表面粗糙度模糊神经网络在线辨识模型

为解决零件加工中表面粗糙度在线检测困难这一问题,提出一种基于模糊神经网络的零件表面粗糙度在线辨识方法,并以外圆纵向磨削为例,建立表面粗糙度模糊神经网络在线辨识模型.首先研究前人建立的外圆纵向磨削零件表面粗糙度理论公式及经验公式,得出加工中的工件速度、砂轮速度、磨削深度和纵向进给量对零件表面粗糙度有直接影响,并进一步提出以在线测得的加工中工件与砂轮的速度比、磨削深度和纵向进给量作为零件表面粗糙度辨识模型的输入.由于加工过程极其复杂,无法建立加工中零件表面粗糙度与加工参数之间的精确数学模型,故将模糊神经网络引入建模过程中.同时,由于加工中零件表面粗糙度的对数与加工参数的对数存在线性关系,故模型中采用了T-S型模糊推理.此模型应用于实际磨削加工中,建模型精度可达97%,这进一步证明此在线辨识方法的可行性.     

腿轮式机器人自适应控制的研究

给出使机器人处于最优运动状态的运动参数。采用模糊神经网络结合常规PD控制器的方法来进行机器人的运动控制，提出了提取模糊规则的方法。实验结果表明该控制算法结构简单，具有实时性好、精度高、鲁棒性强等特点。     

基于人工神经网络BTA钻削时表面粗糙度的预测

为解决深孔加工中表面粗糙度在线检测困难这一问题,提出一种基于BP神经网络的表面粗糙度在线辨识方法,并以BTA钻削为例,建立表面粗糙度BP神经网络在线辨识模型,并将其引入钻削加工领域。该模型能方便地预测钻削加工参数对加工表面粗糙度的影响,有助于准确认识已加工表面质量随切削参数的变化规律,为切削参数的优选和表面粗糙度的控制提供了依据。实验和仿真结果表明,基于BP神经网络模型能够很好地预测表面粗糙度,对提高加工表面粗糙度具有一定的指导意义。     

基于CCD成像的外圆纵向磨削表面粗糙度在线测量

为了提高外圆磨削加工零件表面粗糙度的测量效率,可以采用在线测量的方法.基于CCD成像技术,利用激光图谱比较法以及图像傅立叶变换后的能量谱,对外圆纵向磨削后的零件表面粗糙度进行非接触式在线测量,并判定加工零件表面粗糙度的等级.使用的测量方法,可以实现在线检测表面粗糙度的目的,达到了预想的效果.     

基于激光三角法的零件表面粗糙度在线测量

介绍了一种零件表面粗糙度的激光在线测量方法,该测量方法具有测量速度快且能够显示被测表面的具体形貌等优点．在测量中引入激光三角测量系统,用无衍射激光光束作光源,用高精度的摄像机作位移传感器,通过计算机数据处理得到表面粗糙度值,使表面粗糙度在线检测成为可能。     

基于数据增强的粗糙度加工实时检测技术研究

在铣削加工时对工件的表面粗糙度进行实时检测的过程中，针对相机运动拍摄获取的图像存在运动模糊以及运动模糊的变化影响表面粗糙度识别的问题，根据图像运动模糊的形成原理，提出一种基于运动模糊算子的数据增强方法，该方法可以生成多种模糊程度的图像。测试结果表明，所述方法可以扩大被训练的CNN模型的模糊适应范围，模型的粗糙度平均识别准确率提高了23.45%。     

磨削表面粗糙度在线检测方法的实验研究

在理论分析和实验研究的基础上，提出了一种在线检测磨削表面粗糙度的新方法，该方法利用声发射(AE）传感器探头与磨削表面摩擦产生的AE信号在线检测磨削表面粗糙度。并通过实际跟踪到测试证明了该方法的可行性。     

车削中表面粗糙度在线预测技术

车削参数直接影响零件的表面粗糙度.文中提出基于神经网络理论的车削表面粗糙度实时预测技术,并给出了实现的步骤和部分参考数据.为实现数控系统的切削参数自动在线优化提供了技术基础.     

基于模糊神经网络的磨料水射流切割质量的研究

基于模糊神经网络建立了磨料水射流精密切割的模型.工件厚度、磨料流量、加工表面的粗糙度和射流压力三个是模糊神经网络的输入,切割速度是模糊神经网络的输出.以JJ-Ⅰ水射流切割机床为实验装置,YL12硬铝作为试件材料进行实验研究,获取样本数据.试件表面粗糙度用TR200粗糙度仪测试.在MATLAB上用样本数据对模型进行训练.用训练好的模型计算给定条件下磨料水射流的切割速度,并以该速度进行线性切割.获得的切割表面粗糙度值基本符合给定的精度要求.     

基于动态模糊神经网络的机床时变定位误差补偿

为提高数控机床的定位精度,提出基于动态模糊神经网络进行数控机床时变定位误差补偿的方法.针对数控机床定位误差影响因素复杂、模糊规则难于获取的情况,改进动态模糊神经网络,使其能够应用于多输入多输出系统,并实现模糊规则的自动在线辨识与生成.通过测量机床温度和定位精度,应用改进后的动态模糊神经网络建立机床时变定位误差预测模型....     

