Robust fuzzy neural network control for linear ceramic motor drivevia backstepping design technique

This study presents a robust fuzzy-neural-network (RFNN) control system for a linear ceramic motor (LCM) that is driven by an unipolar switching full-bridge voltage source inverter using LC resonant technique. The structure and operating principle of the LCM are introduced. Since the dynamic characteristics and motor parameters of the LCM are nonlinear and time varying, a RFNN control system is designed based on the hypothetical dynamic model to achieve high-precision position control via the backstepping design technique. In the RFNN control system a fuzzy neural network (FNN) controller is used to learn an ideal feedback linearization control law, and a robust controller is designed to compensate the shortcoming of the FNN controller. All adaptive learning algorithms in the RFNN control system are derived from the sense of Lyapunov stability analysis, so that system-tracking stability can be guaranteed in the closed-loop system. The effectiveness of the proposed RFNN control system is verified by experimental results in the presence of uncertainties. In addition, the advantages of the proposed control system are indicated in comparison with the traditional integral-proportional (IP) position control system     

Adaptive positioning control of an ultrasonic linear motor system

A 3PRR parallel precision positioning system, driven by three ultrasonic linear motors, was designed for use as the object stage of a scanning electron microscope (SEM). To improve the tracking accuracy of the parallel platform, the positioning control algorithms for the drive joints needed to be studied. The dead-zone phenomenon caused by static friction reduces the trajectory tracking accuracy significantly. Linear control algorithms such as PID (Proportion Integration Differentiation) are unable to compensate effectively for the dead-zone nonlinearity. To address this problem, two types of feedforward compensation control algorithms have been investigated. One is constant feedforward with the integral separation PID; the other is adaptive feedback and feedforward based on the model reference adaptive control (MRAC). Simulations and experiments were conducted using these two control algorithms. The results demonstrated that the constant feedforward with integral separation PID algorithm can compensate for the time-invariant system after identifying the dead-zone depth, while the adaptive feedback and feedforward algorithm is more suitable for the time-varying system. The experimental results show good agreement with the simulation results for these two control algorithms. For the dead-zone nonlinearity caused by the static friction, the adaptive feedback and feedforward algorithm can effectively improve the trajectory tracking accuracy.     

Robust control for nonlinear motor-mechanism coupling system using wavelet neural network

A robust controlled toggle mechanism, which is driven by a permanent magnet (PM) synchronous servo motor is studied in this paper. First, based on the principle of computed torque control, a position controller is developed for the motor-mechanism coupling system. Moreover, to relax the requirement of the lumped uncertainty in the design of a computed torque controller, a wavelet neural network (WNN) uncertainty observer is utilized to adapt the lumped uncertainty online. Furthermore, based on the Lyapunov stability a robust control system, which combines the computed torque controller, the WNN uncertainty observer and a compensated controller is proposed to control the position of the motor-mechanism coupling system. The computed torque controller with WNN uncertainty observer is the main tracking controller, and the compensated controller is designed to compensate the minimum approximation error of the uncertainty observer. Finally, simulated and experimental results due to a periodic sinusoidal command show that the dynamic behaviors of the proposed robust control system are robust with regard to parametric variations and external disturbances.     

一类非等阶分数阶非线性系统的神经网络控制

讨论一类不确定非线性分数阶非等阶（noncommensurate）的系统的控制问题。假设系统含的不确定包括正实不确定（positive real uncertainty）项和非线性函数完全未知,首先利用RBF神经网络近似未知非线性函数,再基于系统的连续频率分布模型将分数阶系统转化为等价的无穷维分布状态变量的整数阶系统,结合间接Lyapunov方法及线性矩阵不等式（LMI）方法,给出了系统鲁棒渐近稳定的充分条件。理论和实例仿真验证了方法的有效性。     

Intelligent control system design for UAV using a recurrent wavelet neural network

This paper aims to propose an efficient control algorithm for the unmanned aerial vehicle (UAV) motion control. An intelligent control system is proposed by using a recurrent wavelet neural network (RWNN). The developed RWNN is used to mimic an ideal controller. Moreover, based on sliding-mode approach, the adaptive tuning laws of RWNN can be derived. Then, the developed RWNN control system is applied to an UAV motion control for achieving desired trajectory tracking. From the simulation results, the control scheme has been shown to achieve favorable control performance for the UAV motion control even it is subjected to control effort deterioration and crosswind disturbance.     

