Recurrent Functional-Link-Based Fuzzy Neural Network Controller With Improved Particle Swarm Optimization for a Linear Synchronous Motor Drive

A recurrent functional link (FL)-based fuzzy neural network (FNN) controller is proposed in this study to control the mover of a permanent-magnet linear synchronous motor (PMLSM) servo drive to track periodic reference trajectories. First, the dynamic model of the PMLSM drive system is derived. Next, a recurrent FL-based FNN controller is proposed in this study to control the PMLSM. Moreover, the online learning algorithms of the connective weights, means, and standard deviations of the recurrent FL-based FNN are derived using the back-propagation (BP) method. However, divergence or degenerated responses will result from the inappropriate selection of large or small learning rates. Therefore, an improved particle swarm optimization (IPSO) is adopted to adapt the learning rates of the recurrent FL-based FNN online. Finally, the control performance of the proposed recurrent FL-based FNN controller with IPSO is verified by some simulated and experimental results.      

Recurrent wavelet neural network controller with improved particle swarm optimisation for induction generator system

A recurrent wavelet neural network (RWNN) controller with improved particle swarm optimisation (IPSO) is proposed to control a three-phase induction generator (IG) system for stand-alone power application. First, the indirect field-oriented mechanism is implemented for the control of the IG. Then, an AC/DC power converter and a DC/AC power inverter are developed to convert the electric power generated by a three-phase IG from variable frequency and variable voltage to constant frequency and constant voltage. Moreover, two online trained RWNNs using backpropagation learning algorithm are introduced as the regulating controllers for both the DC-link voltage of the AC/DC power converter and the AC line voltage of the DC/AC power inverter. Furthermore, an IPSO is adopted to adjust the learning rates to further improve the online learning capability of the RWNN. Finally, some experimental results are provided to demonstrate the effectiveness of the proposed IG system.     

Recurrent neural network control for LCC-resonant ultrasonic motor drive

A newly designed driving circuit for the traveling wave-type ultrasonic motor (USM), which consists of a push-pull DC-DC power converter and a two-phase voltage source inverter using one inductance and two capacitances (LCC) resonant technique, is presented in this study. Moreover, because the dynamic characteristics of the USM are difficult to obtain and the motor parameters are time varying, a recurrent neural network (RNN) controller is proposed to control the USM drive system. In the proposed controller, the dynamic backpropagation algorithm is adopted to train the RNN on-line using the proposed delta adaptation law. Furthermore, to guarantee the convergence of tracking error, analytical methods based on a discrete-type Lyapunov function are proposed to determine the varied learning rates for the training of the RNN. Finally, the effectiveness of the RNN-controlled USM drive system is demonstrated by some experimental results.     

动态定量称量包装系统BP神经网络PID控制算法

目的针对动态定量称量包装控制系统具有大惯性、滞后、非线性且无法建立精确数学模型等缺点,研究提高动态定量称量包装系统控制精度的方法。方法提出了一种改进型BP神经网络PID的定量称量包装控制系统,将BP神经网络与PID控制方法相结合,通过神经网络的自学习、加权系数的调整,优化PID控制器参数K_i,K_p,K_d,并将粒子群算法引入到神经网络中作为其学习算法,以有效提高BP神经网络算法的收敛速度。结果仿真和实验结果表明,改进型BP神经网络PID控制响应速度快、超调量较小,系统称量误差得到大幅度减小。结论所述控制方法可以明显提高定量称量控制过程的稳定性、精确性以及鲁棒性。     

