CMP过程多变量免疫预测R2R控制方法

为了解决多输入多输出和产品质量不易在线测量的化学机械研磨(chemical mechanical polishing,CMP)过程R2R(run-to-run)控制的难题,提出了一种基于贝叶斯最小二乘支持向量机(Bayes least squares support vector machine,BLS-SVM)预测模型和克隆选择免疫多目标滚动优化算法的CMP过程多变量R2R预测控制器BSVMPR2R.由LS-SVM和贝叶斯证据框架(Bayes evidence framework,BEF)方法分别构建材料去除率(material removal rate,MRR)和晶圆内非均匀度(within-wafer nonuniformity,WIWNU)的BLS-SVM预测模型,解决了线性预测模型的失配问题;通过预测误差对后续批次过程扰动和漂移进行在线估计实现反馈校正,提高了预测模型精度;将多变量控制问题转化为基于2个预测模型的多目标优化问题,由克隆选择免疫多目标滚动优化算法求解最优控制律提高了控制精度.仿真结果表明,BSVMPR2R控制器的性能优于双指数加权移动平均(double exponential weighted moving average,dEWMA)多变量控制器,抑制了CMP过程扰动和漂移的影响,显著降低了MRR和WIWNU的均方根误差.     

基于改进的免疫克隆算法的PID参数优化

依据PID控制器的控制原理,结合人工免疫算法和克隆选择原则,提出了一种新的基于周期变异的免疫克隆算法,并基于此算法在线优化PID控制参数,仿真结果表明控制输出能快速平稳地跟随期望输出值,系统响应可以获得良好的实时性、稳定性和较高的控制精度。     

基于神经网络的直线电磁阀式怠速系统预测控制方法研究

基于汽油发动机怠速系统的非线性、时变性和不确定性等特点,构建了神经网络与预测算法相结合的控制系统。利用预测控制算法的滚动优化和反馈校正的特性,采用神经网络建立系统的动态模型作为预测控制器的预测模型;提供怠速系统的开环输入输出数据离线训练神经网络,再在线对神经网络模型的权值和阀值进行调整,获得精确的预测模型,实现了对怠速系统的自适应控制。仿真结果表明,这种方法有效地提高了发动机怠速系统的控制精度、可靠性和转速的稳定性。     

基于PSO的神经网络机械臂自校正控制

粒子群优化算法(PSO)基于群体的演化算法,本质上是一种随机搜索算法,并能以较大概率收敛到全局最优.针对非线性机械臂系统,利用径向基函数(RBF)神经网络和PID控制器作为混合控制器,运用PSO算法对神经网络参数进行在线学习优化,同时在PID控制器的辅助下对机械臂系统进行在线自校正控制.计算机仿真表明,该控制器具有较高的控制精度和响应速度,可以满足机械臂工作要求.     

基于灰色支持向量机的汽车制动系统故障诊断与预测

分析了灰色预测方法和支持向量机各自的优缺点,提出了将二者相结合的一种新的预测模型-灰色支持向量机预测模型。为了提高预测精度,用粒子群算法对灰色支持向量机的相关初始化参数进行优化,用优化后的模型对汽车制动系统故障进行预测与诊断。实验结果表明文章所提出的预测模型有效可靠,为提高预测精度提供了新的途径。     

基于粒子群算法的车道保持模型预测控制研究

针对模型预测控制(MPC)在解决车道线偏离过程中遇到的偏差过大,计算时间长的问题,提出基于粒子群算法的车道保持模型预测控制方法,其采用模型预测控制来有效的控制车辆,并利用粒子群算法对模型预测控制的控制时域NP和预测时域Nc进行优化,减小模型预测控制的迭代次数。首先,利用粒子群算法(PSO)对模型预测控制进行优化,使目标函数达到最小值就停止迭代,减少计算量;然后利用CarSim和Simulink对优化后的车道保持控制器进行联合仿真,测试控制效果。仿真结果表明,与文中所提的其他三种方法相比,本控制方法能够更准确地控制车辆在车道线上行驶,可将控制精度提高约16%。另外,基于粒子群算法优化模型预测控制将控制精度提高的同时,兼顾了汽车行驶的稳定性以及控制的平缓性。     

