Adaptive recurrent neural network control using a structure adaptation algorithm

This paper proposes an adaptive recurrent neural network control (ARNNC) system with structure adaptation algorithm for the uncertain nonlinear systems. The developed ARNNC system is composed of a neural controller and a robust controller. The neural controller which uses a self-structuring recurrent neural network (SRNN) is the principal controller, and the robust controller is designed to achieve L ² tracking performance with desired attenuation level. The SRNN approximator is used to online estimate an ideal tracking controller with the online structuring and parameter learning algorithms. The structure learning possesses the ability of both adding and pruning hidden neurons, and the parameter learning adjusts the interconnection weights of neural network to achieve favorable approximation performance. And, by the L ² control design technique, the worst effect of approximation error on the tracking error can be attenuated to be less or equal to a specified level. Finally, the proposed ARNNC system with structure adaptation algorithm is applied to control two nonlinear dynamic systems. Simulation results prove that the proposed ARNNC system with structure adaptation algorithm can achieve favorable tracking performance even unknown the control system dynamics function.     

A Neural Network Adaptive Controller for End-effector Tracking of Redundant Robot Manipulators

In this paper we propose a neural network adaptive controller to achieve end-effector tracking of redundant robot manipulators. The controller is designed in Cartesian space to overcome the problem of motion planning which is closely related to the inverse kinematics problem. The unknown model of the system is approximated by a decomposed structure neural network. Each neural network approximates a separate element of the dynamical model. These approximations are used to derive an adaptive stable control law. The parameter adaptation algorithm is derived from the stability study of the closed loop system using Lyapunov approach with intrinsic properties of robot manipulators. Two control strategies are considered. First, the aim of the controller is to achieve good tracking of the end-effector regardless the robot configurations. Second, the controller is improved using augmented space strategy to ensure minimum displacements of the joint positions of the robot. Simulation examples are also presented to verify the effectiveness of the proposed approach.     

Stable reinforcement learning with recurrent neural networks

In this paper,we present a technique for ensuring the stability of a large class of adaptively controlled systems.We combine IQC models of both the controlled system and the controller with a method of filtering control parameter updates to ensure stable behavior of the controlled system under adaptation of the controller.We present a specific application to a system that uses recurrent neural networks adapted via reinforcement learning techniques.The work presented extends earlier works on stable reinforcement learning with neural networks.Specifically,we apply an improved IQC analysis for RNNs with time-varying weights and evaluate the approach on more complex control system.     

基于间接自适应鲁棒的永磁同步电机电流控制器设计

针对永磁同步电机(PMSM)电流环非理想反电势的抑制问题,本文提出一种基于鲁棒最小二乘(RRLS)自适应律的间接自适应鲁棒控制(IARC)方法.该控制方法基于自适应鲁棒控制(ARC)理论,根据电机状态方程构造最小二乘型自适应律,加入修正因子增强自适应律对系统中扰动的鲁棒性.本文理论证明了该方法的稳定性.通过建立含有非理想反电势的电机模型,设计IARC电流控制器,并分析说明IARC具有比直接ARC更好的输出跟踪性能和扰动抑制能力.最后,通过仿真和实验验证了该方法的有效性.     

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.     

Design of intelligent power controller for DC–DC converters using CMAC neural network

DC–DC converters are the devices which can convert a certain electrical voltage to another level of electrical voltage. They are very popularly used because of the high efficiency and small size. This paper proposes an intelligent power controller for the DC–DC converters via cerebella model articulation controller (CMAC) neural network approach. The proposed intelligent power controller is composed of a CMAC neural controller and a robust controller. The CMAC neural controller uses a CMAC neural network to online mimic an ideal controller, and the robust controller is designed to achieve L ₂ tracking performance with desired attenuation level. Finally, a comparison among a PI control, adaptive neural control and the proposed intelligent power control is made. The experimental results are provided to demonstrate the proposed intelligent power controller can cope with the input voltage and load resistance variations to ensure the stability while providing fast transient response and simple computation.     

