一种新的六自由度并联机器人分散控制方法

结合六自由度并联机器人机构的特点.提出一种新的分散控制方法.首先依据机构特点指出了关节空间内惯性矩阵块对角占优特性,从而将耦合强烈的邻近支路加以整体考虑,即分散控制3个两输入两输出子系统;然后将惯性矩阵的逆分解为块对角矩阵与耦合矩阵之和,从而得到每个子系统的动力学方程;最后针对子系统负载随机构运动而变化的特点引入线性变参数(LPV)控制方法,降低了使用线性定常控制器的保守性.仿真结果表明了所提出方法的有效性.     

基于GWO-BP方法的加速度计动态模型研究

针对高g值加速度计动态模型问题,基于Hopkinson杆的校准系统所测的输入输出数据建立系统模型,提出了GWO-BP神经网络动态建模方法。利用灰狼种群算法优化BP神经网络建立的加速度计动态模型,对模拟输入输出信号进行仿真。最后,利用Hopkinson杆标定系统对加速度计的输入输出进行实测。结果表明,相比于BP神经网络算法,该算法经过优化改进后,求解精度提高了43.6%,证明了该方法的可行性。     

电动Stewart平台分散子系统不确定性加权函数选择

以降低电动Stewart平台两输入两输出子系统不确定性描述的保守性为目的, 提出一种不确定性加权函数选择方法. 首先通过机理分析, 确定以反馈形式来描述平台子系统中低频的结构不确定性, 并得到具有3个待定参数的加权函数. 然后给出标称模型输出与实验数据相匹配的条件, 由此利用实验数据优化加权函数中的待定参数.最后为方便控制器设计, 将系统不确定性描述化为统一的表达形式. 所提方法在描述系统不确定性时, 尽可能将模型中的已知部分分离出来, 并通过实验数据优化加权函数中的待定参数, 从而使得不确定性描述的保守     

基于状态转换的PLC程序模型构建方法

针对可编程逻辑控制器（PLC）程序在进行NuSMV模型检测时需要手工对程序进行建模,不仅浪费人力且容易出错的问题,提出一种基于状态转移的PLC程序模型自动化构建方法。该方法首先分析结构化文本（ST）语言特性并解析ST程序为抽象语法树;其次,在抽象语法树基础上,根据不同的文法结构进行控制流分析生成控制流图;然后,通过数据流分析得到程序依赖图;最后,根据程序依赖图生成NuSMV的输入模型。实验结果表明,所提方法实现了ST程序到NuSMV输入模型的自动化构建,并且构建的NuSMV输入模型既保留了ST程序的原有特性又符合NuSMV模型检测工具输入的规范,与传统手工模型构建方法相比,提高了模型生成的效率和准确率。     

基于改进DFTA的安全苛求系统可靠性分析

针对传统可靠性分析方法容易忽视冗余多态性、可修复性等安全苛求系统特性问题,在形式化的系统可靠性建模中引入可修复因子,提出一种模块化动态故障树分析方法。在动态和静态相结合的模块化定量分析过程中,利用马尔可夫模型和顶事件发生概率逼近算法,有效避免动态故障树分析过程中的状态组合爆炸问题,提高安全苛求系统可靠性分析的可行性和实践效率。     

Behavioral modeling for concurrent dual‐band power amplifiers using 2D hammerstein/wiener models

Behavioral modeling for the concurrent dual‐band power amplifier (PA) is a critical problem in practical applications. The nonlinear distortion in the concurrent dual‐band PA is quite different from that in the conventional single‐band PA. This article analyzes the nonlinearities in the concurrent dual‐band PA and reveals that both input signals in the dual bands are important for the behavioral modeling. The 2D Hammerstein model and 2D Wiener model are proposed for the first time for the concurrent dual‐band PA. They are extended versions of conventional Hammerstein and Wiener structures used in the single‐band PA by including the cross‐band intermodulation in the static nonlinearity block. The proposed 2D models require much less coefficients than the original work of the 2D‐DPD model. Experiments were carried out for an 880 MHz/1960 MHz concurrent dual‐band Doherty PA to demonstrate the effectiveness of the proposed models. The results clearly show that less than ?40 dB normalized mean square errors (NMSEs) are obtained in the dual bands in the behavioral modeling. © 2012 Wiley Periodicals, Inc. Int J RF and Microwave CAE 23: 646–654, 2013.     