未知自由曲面三坐标测量新方法

三坐标测量机(CMM)通常难于实现对未知自由曲面的自动测量,首先需要人工进行测量路径规划,手动控制CMM测量,这种方法不但耗时且测量精度不高。本文提出了一种实时在线灰色预测模型用于控制三坐标测量机的测量。该方法分两个步骤进行:初始化数据测量和实时在线灰色预测自动测量。初始化数据测量主要完成预测用原始数据系列的定义,实时在线灰色预测自动测量则根据原始数据系列预测后续点来控制CMM进行测量。采用这种方法免去了对整个曲面进行测量路径规划,可快速准确地测量自由曲面上的数据而且明显减少测量时间。     

基于极限学习机的板形预测模型

高效地建立起板形模型有利于提高板带轧制过程中的板形精度和有效实现板形控制。提出了一种基于极限学习机(ELM)的板带轧制过程中板形预测模型,不但可以简化参数选择过程,在核函数选择上可以根据训练样本值自动选择无须手动选择,而且可以提高模型的训练速度。结合铝板带四连轧机组在线实测数据进行模型训练,实现对轧制过程板形的预测且得到实验验证。本算法与支持向量机(SVM)模型预测对比,在训练样本数量较少的情况下,模型预测精度都能达到期望精度值,且具有同样甚至更高的预测精度,还具有急速的特点和更强的泛化能力。     

灰色预测模糊PID控制在调节阀智能定位系统中的应用

针对气动调节阀系统大惯性、纯滞后和时变性的特点,建立了调节阀执行机构的二阶加纯滞后模型,在此基础上设计了基于灰色预测模糊PID算法的复合控制器。PID模块作为该复合算法的基础,用来减小系统偏差,提升动态性能;模糊控制模块对系统偏差及其变化率进行模糊处理,输出值作为PID参数的调整量,实现在线调整控制参数,克服时变性对系统的影响;灰色预测模块对系统输出数据序列进行提取并预测未来发展趋势以进行系统的“超前控制”,进一步解决气动系统滞后和稳态性能差的问题。基于灰色预测模糊PID算法的复合控制器将灰色预测模型、模糊控制和比例微积分算法相结合,可实现阀门位置的高精度调节与智能控制。仿真结果表明,灰色预测模糊PID控制算法相比常规PID以及模糊PID具有更快的响应速度、更高的调节精度以及更好的稳态性能。     

改进GM-Markov模型在道路交通事故预测中的应用研究

针对随机波动性数据对灰色GM(1.1)模型预测精度的影响问题,提出了基于BX数据处理方法与马尔可夫链理论的灰色预测模型(BXGrey-Markov模型)。首先,引入BX数据生成法对原始数据进行处理,以弱化原始数据之间的随机性。在灰色预测方法的基础上,引入马尔可夫链预测理论,建立了灰色马尔可夫预测模型,它是将灰色预测模型与马尔可夫预测方法优化组合,灰色预测模型用于预测随机序列数据的总体发展趋势,而用马尔可夫链模型预测各数据在总体趋势下的随机波动性变化,得到随机时间数列趋势预测模型的解。通过上海市交通事故预测实际数据进行了验证表明:灰色马尔可夫预测模型预测精度高于GM(1,1)模型的预测精度。GM(1,1)模型的平均预测精度为42.29%,BX GM(1,1)-Markov模型的平均预测精度为86.9%。     

带料纠偏的模糊预测控制

带料纠偏是高度非线性过程,传统的模型预测控制(MPC)无法有效地处理这种过程.模糊神经网络(FNN)方法可以实现非线性过程模型.通过测量得到的数据作为样本来训练神经网络.预测准确度由前馈网络的插值能力保证.多维搜索技术用来解决非线性最优化问题,最优结果被嵌入BP神经网络预测控制器中.BP神经网络的快速计算能满足实时控制需要.带料纠偏试验结果已经证明了FNN预测控制的有效性.     

