器设计过程,避免了滑模到达阶段、传统滑模的抖振问题,采用具有指数收敛的鲁棒项抑制干扰估计误差对系统跟踪性能的影响,利用Lyapunov理论证明闭环系统的稳定性;将该方法应用于混沌陀螺系统同步控制仿真实验,结果表明所提方法的有效性.     

Dynamic switching based fuzzy control strategy for a class of distributed parameter system

In this work, a dynamic switching based fuzzy controller combined with spectral method is proposed to control a class of nonlinear distributed parameter systems (DPSs). Spectral method can transform infinite-dimensional DPS into finite ordinary differential equations (ODEs). A dynamic switching based fuzzy controller is constructed to track reference values for the multi-inputs multi-outputs (MIMO) ODEs. Only a traditional fuzzy logic system (FLS) and a rule base are used in the controller, and membership functions (MFs) for different ODEs are adjusted by scaling factors. Analytical models of the dynamic switching based fuzzy controller are deduced to design the scaling factors and analyze stability of the control system. In order to obtain a good control performance, particle swarm optimization (PSO) is adopted to design the scaling factors. Moreover, stability of fuzzy control system is analyzed by using the analytical models, definition of the stability and Lyapunov stability theory. Finally, a nonlinear rod catalytic reaction process is used as an illustrated example for demonstration. The simulation results show that performance of proposed dynamic switching based fuzzy control strategy is better than a multi-variable fuzzy logic controller.