融合外部属性的短时交通流预测研究

针对现有交通流量预测算法大多仅考虑常态下的预测,而未考虑天气属性、周围地理属性对预测结果的影响,提出一种融合外部属性的组合预测模型（A-STIGCN）。首先,将外部属性作为路网中路段的属性,同时对路段的属性和交通特征进行建模,得到增强的特征向量。其次,采用图小波变换和自适应矩阵分别提取交通流局部和全局空间特征信息,并借助门控循环单元（GRU）对时间信息的长时记忆能力以提取其时间特性。最后,通过注意力机制来捕获时空动态变化性进行交通流预测。采用深圳出租车轨迹数据、对应天气数据以及POI数据进行预测,研究结果表明：A-STIGCN组合模型预测效果优于传统线性模型及变体模型,与未引入注意力机制的ASTGCN模型相比,MAE降低了约0.131,精度提高了0.068,与未引入外部因素的TGCN模型对比分析,MAPE降低了约0.637%,精度提高了0.079,从而更好地为交通管理提供指导意见。     

基于圆柱体轴向包围盒检测的巷道相交建模

针对岩土工程中三维巷道相交建模复杂、运算时间长的问题,根据巷道的几何特性,提出了一种圆柱体-轴向包围盒的双层包围盒检测方法。该方法能够快速查找出可能相交的三角形单元,结合三维实体布尔运算实现了一种不规则三角形网(TIN)巷道曲面相交的快速构建方法。详细讲述了圆柱体-轴向包围盒(AABB)双层包围盒碰撞检测的基本原理以及实体相交布尔运算中的关键技术,对生成的实体网格提出优化方案。通过工程实例验证,在巷道曲面相交建模中,相比于层次有向包围盒(OBB)算法,圆柱体-AABB双层包围盒在包围盒生成方面效率提高近50%,具有建模简单、检测时间短、顶层检测准确度高等特点。     

Automated time domain modeling of linear and nonlinear microwave circuits using recurrent neural networks

In this article, a recurrent neural network (RNN) method is employed for dynamic time‐domain modeling of both linear and nonlinear microwave circuits. An automated RNN modeling technique is proposed to efficiently determine the training waveform distribution and internal RNN structure during the offline training process. This technique extends a recent automatic model generation (AMG) algorithm from frequency‐domain model generation to dynamic time‐domain model generation. Two types of applications of the algorithm are presented, transient electromagnetic (EM) behavior modeling of microwave structures, and time‐domain envelope modeling of power amplifiers (PA). For transient EM modeling, we consider EM structures with varying material and geometrical parameters. AMG automatically varies the EM structural parameters during training and drives time‐domain EM simulators to generate necessary amount of data for RNN to learn. AMG aims to model the transient behavior with minimum RNN order while satisfying accuracy requirements. In modeling PA behavior, an envelope formulation is used to specifically learn the AM/AM and AM/PM distortions due to third‐generation (3G) digital modulation input. The RNN PA model is able to model these time domain distortions after training and can accurately model the amplifier behavior in both time (AM/AM, AM/PM) and frequency (spectral re‐growth). © 2008 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2008.     

视频编码量化失真估值算法研究

针对量化失真估计算法存在的误差问题,对算法中的DCT系数分布模型进行了改进,提出了基于LAP分布模型的分段建模方法。将DCT系数的尾部数据进行分离,以主体数据的建模结果作为全体数据的分布模型。以均方误差作为量化失真的衡量准则,归纳并推到上述分布模型下的失真估计算法。采用限制量化步长的方法来评估失真估计算法的准确度。实验结果表明,采用LAP分布模型对DCT系数进行分段建模,不仅提高了模型的准确度,还简化了分布模型的复杂度;由此所产生的失真估计算法在复杂度和准确度方面具有很高的兼容性,与传统的LAP失真估计算法相比,准确度有所提高。     

基于非负绞杀与长短期记忆神经网络的动态软测量算法

现代工业过程建模中,生产过程的多变量、非线性及动态性会导致模型复杂度增高且建模精度降低.针对这一问题,将非负绞杀算法(NNG)嵌入长短期记忆(LSTM)神经网络,提出一种基于LSTM神经网络及其输入变量选择的动态软测量算法.首先,通过参数优化生成训练好的LSTM神经网络,利用其出色的历史信息记忆能力处理工业过程中的动态、时滞等问题;其次,采用NNG算法对LSTM网络输入权重进行压缩,剔除冗余变量,提高模型精度,并采用网格搜索法与分块交叉验证对其超参数寻优;最后,将算法应用于某火电厂脱硫过程排放烟气SO2浓度软测量建模,并与其它先进算法进行性能比较.实验结果表明所提算法能有效剔除冗余变量,降低模型复杂度并提高其预测性能.     