基于改进FNN-CCC的双伺服压力机同步控制策略研究

目的 改善双伺服压力机同步控制策略的动态响应性能和鲁棒性,提升双伺服压力机的单轴跟踪精度和双轴同步精度,实现成形过程的高精度位置控制。方法 建立双伺服压力机驱动系统数学模型,分析系统同步误差来源,结合模糊神经网络单轴控制算法,引入迭代学习律,设计一种改进模糊神经网络-交叉耦合(FNN-CCC)同步控制器。基于系统控制模型进行单轴阶跃响应特性与双轴正弦跟随特性仿真,搭建嵌入式双伺服压力机驱动系统试验平台,在偏载干扰条件下进行双轴同步控制试验,验证所提出理论的有效性。结果 仿真结果表明,与模糊控制算法和BP神经网络控制算法相比,该控制器单轴控制算法的超调量分别减少了11.5%和25.5%,调节时间分别减少了48.8%和34.4%,具有更好的动态响应性能。与原控制器相比,改进后的交叉耦合同步控制器最大双轴同步误差降低了65.7%,同步控制精度有所提高。试验结果表明,与传统PID-交叉耦合控制器相比,改进的FNN-CCC控制器有更好的控制性能,在热冲压合模成形阶段,单轴跟踪误差分别减小了81.8%和75.0%,双轴同步误差减小了69.2%。结论 所提出的同步控制策略在偏载干扰条件下具有较好的动态响应性能和鲁棒性,能够使同步误差快速收敛,提高了双伺服压力机驱动系统的单轴跟踪精度和双轴同步控制精度,实现了对双伺服压力机的高精度控制。     

Recurrent fuzzy neural network control for piezoelectric ceramic linear ultrasonic motor drive

In this study, a recurrent fuzzy neural network (RFNN) controller is proposed to control a piezoelectric ceramic linear ultrasonic motor (LUSM) drive system to track periodic reference trajectories with robust control performance. First, the structure and operating principle of the LUSM are described in detail. Second, because the dynamic characteristics of the LUSM are nonlinear and the precise dynamic model is difficult to obtain, a RFNN is proposed to control the position of the moving table of the LUSM to achieve high precision position control with robustness. The back propagation algorithm is used to train the RFNN on-line. Moreover, to guarantee the convergence of tracking error for periodic commands tracking, analytical methods based on a discrete-type Lyapunov function are proposed to determine the varied learning rates of the RFNN. Then, the RFNN is implemented in a PC-based computer control system, and the LUSM is driven by a unipolar switching full bridge voltage source inverter using LC resonant technique. Finally, the effectiveness of the RFNN-controlled LUSM drive system is demonstrated by some experimental results. Accurate tracking response and superior dynamic performance can be obtained because of the powerful on-line learning capability of the RFNN controller. Furthermore, the RFNN control system is robust with regard to parameter variations and external disturbances     

Recurrent Radial Basis Function Network-Based Fuzzy Neural Network Control for Permanent-Magnet Linear Synchronous Motor Servo Drive

We propose a recurrent radial basis function network-based (RBFN-based) fuzzy neural network (FNN) to control the position of the mover of a field-oriented control permanent-magnet linear synchronous motor (PMLSM) to track periodic reference trajectories. The proposed recurrent RBFN-based FNN combines the merits of self-constructing fuzzy neural network (SCFNN), recurrent neural network (RNN), and RBFN. Moreover, it performs the structureand parameter-learning phases concurrently. The structure learning is based on the partition of input space, and the parameter learning is based on the supervised gradient descent method, using a delta adaptation law. Furthermore, all the control algorithms are implemented in a TMS320C32 DSP-based control computer. The simulated and experimental results due to periodic reference trajectories show that the dynamic behaviors of the proposed recurrent RBFN-based FNN control system are robust with regard to uncertainties     

Field-programmable gate array-based recurrent wavelet neural network control system for linear ultrasonic motor

A field-programmable gate array (FPGA)-based recurrent wavelet neural network (RWNN) control system is proposed to control the mover position of a linear ultrasonic motor (LUSM). First, the structure and operating principles of the LUSM are introduced. Since the dynamic characteristics and motor parameters of the LUSM are non-linear and time-varying, an RWNN controller is designed to improve the control performance for the precision tracking of various reference trajectories. The network structure and its on-line learning algorithm using delta adaptation law of the RWNN are described in detail. Moreover, the connective weights, translations and dilations of the RWNN are trained on-line. Furthermore, to guarantee the convergence of the tracking error, analytical methods based on a discrete-type Lyapunov function are proposed to determine the varied learning rates of the RWNN. In addition, an FPGA chip is adopted to implement the developed control algorithm for possible low-cost and high-performance industrial applications. Finally, the effectiveness of the proposed control system is verified by some experimental results.     

