In-situ neural network process controller for copper chemical mechanical polishing

Process control is one of the key methods to improve manufacturing quality. This research proposes a neural network based run-to-run process control scheme that is adaptive to the time-varying environment. Two multilayer feedforward neural networks are implemented to conduct the process control and system identification duties. The controller neural network equips the control system with more capability in handling complicated nonlinear processes. With the system information provided by this neural network, batch polishing time (T) an additional control variable, can be implemented along with the commonly used down force (p) and relative speed between the plashing pad and the plashed wafer (v). Computer simulations and experiments on copper chemical mechanical polishing processes illustrate that in drafting suppression and environmental changing adaptation that the proposed neural network based run-to-run controller (NNRTRC) performs better than the double exponentially weighted moving average (d-EWMA) approach. It is also suggested that the proposed approach can be further implemented as both an end-point detector and a pad-conditioning sensor.     

基于灰色模型的CMP过程免疫预测R2R控制

针对化学机械研磨(chemical mechanical polishing,CMP)过程非线性、时变、产品质量不能在线测量的特性,为了提高CMP过程R2R(Rum-to-Run)控制的精度,提出了一种基于灰色模型和克隆选择免疫算法的CMP过程R2R预测控制器GI-PR2R。通过离线测量获得历史批次少量数据,构建CMP过程的在线灰色GM(1,N)预测模型,解决了复杂CMP过程难以建立精确数学模型的难题提高了预测模型的精度。通过基于克隆选择免疫算法的CMP过程预测控制的滚动优化,避免了基于导数的优化技术易陷入局部最优的问题,进而提高了控制精度。仿真结果表明,CMP过程GIPR2R控制器的控制精度优于EWMA(exponentially weighted moving average)方法,有效抑制了过程漂移,减小了不同批次间产品的差异,材料去除率(material removalrate,MRR)的均方根误差在总批次与控制目标不同这2种情况下分别降低了18.09%和16.84%。     

A neural-Taguchi-based quasi time-optimization control strategy for chemical-mechanical polishing processes

Besides the major factors such as the down force, back pressure and the rotating speed of wafer carrier, effect of polishing time is also an important issue in CMP processes. In this study, a neural-Taguchi method based on a cost-effective quasi time-optimisation technique for chemical-mechanical polishing (CMP) processes is developed. The key concept of this new technique is that an optimal process parameter set is obtained through a neural-network-simulated CMP process model. Under such an optimal parameter set, the desired material removal rate within-wafer-nonuniformity can be reached with the optimal polishing time. It has been proved by experiment that the proposed method can offer a better polishing performance while reducing the polishing time by 1/3.     

Nano particles’ behavior in non-Newtonian slurry in mechanical process of CMP

Thin fluid film is thought to be formed between the wafer surface and the pad asperity. Hydrodynamic pressure on the surface asperity is periodically generated when particles are passing through it. Fatigue fracture occurs under the effect of periodic pressure, and the fatigue begins from the top to the bottom of the asperity. The removal rate is calculated based on the energy-balance fracture theory. Particle size and its relative velocity are important parameters that affect the polishing effect. Using the multiphase model and the power–law viscosity model of the slurry, particle’s velocity and its distribution in the slurry are numerically calculated. The results indicate that the slurry film thickness needs to be in the same order of the particle size that the particle can generate effective hydrodynamic pressure to remove the asperity materials.     

工序质量控制系统的研究

对工序质量控制系统的实现进行了研究.系统可生成质量控制图表对工序质量进行控制.     