超声电机测控系统的一种实现方法

设计了一套基于微机的超声电机速度和位置测试与控制系统.该系统解决了超声电机长时间工作时由于压电陶瓷特性的改变导致电机速度不稳定问题,采用PI算法的闭环控制时,电机速度可以稳定在3%之内.位置控制实验结果表明:采用模糊推理 PI控制器对电机进行位置精密伺服控制是完全可行的,精度可以达到0.09°.     

Backstepping wavelet neural network control for indirect field-oriented induction motor drive

This study address a newly designed decoupling system and a backstepping wavelet neural network (WNN) control system for achieving high-precision position-tracking performance of an indirect field-oriented induction motor (IM) drive. First, a decoupling mechanism with an online inverse time-constant estimation algorithm is derived on the basis of model reference adaptive system theory to preserve the decoupling control characteristic of an indirect field-oriented IM drive. Moreover, based on the backstepping design methodology, a desired feedback control law is developed for ensuring the favorable control performance. However, the uncertainties, such as mechanical parameter uncertainty, external load disturbance, unstructured uncertainty due to nonideal field orientation in transient state, and unmodeled dynamics in practical applications, are difficult to know in advance. Thus, the stability of the desired feedback control may be destroyed. Due to the powerful approximation ability of WNN, a backstepping WNN control scheme is designed in this study to control the rotor position of an indirect field-oriented IM drive for periodic motion. This control scheme contains two parts: one is a WNN control that is utilized to mimic the desired feedback control law, and the other is a robust control that is designed to recover the residual part of approximation for ensuring the stable control characteristic. In addition, numerical simulation and experimental results due to periodic commands are provided to verify the effectiveness of the proposed control strategy.     

Robust reliable control design for networked control system with sampling communication

In this article, the problem of robust exponential stability and reliable stabilisation for a class of continuous-time networked control systems (NCSs) with a sample-data controller and unknown time-varying sampling rate is considered. The analysis is based on average dwell-time, Lyapunov–Krasovskii functional and linear matrix inequality (LMI) technique. The delay-dependent criteria are developed for ensuring the robust exponential stability of the considered NCSs. The obtained conditions are formulated in terms of LMIs that can easily be solved by using standard software packages. Furthermore, the result is extended to study the robust stabilisation for NCS with parameter uncertainties. A state feedback controller is constructed in terms of the solution to a set of LMIs, which guarantee the robust exponential stabilisation of NCS and the controller. Finally, numerical examples are presented to illustrate the effectiveness of the obtained results.     

Self-organizing neural control system design for dynamic processes

This paper discusses the achievable nominal performance of a well-parametrized neural feedback control system, and proposes an efficient training method for parametrizing such a controller. A self-organizing neural control (SONC) system is presented in which a layered feedforward neural network is adopted as the controller structure in order to apply directly existing back-propagated learning techniques. A self-organizing methodology is introduced to provide the training set for adjusting parameters of the neural controller. One important feature of the proposed adaptive mechanism is that, though it should lack extensive knowledge of the process dynamics at the outset of controller design, it will still be able to achieve its desired results by employing the subjective experience of control specialists as its training aids. Tuning variables of the SONC system are reviewed through exploring their effects on five typical transfer functions. The applicability of the SONC system is also demonstrated on a continuous stirred tank reactor. Simulation results show that a well-parametrized neural controller can improve nominal performance for a wide variety of different processes, and the proposed self-organizing mechanism can direct a controller to achieve the desired final parametrization.     

基于RBF神经网络监督的电动机直接转矩控制系统设计

针对矿井输送机在低速运行时电动机转矩脉动较大的问题,在传统电动机直接转矩控制系统的基础上,采用RBF神经网络监督控制器代替PID控制器。仿真结果表明,基于RBF神经网络监督的电动机直接转矩控制系统能有效改善磁链波形,降低电动机转矩脉动。     

Robust neural control for robotic manipulators

A robust neural control scheme for mechanical manipulators is presented. The design basically consists of an adaptive neural controller which implements a feedback linearization control law for a generic manipulator with unknown parameters, and a sliding-mode control which robustifies the design and compensates for the neural approximation errors. It is proved that the resulting closed-loop system is stable and that the trajectory-tracking control objective is achieved. Some simulation results are also provided to evaluate the design.     