An adaptive fuzzy-neural-network controller for ultrasonic motor drive using the LLCC resonant technique

In this study an adaptive fuzzy-neural-network controller (AFNNC) is proposed to control a rotary traveling wave-type ultrasonic motor (USM) drive system. The USM is derived by a newly designed, high frequency, two-phase voltage source inverter using two inductances and two capacitances (LLCC) resonant technique. Then, because the dynamic characteristics of the USM are complicated and the motor parameters are time varying, an AFNNC is proposed to control the rotor position of the USM. In the proposed controller, the USM drive system is identified by a fuzzy-neural-network identifier (FNNI) to provide the sensitivity information of the drive system to an adaptive controller. The backpropagation algorithm is used to train the FNNI on line. Moreover, to guarantee the convergence of identification and tracking errors, analytical methods based on a discrete-type Lyapunov function are proposed to determine the varied learning rates of the FNNI and the optimal learning rate of the adaptive controller. In addition, the effectiveness of the adaptive fuzzy-neural-network (AFNN) controlled USM drive system is demonstrated by some experimental results.     

基于Elman网络的稳像平台速度环设计

稳像平台速度环的性能直接影响成像质量,本文提出了一种基于Elman网络和PD复合控制的自适应逆控制算法.通过对Elman网络模型和控制对象的分析,设计了独立的指令跟踪回路和干扰抑制回路,并将逆控制和PD复合控制思想应用在干扰抑制回路中,实现了Elman网络在线学习和对被控对象的在线辨识.仿真实验结果表明,该方法能有效克服系统慢时变、干扰等非线性因素的影响,增强系统的鲁棒性.     

六自由度运动平台控制系统的神经网络优化

阐述了六自由度运动平台的控制原理，并根据控制系统的特点，提出采用基于RBF和BP神经网络来改进常规PID控制器实现系统控制性能。在该控制系统结构中，提出了在RBF网络辨识Jacobian的基础上，将BP神经网络引入了平台控制系统中PID控制器的控制参数在线整定的算法，最后给出了在MATLAB下的具体仿真算法。     

基于改进BP神经网络的轧机扭振智能控制

针对轧机传动系统扭振控制问题,建立考虑负载转矩的轧机传动系统动力学模型。考虑到扭振模型比较复杂和参数不易测量的特点,提出基于神经网络的状态观测器,并对标准BP网络进行优化处理。设计基于改进BP神经网络状态观测器的智能控制系统,并利用SIMULINK对轧机实例进行仿真。结果表明设计的智能控制系统对轧机传动系统的扭振有良好的控制效果。     

FPGA-based elman neural network control system for linear ultrasonic motor

A field-programmable gate array (FPGA)-based Elman neural network (ENN) control system is proposed to control the mover position of a linear ultrasonic motor (LUSM) in this study. First, the structure and operating principle of the LUSM are introduced. Because the dynamic characteristics and motor parameters of the LUSM are nonlinear and time-varying, an ENN control system is designed to achieve precision position control. The network structure and online learning algorithm using delta adaptation law of the ENN are described in detail. Then, a piecewise continuous function is adopted to replace the sigmoid function in the hidden layer of the ENN to facilitate hardware implementation. In addition, an FPGA chip is adopted to implement the developed control algorithm for possible low-cost and high-performance industrial applications. The effectiveness of the proposed control scheme is verified by some experimental results.     

自动定量称量包装传感器信号去噪算法

目的为了有效滤除自动称量控制系统中的噪声信号,提升称量系统的稳定性和精确度,提出一种基于BP神经网络粒子滤波的称量信号去噪方法。方法在粒子滤波算法中映入了BP神经网络,利用BP神经网络的非线性映射特点,对权值进行分裂和选择,将观测值看作神经网络的目标信号,通过神经网络中的多次训练增大小权值粒子的权重,从而提高粒子滤波算法的多样性。结果仿真和实验结果表明,BP神经网络粒子滤波方法能有效滤除称量包装系统中的噪声信号,提升传感器信号品质。结论该滤波方法大大提升了称量系统的稳定性,有效提高了称量包装的精度,所述控制方法可以明显提高定量称量控制过程的稳定性、精确性以及鲁棒性。     

Wavelet neural network control for linear ultrasonic motor drive via adaptive sliding-mode technique