Robust tracking control of a unicycle-type wheeled mobile manipulator using a hybrid sliding mode fuzzy neural network

This article presents a robust tracking controller for an uncertain mobile manipulator system. A rigid robotic arm is mounted on a wheeled mobile platform whose motion is subject to nonholonomic constraints. The sliding mode control (SMC) method is associated with the fuzzy neural network (FNN) to constitute a robust control scheme to cope with three types of system uncertainties; namely, external disturbances, modelling errors, and strong couplings in between the mobile platform and the onboard arm subsystems. All parameter adjustment rules for the proposed controller are derived from the Lyapunov theory such that the tracking error dynamics and the FNN weighting updates are ensured to be stable with uniform ultimate boundedness (UUB).     

基于神经网络和PID算法的数控机床并行混合控制模型

针对数控机床低速运动时由于非线性摩擦造成的问题，提出了一种基于神经网络和PID算法的并行混合控制模型．当电机速度大于转换速度时使用PID控制，小于转换速度时使用神经网络控制器．神经网络为5个输入的单神经元，采用Hebb学习算法．分析表明，混合控制器使跟随误差的波动明显减小，机床运动变得平稳．利用可由用户编写伺服算法的多轴运动控制器(PMAC)进行了实验，验证了混合控制器的控制效果．     

漂浮基空间机器人的径向基神经网络鲁棒自适应控制

针对一类同时具有参数及非参数不确定性的自由漂浮空间机器人系统的轨迹跟踪问题,采用了一种RBF神经网络的自适应鲁棒补偿控制策略.对于系统的参数不确定性,通过对径向基神经网络来自适应学习并补偿,逼近误差通过滑模控制器消除,神经网络权重的自适应修正规则基于Lyapunov函数方法得到;而非参数不确定通过鲁棒控制器来实时自适应...     

Indirect adaptive self-organizing RBF neural controller design with a dynamical training approach

This study proposes an indirect adaptive self-organizing RBF neural control (IASRNC) system which is composed of a feedback controller, a neural identifier and a smooth compensator. The neural identifier which contains a self-organizing RBF (SORBF) network with structure and parameter learning is designed to online estimate a system dynamics using the gradient descent method. The SORBF network can add new hidden neurons and prune insignificant hidden neurons online. The smooth compensator is designed to dispel the effect of minimum approximation error introduced by the neural identifier in the Lyapunov stability theorem. In general, how to determine the learning rate of parameter adaptation laws usually requires some trial-and-error tuning procedures. This paper proposes a dynamical learning rate approach based on a discrete-type Lyapunov function to speed up the convergence of tracking error. Finally, the proposed IASRNC system is applied to control two chaotic systems. Simulation results verify that the proposed IASRNC scheme can achieve a favorable tracking performance.     

无刷直流电机的模糊神经网络控制设计

在无刷直流电机(BLDCM)的控制上,传统PID等控制方法存在或多或少的不足.在模糊PID控制的基础上提出了一种模糊神经网络PI控制器的设计方法.该方法结合了模糊逻辑与神经网络,使得模糊控制器模拟了人的控制功能,不仅对环境变化有较强的适应能力,还拥有自学习能力.相比模糊PID控制,其具有计算量小、稳定性强等特点.对BLDCM进行建模与分析;在BLDCM数学模型的基础上,分别设计模糊PID控制器和模糊神经网络PI控制器;对设计的控制器进行仿真验证并分析.实验结果表明,模糊神经网络PI控制具有跟踪性能好、超调小、响应快、脉动小等优点,其动静态特性均优于模糊PID控制.     