Fuzzy model predictive control of non-linear processes using convolution models and foraging algorithms

In this paper, a fuzzy model predictive control (FMPC) approach is introduced to design a control system for nonlinear processes. The proposed control strategy has been successfully employed for representative, benchmark chemical processes. Each nonlinear process system is described by fuzzy convolution models, which comprise a number of quasi-linear fuzzy implications (FIs). Each FI is employed to describe a fuzzy-set based relation between control input and model output. A quadratic optimization problem is then formulated, which minimizes the difference between the model predictions and the desired trajectory over a predefined predictive horizon and the requirement of control energy over a shorter control horizon. The present work proposes to solve this optimization problem by employing a contemporary population-based evolutionary optimization strategy, called the Bacterial Foraging Optimization (BFO) algorithm. The solution of this optimization problem is utilized to determine optimal controller parameters. The utility of the proposed controller is demonstrated by applying it to two non-linear chemical processes, where this controller could achieve better performances than those achieved by similar competing controller, under various operating conditions and design considerations. Further comparisons between various stochastic optimization algorithms have been reported and the efficacy of the proposed approach over similar optimization based algorithms has been concluded employing suitable performance indices.     

Online optimization of fuzzy-PID control of a thermal process

A constrained optimization of a simple fuzzy-PID (PID-proportional integral derivative) system is designed for the online improvement of PID control performance during productive control runs. The cost function design yields a desirable balance between rise time, setpoint overshoot, and settling time to the setpoint. The constraints determined by simulation yield control performance no worse than the existing control performance during online optimization. The optimized fuzzy-PID system is compared to a similarly optimized PID controller and a benchmark model predictive controller.     

Grey fuzzy PI control for packing pressure during injection molding process

This study presents a grey fuzzy PI (GFPI) controller for packing pressure control during the injection process. The novel controller was designed for solving the problems of large overshoot, static error, and long delay time on servo motor-driven injection molding machines. Based on reasonable assumptions, a mathematical model of injection system was established. According to the nonlinear, severe interferences, and long delay time characteristics in injection process, this paper integrates predictive grey system, robust fuzzy ratiocination, and PI control. Using these mathematical model and control algorithms, a GFPI controller is implemented into an MCU using C programming techniques. The integral discrete PID controller and solid fuzzy controller were realized for contrast experiments. The experimental results show that GFPI controller had better performance on reducing overshoot and static error, increasing both response rate and repeatable accuracy. Such a developed technology would provide helpful references for designing the controller of energy-saving servo motor-driven injection molding equipment.     

基于参数优化的连铸结晶器振动位移系统 复合控制研究

本文以伺服电机驱动的连铸结晶器振动位移控制系统为研究对象,针对系统工艺控制中要求伺服电机转速单方向、变 角速度转动,同时考虑系统控制器参数的选取大多依靠经验等问题,提出了一种基于前馈控制与参数优化的 PID 反馈控制相结 合的复合跟踪控制策略。 首先,根据伺服电机驱动的连铸结晶器振动位移系统特性,建立了伺服电机输出转速与振动位移之间 的近似数学模型。 其次,针对伺服电机单方向转动工艺约束条件,确定结晶器振动位移系统以转速补偿作为前馈控制器,保证 系统控制器输出大于零. 再次,针对振动位移系统控制器参数大多依靠经验选取的问题,提出采用一种改进的飞蛾火焰优化算 法优化 PID 控制器参数的策略,以实现结晶器振动位移高精度跟踪控制。 最后,通过仿真与实验验证所提方法的有效性,实验 结果表明:优化后的振动位移调整时间缩短了 0. 3 s,振动位移跟踪相对误差减小了 1. 8% 。     