A wavelet neural network (WNN) control system is proposed to control the moving table of a linear ultrasonic motor (LUSM) drive system to track periodic reference trajectories in this study. The design of the WNN control system is based on an adaptive sliding-mode control technique. The structure and operating principle of the LUSM are introduced, and the driving circuit of the LUSM, which is a voltage source inverter using two-inductance two capacitance (LLCC) resonant technique, is introduced. Because the dynamic characteristics and motor parameters of the LUSM are nonlinear and time varying, a WNN control system is designed based on adaptive sliding-mode control technique to achieve precision position control. In the WNN control system, a WNN is used to learn the ideal equivalent control law, and a robust controller is designed to meet the sliding condition. Moreover, the adaptive learning algorithms of the WNN and the bound estimation algorithm of the robust controller are derived from the sense of Lyapunov stability analysis. The effectiveness of the proposed WNN control system is verified by some experimental results in the presence of uncertainties.     

模糊神经网络在高层建筑横风向振动控制中的应用研究

提出了模糊神经网络方法控制高层建筑横风向风振反应。通过观测部分楼层加速度和控制力输出，建立了模糊神经网络控制器，解决了传统控制中有限的传感器数目对系统振动状态估计的困难．利用模糊神经网络控制器预测结构的控制行为，消除了闭环控制系统中存在的时滞。利用模糊神经网络控制器的自学习能力来确定模糊规则和语言变量隶属函数，解决了土木工程复杂结构模糊控制中，难于依据专家的主观经验来确定模糊控制规则和语言变量隶属函数等困难。模糊神经网络方法的优势在于算法自身的鲁棒性，处理结构非线性、参数不确定性及时变等问题的能力。通过对基准建筑的刚度不确定性分析，讨论了模糊神经网络控制器的鲁棒性。仿真分析表明，模糊神经网络控制策略能有效地抑制高层建筑的横风向风振反应，控制效果略优于LQG控制，而拥有LQG控制不具备的诸多优点。     

拟牛顿优化BP网络盲判决反馈均衡器

针对水声通信严重多途效应导致的码间干扰,利用神经网络良好的非线性拟合能力,将盲判决反馈均衡器结构与神经网络相结合,同时通过拟牛顿算法提升神经网络的收敛速度,提出了一种拟牛顿优化神经网络的盲判决反馈均衡器。用两个单隐层误差反向传播（Back Propagation,BP）网络替换判决反馈均衡器前馈和反馈滤波器,利用拟牛顿迭代计算神经网络权值,在不计算二阶导数的前提下,使用近似矩阵来近似各层网络权值误差性能函数Hessian矩阵的逆矩阵,通过测量各层权值的梯度变化进行迭代计算。应用自动增益控制和锁相环进行幅度和相位修正。仿真结果表明,拟牛顿优化神经网络的盲判决反馈均衡器在水声信道均衡问题中具有更快的收敛速度及更低的误码率。     

基于BP神经网络的真空度测量精度改善方法研究

针对真空度测量精度低的现状,提出一种真空度测量精度改善方法。以热偶规为研究对象,基于BP神经网络设计真空度测量系统。通过设计BP网络结构,采用三种不同的算法对网络权值进行训练,以获得尽可能稳定、精度更高的BP神经网络。对三种算法由测试样本进行测试,三种算法训练的网络能较大程度地提高真空度测量精度,受热丝电流、热丝冷阻干扰影响大大减小;而且最速下降法对应的网络输出值波动较大,附加动量法次之,自适应学习速率调整法对应的输出值波动最小,波动量小于0.01。     

PSO算法结合BP神经网络在传感器静态非线性校正中的应用

将粒子群优化(PSO)算法与BP神经网络相结合,应用在传感器静态非线性特性的校正中.用PSO算法所得到的全局最优值作为BP神经网络的初始权值,训练BP神经网络,训练结束后的神经网络作为传感器的静态特性校正器.应用结果表明,该方法可以提高BP神经网络的精度,并且该神经网络具有良好的泛化能力.     

基于Elman网络的齿轮箱载荷识别研究

为了提高Elman网络的动态性能，有效地解决高阶系统的辨识问题，对Elman网络的结构及学习算法进行了改进，提出了一种新的Elman网络，建立了相应的神经网络载荷识别模型，并用于齿轮箱的载荷识别研究。试验结果表明，该网络模型具有收敛速度快、识别精度高的特点，为载荷识别研究提供了一种新的思路，具有一定的实用价值。