Dynamic Modeling and Inverse Optimal PID with Feed-forward Control in <Emphasis Type="Italic">H</Emphasis><Subscript>∞</Subscript> Framework for a Novel 3D Pantograph Manipulator

This paper affords dynamic modeling and control for a new 3D pantograph manipulator. The new manipulator possesses pure decoupled translational motions and it is characterized by large workspace to size ratio, high speed, rigidity, and accuracy. Euler-Lagrange first type method is used to get the dynamic model. However, the resulted dynamic model is too complex to be used in model-based control techniques. Therefore, a simplified nominal plant is proposed. It allows the inverse dynamic solution efficiently. However, an explicit form of the nominal Coriolis and centrifugal matrix cannot be obtained due to the complicated kinematic terms. Considering these dynamic characteristics as well as the required robust trajectory tracking performance of the manipulator, a new controller is proposed. The new controller is called inverse optimal PID with Feed-Forward Control which is designed in H_∞ framework. The new controller has the following merits; robustness, optimality, simple implementation, and efficient execution without the need of explicit forms of dynamic matrices. The extended disturbance in the proposed controller is smaller than that in the inverse optimal PID control (IPID) and contains one type of error contrary to the nonlinear robust motion controller (NRIC). The performance of the proposed controller is compared with those of IPID and NRIC controllers for different trajectories and payloads. The dynamic simulation results via co-simulation of MSC-ADAMS® and MATLAB®/Simulink software prove the robustness of the proposed controller against speed/payload variations. The proposed controller is found to have higher performance compared with IPID and NRIC controllers. These results assure the feasibility of the 3D pantograph manipulator with the proposed controller for pure translational tracking applications.     

Recurrent neural network technique for behavioral modeling of power amplifier with memory effects

A new technique for behavioral modeling of power amplifier (PA) with short‐ and long‐term memory effects is presented here using recurrent neural networks (RNNs). RNN can be trained directly with only the input–output data without having to know the internal details of the circuit. The trained models can reflect the behavior of nonlinear circuits. In our proposed technique, we extract slow‐changing signals from the inputs and outputs of the PA and use these signals as extra inputs of RNN model to effectively represent long‐term memory effects. The methodology using the proposed RNN for modeling short‐term and long‐term memory effects is discussed. Examples of behavioral modeling of PAs with short‐ and long‐term memory using both the existing dynamic neural networks and the proposed RNNs techniques are shown. © 2014 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:289–298, 2015.     

面向工业过程的建模辨识平台的设计与实现

提出了一种面向工业过程的可视化建模辨识平台的设计和实现方法.该平台加载了多种辨识算法,并使用OPC技术和各类工控系统进行数据交互,以实现对复杂工业系统的动态特性测试.基于输入输出数据,获得系统的参数模型或非参数模型.对实际工业对象建模辨识的结果,表明该平台大大提高了建模的效率和精度.     

Quad‐Rotor Modeling and Attitude Control Using State‐Dependent ARX Type Model

A state‐dependent autoregressive with exogenous variables (SD‐ARX) model whose functional coefficients are approximated by sets of radial basis function (RBF) networks is proposed to describe the dynamic behavior of a quad‐rotor in this paper. This model is identified offline and used as an internal predictor of a receding horizon predictive controller to address the quad‐rotor's attitude control issue. In addition, the physical constraints of the system have been also taken into account during the controller design process. The results of real‐time control on a quad‐rotor aircraft illustrate satisfactory modeling accuracy in a large operating range and good performance of control approach proposed in this paper.     