过程控制综合实验测控装置的研制

介绍了一套我们自己研制的过程控制综合实验测控装置。该装置以昌辉SWP智能仪表为核心。采用模块化设计,可方便的组合成各种实验。该系统通过RS485总线。利用开物controX2000组态软件。可对实验进行实时监控。     

Effects of wireless packet loss in industrial process control systems

Timely and reliable sensing and actuation control are essential in networked control. This depends on not only the precision/quality of the sensors and actuators used but also on how well the communications links between the field instruments and the controller have been designed. Wireless networking offers simple deployment, reconfigurability, scalability, and reduced operational expenditure, and is easier to upgrade than wired solutions. However, the adoption of wireless networking has been slow in industrial process control due to the stochastic and less than 100% reliable nature of wireless communications and lack of a model to evaluate the effects of such communications imperfections on the overall control performance. In this paper, we study how control performance is affected by wireless link quality, which in turn is adversely affected by severe propagation loss in harsh industrial environments, co-channel interference, and unintended interference from other devices. We select the Tennessee Eastman Challenge Model (TE) for our study. A decentralized process control system, first proposed by N. Ricker, is adopted that employs 41 sensors and 12 actuators to manage the production process in the TE plant. We consider the scenario where wireless links are used to periodically transmit essential sensor measurement data, such as pressure, temperature and chemical composition to the controller as well as control commands to manipulate the actuators according to predetermined setpoints. We consider two models for packet loss in the wireless links, namely, an independent and identically distributed (IID) packet loss model and the two-state Gilbert-Elliot (GE) channel model. While the former is a random loss model, the latter can model bursty losses. With each channel model, the performance of the simulated decentralized controller using wireless links is compared with the one using wired links providing instant and 100% reliable communications. The sensitivity of the controller to the burstiness of packet loss is also characterized in different process stages. The performance results indicate that wireless links with redundant bandwidth reservation can meet the requirements of the TE process model under normal operational conditions. When disturbances are introduced in the TE plant model, wireless packet loss during transitions between process stages need further protection in severely impaired links. Techniques such as retransmission scheduling, multipath routing and enhanced physical layer design are discussed and the latest industrial wireless protocols are compared.     

Recent Advances in Machining of Silicon Wafers for Semiconductor Applications

Silicon wafers are used world-wide for the production of microchips. Silicon is a hard and brittle material. Conversion of silicon ingots into polished wafers requires much processing including machining and chemical processing. The machining is critical to high-quality standards. With the development of new components, the eletronic industries require hgher standards for total thickness variation and also wafer warp. This paper focuses on the different machining methods available for silicon processing.     

小批量生产条件下的统计过程控制研究

从小批量生产的定义入手，分析传统的休哈特控制图应用在小批量生产条件下存在的问题及局限性。对目前小批量生产质量控制的方法进行简要分析。在此基础上，提出一种适合于小批量生产质量控制的新思路，并用实际数据对提出的方法与传统的休哈特控制图方法进行了对比，说明这种新思路应用在小批量生产过程中的可行性和有效性。     

涡轮盘数控仿形抛光中刀具路径生成方法的研究

选用FAROGagePlus便携式三坐标测量机测量涡轮盘实际表面轮廓尺寸,利用CMM对其轮廓数据进行采集,运用程序处理方式实现采样数据点的规则化处理,根据处理后的测点数据生成刀具的路径。     

过程控制中测量系统误差的性能影响分析

从控制图的建立和监控两个不同阶段的角度分别讨论了测量系统误差对过程质量控制监控性能的影响.以平均运行长度作为过程控制性能评价的指标,分析了两种不同类型的测量误差对监控性能的干扰模式.最后通过一个算例分析测量系统误差的危害性,表明一个好的测量系统在过程监控中的重要性.     

Application of 3-D finite element method using Lagrangian formulation to dilution control in laser cladding process

In this study a three-dimensional finite element model is presented for precisely simulating laser cladding process with a focus on dilution control. Dilution is referred to as an important quality index in the laser cladding process, indicating the contamination level of the properties of clad layer by substrate metals. As regards a good quality of laser clad layer, low dilution as well as metallurgical bond of interface are prerequisite, so the dilution control is essential in the process. Unfortunately despite of its importance, to date, any practically usable computation techniques have not been reported, which is a motivation of this work. In the paper, proposing a simulation procedure, we develop and verify a code of finite element method with Lagrangian view-point. Following the procedure, the dilution control is precisely estimated. The effects of process parameters on the dilution of clad layer are quantitatively discussed by the numerical and experimental means.     