Design and implementation of adaptive PI control schemes for web tension control in roll-to-roll (R2R) manufacturing

In this paper, two adaptive Proportional-Integral (PI) control schemes are designed and discussed for control of web tension in Roll-to-Roll (R2R) manufacturing systems. R2R systems are used to transport continuous materials (called webs) on rollers from the unwind roll to the rewind roll. Maintaining web tension at the desired value is critical to many R2R processes such as printing, coating, lamination, etc. Existing fixed gain PI tension control schemes currently used in industrial practice require extensive tuning and do not provide the desired performance for changing operating conditions and material properties. The first adaptive PI scheme utilizes the model reference approach where the controller gains are estimated based on matching of the actual closed-loop tension control systems with an appropriately chosen reference model. The second adaptive PI scheme utilizes the indirect adaptive control approach together with relay feedback technique to automatically initialize the adaptive PI gains. These adaptive tension control schemes can be implemented on any R2R manufacturing system. The key features of the two adaptive schemes is that their designs are simple for practicing engineers, easy to implement in real-time, and automate the tuning process. Extensive experiments are conducted on a large experimental R2R machine which mimics many features of an industrial R2R machine. These experiments include trials with two different polymer webs and a variety of operating conditions. Implementation guidelines are provided for both adaptive schemes. Experimental results comparing the two adaptive schemes and a fixed gain PI tension control scheme used in industrial practice are provided and discussed.     

基于改进PSO算法的电液位置伺服系统MRAC跟踪控制

针对电液位置伺服系统控制性能不佳的问题,提出一种基于改进PSO算法优化的模型参考自适应(Model Reference Adaptive Control,MRAC)跟踪控制方法。首先,建立电液位置伺服系统数学模型,设计出模型参考自适应控制器;其次,分析PSO算法、APSO算法在参数寻优过程中的不足,提出一种改进的PSO算法;最后,将改进的PSO算法用于模型参考自适应控制器以改善其控制性能。结果表明,改进PSO算法优化的模型参考自适应控制具有响应速度快、跟踪精度高的优点。     

Improved design of constrained model predictive tracking control for batch processes against unknown uncertainties

In this paper, an improved constrained tracking control design is proposed for batch processes under uncertainties. A new process model that facilitates process state and tracking error augmentation with further additional tuning is first proposed. Then a subsequent controller design is formulated using robust stable constrained MPC optimization. Unlike conventional robust model predictive control (MPC), the proposed method enables the controller design to bear more degrees of tuning so that improved tracking control can be acquired, which is very important since uncertainties exist inevitably in practice and cause model/plant mismatches. An injection molding process is introduced to illustrate the effectiveness of the proposed MPC approach in comparison with conventional robust MPC.     

Model predictive control for systems with fast dynamics using inverse neural models

In this work, a novel model predictive control (MPC) scheme is introduced, by integrating direct and indirect neural control methodologies. The proposed approach makes use of a robust inverse radial basis function (RBF) model taking into account the applicability domain criterion, in order to provide a suitable initial starting point for the optimizer, thus helping to solve the optimization problem faster. The performance of the proposed controller is evaluated on the control of a highly nonlinear system with fast dynamics and compared with different control schemes. Results show that the proposed approach outperforms the rivaling schemes in terms of response; moreover, it solves the optimization problem in less than one sampling period, thus effectively rendering MPC-based controllers capable of handling systems with fast dynamics.     

绗缝加工企业信息化构建

随着绗缝企业规模的扩大,企业的信息化建设势在必行。针对绗缝企业生产流程控制和优化问题进行了分析和思考,从数据驱动控制理论的角度出发,考虑采用预测控制,并结合子空间方法以及现场总线技术等方法,提出了一种绗缝生产企业信息化质量管理系统解决方案。以基于数据驱动控制方法为核心,以预测控制为技术手段来建立整体控制系统。底层生产设备的控制上采用预测控制器,上层的企业整体控制系统考虑采用子空间预测控制构建信息化管理系统。