四容水箱的小波神经网络广义预测控制

针对四容水箱系统的多变量、大时滞、非线性及强耦合等特性,采用了小波神经网络广义预测控制（WNNGPC）策略。利用小波神经网络良好的函数逼近能力,对系统被控对象进行辨识,得到控制系统的预测模型,再结合广义预测控制良好的控制性能,达到对四容水箱系统的稳定控制。在系统辨识的过程中,采用的是改进的BP学习算法,这一算法能够快速平稳地修正网络权值和阈值,使预测输出平滑地趋近期望输出。在解决系统的耦合问题上,利用了模糊控制的通用逼近性,设计了模糊前馈补偿解耦。基于模糊补偿解耦的WNNGPC对四容水箱进行控制实验,并对比分析实验结果。结果表明,这一控制策略对四容水箱进行控制时取得了较好的控制效果。     

Hybrid control using recurrent fuzzy neural network for linearinduction motor servo drive

A hybrid control system using a recurrent fuzzy neural network (RFNN) is proposed to control a linear induction motor (LIM) servo drive. First, feedback linearization theory is used to decouple the thrust force and the flux amplitude of the LIM. Then, a hybrid control system is proposed to control the mover of the LIM for periodic motion. In the hybrid control system, the RFNN controller is the main tracking controller, which is used to mimic a perfect control law, and the compensated controller is proposed to compensate the difference between the perfect control law and the RFNN controller. Moreover, an online parameter training methodology, which is derived using the Lyapunov stability theorem and the gradient descent method is proposed to increase the learning capability of the RFNN. The effectiveness of the proposed control scheme is verified by both the simulated and experimental results. Furthermore, the advantages of the proposed control system are indicated in comparison with the sliding mode control system     

Intelligent transportation control system design using wavelet neural network and PID-type learning algorithms

In this paper, an intelligent transportation control system (ITCS) using wavelet neural network (WNN) and proportional-integral-derivative-type (PID-type) learning algorithms is developed to increase the safety and efficiency in transportation process. The proposed control system is composed of a neural controller and an auxiliary compensation controller. The neural controller acts as the main tracking controller, which is designed via a WNN to mimic the merits of an ideal total sliding-mode control (TSMC) law. The PID-type learning algorithms are derived from the Lyapunov stability theorem, which are utilized to adjust the parameters of WNN on-line for further assuring system stability and obtaining a fast convergence. Moreover, based on H_∞ control technique, the auxiliary compensation controller is developed to attenuate the effect of the approximation error between WNN and ideal TSMC law, so that the desired attenuation level can be achieved. Finally, to investigate the effectiveness of the proposed control strategy, it is applied to control a marine transportation system and a land transportation system. The simulation results demonstrate that the proposed WNN-based ITCS with PID-type learning algorithms can achieve favorable control performance than other control methods.     

Robust force/motion control of constrained robots using neural network

A robust neural network (NN) controller is proposed for the simultaneous force/motion control of constrained rigid robots. The NN weights here are tuned on‐line, with no off‐line learning phase required. Most importantly, we can guarantee the boundedness of constraint force errors, joint position tracking errors, and NN weights. When compared with adaptive controllers, we do not require linearity in the unknown parameters, and the tedious computation of the regression matrix. Novel passivity properties of the NN controller are stated and proven. ©1999 John Wiley & Sons, Inc.     

改进型BP神经网络MRAS控制系统

在常规BP神经网络模型参考自适应控制器基础上采用改进型BP神经网络作为辨识器和控制器,组成新的模型参考神经网络自适应控制系统,利用改进型BP神经网络的优点弥补传统自适应方法的不足,使系统具有更强的鲁棒性,收敛更快,逼近精度更高的优点。仿真结果表明,该系统比传统BP神经网络模型参考自适应系统具有更好的稳定性和更快的响应速度。     

An architecture-adaptive neural network online control system

An architecture-adaptive intelligent self-tuning control system is presented. The system is composed of the supervisor module, the model refinement module, the process plant and the database. In the supervisor module, the user prescribes the desired curve for the plant dynamic process. The model refinement module is in parallel with the process plant, and consists of the self-tuning process model, which contains an architecture-adaptive neural network. The model refinement module could learn intelligently the real process plant by the prompt adjustments based on the difference of the outputs of the two modules, and its learned model is also refined gradually. This diagram is especially versatile in the complex nonlinear and time-variant systems in practice.     

Nonlinear system identification with continuous piecewise linear neural network

This paper considers system identification using domain partition based continuous piecewise linear neural network (DP-CPLNN), which is newly proposed. DP-CPLNN has the capability of representing any continuous piecewise linear (CPWL) function, hence its identification performance can be expected. Another attractive feature of DP-CPLNN is the geometrical property of its parameters. Applying this property, this paper proposes an identification method including domain partition and parameter training. In numerical experiments, DP-CPLNN with this method outperforms hinging hyperplanes and high-level canonical piecewise linear representation, which are two widely used CPWL models, showing the flexibility of DP-CPLNN and the effectiveness of the proposed algorithm in nonlinear identification.