Design of an adaptive self-organizing fuzzy neural network controller for uncertain nonlinear chaotic systems

Though the control performances of the fuzzy neural network controller are acceptable in many previous published papers, the applications are only parameter learning in which the parameters of fuzzy rules are adjusted but the number of fuzzy rules should be determined by some trials. In this paper, a Takagi–Sugeno-Kang (TSK)-type self-organizing fuzzy neural network (TSK-SOFNN) is studied. The learning algorithm of the proposed TSK-SOFNN not only automatically generates and prunes the fuzzy rules of TSK-SOFNN but also adjusts the parameters of existing fuzzy rules in TSK-SOFNN. Then, an adaptive self-organizing fuzzy neural network controller (ASOFNNC) system composed of a neural controller and a smooth compensator is proposed. The neural controller using the TSK-SOFNN is designed to approximate an ideal controller, and the smooth compensator is designed to dispel the approximation error between the ideal controller and the neural controller. Moreover, a proportional-integral (PI) type parameter tuning mechanism is derived based on the Lyapunov stability theory, thus not only the system stability can be achieved but also the convergence of tracking error can be speeded up. Finally, the proposed ASOFNNC system is applied to a chaotic system. The simulation results verify the system stabilization, favorable tracking performance, and no chattering phenomena can be achieved using the proposed ASOFNNC system.     

基于单神经元自适应PI 控制器的主动队列管理算法

基于神经网络理论中的神经元模型与学习算法,设计了一种主动队列管理算法SNAPI（Single Neuronbased Adaptive PI controller）．控制器根据系统误差在线调整PI 控制器的控制参数,以适应动态变化的网络参数．运 用Nyquist 稳定判据给出了系统在平衡点附近的局部稳定条件．最后通过仿真检验了SNAPI,并比较了它与使用固 定控制参数的PI 算法的性能．     

基于模糊神经网络的变换器自适应控制方法

提出了一种新型的基于模糊神经网络自适应PI调节电流控制电压型PWM变换器方法.结合了模糊神经网络控制与PI控制器,根据三相电流比较产生的三相电流误差和电流误差变化率,自动调整P、I参数,提高了电流的控制精度和变换器的动态性能.采用MATLAB/Simulink对常规PI控制器和模糊神经网络自适应PI控制器进行了仿真对比.仿真结果表明了采用模糊神经网络自适应PI控制器,其系统输出的误差及误差变化要小,系统的跟踪精度得以提高,动态性能得到改善.     

基于代码属性图及注意力双向LSTM的漏洞挖掘方法

随着信息安全愈发严峻的趋势,软件漏洞已成为计算机安全的主要威胁之一.如何准确地挖掘程序中存在的漏洞,是信息安全领域的关键问题.然而,现有的静态漏洞挖掘方法在挖掘漏洞特征不明显的漏洞时准确率明显下降.一方面,基于规则的方法通过在目标源程序中匹配专家预先定义的漏洞模式挖掘漏洞,其预定义的漏洞模式较为刻板单一,无法覆盖到细节特征,导致其存在准确率低、误报率高等问题;另一方面,基于学习的方法无法充分地对程序源代码的特征信息进行建模,并且无法有效地捕捉关键特征信息,导致其在面对漏洞特征不明显的漏洞时,无法准确地进行挖掘.针对上述问题,提出了一种基于代码属性图及注意力双向LSTM的源码级漏洞挖掘方法.该方法首先将程序源代码转换为包含语义特征信息的代码属性图,并对其进行切片以剔除与敏感操作无关的冗余信息;其次,使用编码算法将代码属性图编码为特征张量;然后,利用大规模特征数据集训练基于双向LSTM和注意力机制的神经网络;最后,使用训练完毕的神经网络实现对目标程序中的漏洞进行挖掘.实验结果显示,在SARD缓冲区错误数据集、SARD资源管理错误数据集及它们两个C语言程序构成的子集上,该方法的F1分数分别达...     

Development of PI training algorithms for neuro-wavelet control on the synchronization of uncertain chaotic systems

This paper investigates a neuro-wavelet control (NWC) system to address the problem of synchronization control of uncertain chaotic systems. In this NWC system, a wavelet neural network (WNN) controller is the principal tracking controller designed to mimic the perfect control law and an auxiliary compensation controller is used to recover the residual approximation error so that the favorable synchronization can be achieved. Moreover, the proportional-integral (PI) training algorithms of the control system are derived from the Lyapunov stability theorem, which are utilized to update the adjustable parameters of WNN controller on-line for further assuring system stability and obtaining a fast convergence. In addition, to relax the requirement of unknown uncertainty bound, a bound estimation law is derived to estimate the uncertainty bound. Finally, some numerical simulations are presented to illustrate the effectiveness of the proposed control strategy. The simulation results demonstrate that the proposed NWC with PI training algorithms can synchronize the chaotic systems more accurately than the other control strategies.     