互信息深度稀疏自编码融合DLSTM预测网络

针对工业系统变量之间存在动态和相互关联特性导致关键变量预测精度降低问题,提出一种互信息深度堆叠稀疏自编码数据特征网络（mutual information-deep stack sparse auto-encoder,MI-DSSAE）结合深度长短期记忆（deep LSTM,DLSTM）预测模型。MI-DSSAE模型对稀疏编码器改进,采用堆叠稀疏编码器结构,引入互信息作为重构损失权重,对多个稀疏编码器隐层迁移并微调。预测部分采用深度DLSTM网络结构,用双层Bi-LSTM结构对序列数据的动态变化特性双向捕捉,将输出数据输入到普通LSTM进行记忆处理,进行全连接层加权预测关键质量变量。采用流程化工业案例脱丁烷塔的C4含量对提出的模型验证,同时对比RNN、LSTM、GRU模型以及MI-DSSAE-RNN、MI-DSSAE-LSTM、MI-DSSAE-GRU等模型,通过RMSE、R2和MAE多项回归误差指标对比分析,验证MI-DSSAE-DLSTM模型的有效性。     

基于梯度提升回归树的短时交通流预测模型

短时交通流预测是交通流建模的一个重要组成部分,在城市道路交通的 管理和控制中起着重要的作用。然而,常见的时间序列模型(如ARIMA)、随机森林(RF)模型在交通流预测方面由于被构建模型产生的残差和输入变量所影响,其预测精度受到限制。针对该问题,提出了一种基于梯度提升回归树的短时交通预测模型来预测交通速度。首先,模型引入Huber损失函数作为模型残差的处理方法;其次, 在输入变量中考虑预测断面受到毗邻空间因素和时间因素相关性的影响。模型在训练过程中通过不断调整弱学习器的权重来纠正模型的残差,从而提高模型预测的精度。利用某城市快速路的交通速度数据进行实验,并使用MSE和MAPE等指标将本文模型与ARIMA模型和随机森林模型进行对比,结果表明,文中所提模型的预测精度最好,从而验证了模型在短时交通流预测方面的有效性。     

A multi-variate Hammerstein model for processes with input directionality

A new formulation of a block-structured model based on the Hammerstein operator is presented for the identification of multi-variate systems with input directionality. In contrast to the existing formulations for multi-variate Hammerstein models, the proposed structure offers the possibility to independently model the dynamic and nonlinear characteristics of the system and at the same time preserves the possibility to use the new efficient algorithms developed for the identification of single input Hammerstein models. Further, the formulation allows for a representation of arbitrary static nonlinear coupling of input variables with a considerably lower amount of parameters compared to existing formulations. The new model structure is applied to the identification of a fluid catalytic cracking (FCC) unit and significantly outperforms all previous multi-variate Hammerstein model structures by reducing the prediction error by over 50%.     

基于改进BP网络8/6极SRM非线性建模的研究

针对开关磁阻电机(SRM)磁化曲线高度饱和、非线性的特点,提出一种基于改进的BP神经网络建立开关磁阻电机模型的方法。该方法构造了一个将连接权值变为参数可调函数的BP神经网络。通过分析开关磁阻电机磁链与转矩特性获得神经网络的训练样本,经过训练,实现开关磁阻电机非线性建模,并在Matlab/Simulink中建立开关磁阻电机控制系统(SRD)仿真模型。仿真与实验结果的对比,证明了此建模方法可行。与传统BP神经网络建模相比,该方法节约了计算时间,具有很强的泛化能力和较高精度,有效地提高了收敛速度。     

A Highly Accurate Model-Free Motion Control System with a Mamdani Fuzzy Feedback Controller combined with a TSK Fuzzy Feed-forward Controller

In this paper, a new intelligent robot motion control architecture – a highly accurate model-free fuzzy motion control- is proposed in order to achieve improved robot motion accuracy and dynamic performance. Its architecture combines a Mamdani fuzzy proportional (P) and a conventional integral (I) plus derivative (D) controller for the feedback part of the system, and a Takagi-Sugeno-Kang fuzzy controller for the feed-forward, nonlinear part. The fuzzy P + ID controller improves the performance of the nonlinear system, and the TSK fuzzy controller uses a TSK fuzzy inference system based on extended subtractive- clustering method which integrates information on joint angular displacement, velocity and acceleration for torque identification. The advantage of this kind of model-free control is that it uses the information directly from the input/output of the nonlinear system, without any complex robot model computation, in order to decrease the control system’s sensitivity to any dynamical uncertainty. Furthermore, parametric search for clustering parameters in extended subtractive clustering secures the high accuracy of the system identification. Consequently, this proposed model-free fuzzy motion control benefits from the advantages of two kinds of fuzzy system. It not only incorporates flexible design, good performance and simple conception but also ensures precise motion control and great robustness. Comparisons with other intelligent models and results from numerical studies on a 4-bar planar parallel mechanism show the effectiveness and competitiveness of the proposed control.