基于信息优化的加工过程神经网络控制

为了提高加工过程生产率和保证加工精度,以加工过程的恒切削力控制作为研究对象,将信息论原理和神经网络智能控制理论应用于加工过程控制,以信息熵作为加工过程智能控制系统的性能测度能统一各级性能指标,将神经网络作为加工过程控制输入和系统输出的信息传输通道,确定了神经网络基于信息优化的目标函数,推导出了信息优化的三层BP神经网络学习算法,提出了恒力切削过程中基于信息优化的神经网络控制系统框架.通过加工过程的仿真实例证明,与传统自适应神经网络控制方法相比,基于信息优化的神经网络控制方法收敛精确,速度快,振荡小,系统超调量小,具有较好的综合性能.研究结果为信息理论应用于加工过程控制提供了有效途径.     

A hybrid control scheme to enhance the detection ability of process mean shifts

The hybrid use of Robert’s EWMA and Crosier’s cumulative sum (CUSUM) control schemes is shown to result in a control scheme with high-performance detection of any magnitude of process mean shifts. The parameters of the hybrid scheme are found by adapting the average run length (ARL) to those of a set of locally optimal EWMA schemes in the best way. In this report, an enhancement to the hybrid scheme is considered. First, the ARLs of the hybrid scheme are derived by using the extrapolation method proposed by Waldmann. Second, an optimization of parameter settings is stated and solved. An extensive comparison shows that the ARL properties of the hybrid scheme are comparable to those of the combined Shewhart-CUSUM scheme. Finally, numerical results and examples are presented to demonstrate the efficiency of the hybrid scheme.     

神经内模优化控制策略在配煤过程中的应用

采用径向基函数神经网络建立了配煤过程的非线性动态模型,并由此提出配合煤灰分的神经内模优化控制策略,设计了基于Modbus Plus网络技术的分布式控制系统。在选煤厂自动配煤系统的实际应用结果表明,该文提出的控制算法能有效地控制配合煤灰分。     

流程工业调度与控制集成系统的数据采集与传输

该文分析了数据采集系统的结构与数据采集方式,提出了实时数据库与DCS系统之间实现物理隔离的数据采集方法,研究了基于OPC技术的异构数据集成解决方案,探讨了数据采集系统中实时数据的传输与通信方法,为实现流程工业生产调度与控制系统的集成提供了一种新的数据采集与处理方法。     

污水生化处理过程中溶解氧的非线性控制

溶解氧浓度是污水生化处理过程中的一个重要参数,传统的控制方法并不能取得理想的控制效果.由于溶解氧过程模型中的呼吸率不易卣接得到,将神经网络建模技术与溶解氧过程数学模型相结合得到溶解氧的混合非线性过程模型.针对所得到的混合非线性过程模型,提出了一般模型的非线性控制方法.该方法不需要任何线性化和模型简化工作,所得到的溶解氧的混合非线性过程模型可以直接整合到控制器的设计中.仿真结果验证了该设计方法的有效性和正确性.     

机械加工过程质量控制集成模型研究与实现

在分析现有质量控制方法特点和总结传统机械加工过程质量控制模式存在的不足基础上不足提出了一种以机械加工序为控制对象、以保民改进产品加工质量为目标的机械加工过程质量控制集成模型。该模型实现了机械加工过程的质量数据采集、处理与识别、分析与统计、决策与改进的集成。同时,介绍了基于机械加工过程质量控制集成模型的系统框架及其实现。     

先进控制技术是提高石油化工企业经济效益的有效途径

文章对先进控制技术的发展进行了分析,并结合实际阐述了先进控制技术在石油化工企业的应用情况,提出了进一步应用的建议。     

数控加工中表面粗糙度的影响因素及其控制

艰数控加工过程中的普通外圆车削加工和用球头铣刀平面铣削为研究对象,建立这两种典型加工过程中表面粗糙度的数学模型。根据数学模型分析数控加工过程中表面粗糙度的影响因素,并研究影响因素的选择方法及合理的取值范围。