Adaptive neural network control of flexible joint robots based on feedback linearization

A robust adaptive neural network controller is presented for flexible joint robots using feedback linearization techniques. The controller is based on an approach of using an additional neural network to provide adaptive enhancements to a bask fixed nonlinear controller which can be either neural-network-based or model-used. The weights of the additional neural network are updated on-line based on direct adaptive techniques. It is shown that if Gaussian radial basis function networks are used for the additional neural network, uniformly stable adaptation is assured and asymptotic tracking of the position reference signal is achieved. Intensive computer simulations on a two-link flexible joint robot have shown that the controller can belter handle dynamical model changes and parameter uncertainties than the conventional feedback linearization controller     

Adaptive PI Hermite neural control for MIMO uncertain nonlinear systems

This paper presents an adaptive PI Hermite neural control (APIHNC) system for multi-input multi-output (MIMO) uncertain nonlinear systems. The proposed APIHNC system is composed of a neural controller and a robust compensator. The neural controller uses a three-layer Hermite neural network (HNN) to online mimic an ideal controller and the robust compensator is designed to eliminate the effect of the approximation error introduced by the neural controller upon the system stability in the Lyapunov sense. Moreover, a proportional–integral learning algorithm is derived to speed up the convergence of the tracking error. Finally, the proposed APIHNC system is applied to an inverted double pendulums and a two-link robotic manipulator. Simulation results verify that the proposed APIHNC system can achieve high-precision tracking performance. It should be emphasized that the proposed APIHNC system is clearly and easily used for real-time applications.     

FPGA‐based adaptive dynamic sliding‐mode neural control for a brushless DC motor

In the adaptive neural control design, since the number of hidden neurons is finite for real‐time applications, the approximation errors introduced by the neural network cannot be inevitable. To ensure the stability of the adaptive neural control system, a switching compensator is designed to dispel the approximation error. However, it will lead to substantial chattering in the control effort. In this paper, an adaptive dynamic sliding‐mode neural control (ADSNC) system composed of a neural controller and a fuzzy compensator is proposed to tackle this problem. The neural controller, using a radial basis function neural network, is the main controller and the fuzzy compensator is designed to eliminate the approximation error introduced by the neural controller. Moreover, a proportional‐integral‐type adaptation learning algorithm is developed based on the Lyapunov function; thus not only the system stability can be guaranteed but also the convergence of the tracking error and controller parameters can speed up. Finally, the proposed ADSNC system is implemented based on a field programmable gate array chip for low‐cost and high‐performance industrial applications and is applied to control a brushless DC (BLDC) motor to show its effectiveness. The experimental results demonstrate the proposed ADSNC scheme can achieve favorable control performance without encountering chattering phenomena. Copyright © 2010 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

受约束空间机器人降阶自适应神经网络滑模控制

为了实现受约束空间机器人的高精度控制,提出了一种基于U-K(Udwadia-Kalaba)方程的降阶自适应神经网络滑模控制算法;基于U-K方程,同时考虑受约束空间机器人各个关节的理想约束力与非理想约束力,推导得到详细的动力学方程;考虑到非理想约束力具有不确定性且单独采用滑模控制会出现抖振现象,提出了自适应神经网络滑模控制算法,实现各关节角度、角速度以及非理想约束力的高精度跟踪;针对系统受约束模型,对动力学方程和滑模控制器进行了降阶求解,减少了变量并简化了计算过程;为了验证所提算法的正确性与合理性,以2自由度受约束空间机器人为例进行了仿真验证;仿真结果表明：受约束空间机器人的各关节角度、角速度以及非理想约束力的跟踪误差均低于10^-4量级。