在线微磨损检测技术的应用

本文叙述了在线表面粗糙度检测技术在动态微磨损研究中的应用。通过设计环块试验机模拟部分膜弹性流体动力润滑(PEHL)下的微磨损工况,考察了在线检测技术在润滑条件下对微磨损检测的有效性。该套技术成功地在不停机的情况下测得微磨损过程中表面粗糙度的变化,并通过计算获得了磨损表面的微磨损量。该项技术不仅可以应用到对PEHL下动态磨损的研究,也可应用到一些运动工件表面形貌的检测。     

In-Process Surface Roughness Recognition (ISRR) System in End-Milling Operations

This paper describes a new approach for surface roughness recognition (ISRR) systems to predict surface roughness (Ra) in-process using an accelerometer to measure vibration signals and cutting conditions while end-milling is taking place. The analysis of the data and the model building is carried out using a neural fuzzy system. Experimental results show that the parameters of spindle speed, feedrate, depth of cut, and vibration variables can predict the surface roughness (Ra) effectively. Surface roughness can also be predicted with a 96% accuracy rate by ISRR using the neural fuzzy system.     

On-line surface roughness recognition system using artificial neural networks system in turning operations

In modern manufacturing environments, the quality assurance of machined parts has attracted great attention from manufacturers. The surface roughness of a workpiece is one of the most important factors to consider. The need for developing a surface recognition system that is able to replace stylus-style surface measuring systems has increased to improve the efficiency of production. In this research an on-line surface recognition system was developed based on artificial neural networks (OSRR-ANN) using a sensing technique to monitor the effect of vibration produced by the motions of the cutting tool and workpiece during the cutting process. Different combinations of cutting conditions were conducted to develop an OSRR system for a lathe. In order to determine the direction of the vibration which most significantly affects surface roughness, a triaxial accelerometer was employed. Three directional vibrations which were detected simultaneously by the accelerometer were analyzed using a statistical method. The radial direction vibration was found to be the most significant vibration in turning operations. The accuracy of the developed systems showed that the developed system could predict surface roughness efficiently. The developed system not only proposes a surface recognition system which is alternative to that using a traditional measurement instrument, but also provides an on-line surface recognition system for turning operations.     

高速深切磨削氮化硅陶瓷表面粗糙度的在线监测

从放在工件夹具上的声发射(AE)传感器测得的磨削加工中的AE信号中,提取有关磨削表面粗糙度的信息,用神经网络的方法对高速深切平面磨削工程陶瓷氮化硅工件表面粗糙度进行了在线连续监测.结果表明,该方法基本可行,通过进一步改进,可以用于磨削工程陶瓷工件表面粗糙度的在线监测,为磨削智能化打下基础.     

基于图像清晰度评价的磨削表面粗糙度检测方法

针对当前机器视觉检测粗糙度主要采用图像灰度值信息进行统计分析,没有充分利用色彩信息且忽略了人眼视觉系统主观评判的问题,提出一种基于图像清晰度评价的磨削表面粗糙度检测方法。根据色块在不同等级粗糙度表面上形成的图像清晰度不一样,采用熵函数评价算法和基于色彩相关性的彩色图像清晰度评价算法分别构建清晰度与粗糙度之间的关系模型,论证了基于图像清晰度检测磨削表面粗糙度方法的可行性。试验结果表明,基于图像清晰度检测磨削表面粗糙度是一种可行的粗糙度检测方法,清晰度与粗糙度相关性强,清晰度有随着粗糙度的增大而减小的趋势,且利用色彩相关性的彩色图像清晰度评价算法对磨削表面粗糙度检测具有较好的灵敏性,并且该方法符合人眼视觉系统的主观评价;清晰度算法和主观评价二者结合可快速简易地在线检测工件的整体表面轮廓粗糙度。     

外圆磨削表面粗糙度的BP网络建模与验证

基于零件加工表面粗糙度在线检测困难问题,应用BP网络建模对外圆磨削加工表面粗糙度值进行预测,并通过实验验证所建模型的正确性,同时也验证了实验数据的准确性。     

A Fuzzy-Net-Based Multilevel In-Process Surface Roughness Recognition System in Milling Operations

This paper describes a fuzzy-nets approach for a multilevel in-process surface roughness recognition (FN-M-ISRR) system, the goal of which is to predict surface roughness (Ra ) under multiple cutting conditions determined by tool material, workpiece material, tool size, etc. Surface roughness was measured indirectly by extrapolation from vibration signal and cutting condition data, which were collected in real-time by an accelerometer sensor. These data were analysed and a model was constructed using a neural fuzzy system. Experimental results showed that parameters of spindle speed, feedrate, depth of cut, and vibration variables could predict surface roughness (Ra) under eight different combinations of tool and workpiece characteristics. This neural fuzzy system is shown to predict surface roughness (Ra ) with 90% prediction accuracy during a milling operation.     

基于模糊PI控制的永磁同步电机矢量控制系统

本文采用模糊PI控制代替传统的PI控制,通过检测电机转速的实际值与给定值的偏差和偏差的变化率,在线查表选择适当的PI参数,实现了永磁同步电机的矢量控制。基于matlab/simulink的仿真结果表明,该方法具有良好的静动态特性。     

基于ANFIS的铝合金铣削加工表面粗糙度预测模型研究

分析以往建立表面粗糙度预测模型方法的不足，采用自适应神经模糊推理系统(ANFIS)建立了铝合金铣削加工表面粗糙度预测模型。经检验，该模型预测精度高，泛化能力强，且可简便预测铣削参数对已加工表面的表面粗糙度的影响，有助于准确认识已加工表面质量随铣削参数的变化规律，为切削参数的优选和表面质量的控制提供了依据。     

A digital system for surface roughness analysis of plane and cylindrical parts

This paper describes an on-line system for digital analysis of surfaces where the electrical signal from a surface roughness instrument is converted and input into a desk-top computer which also controls the traversing. Special fixtures integrated with the system and dedicated software permit two- and three-dimensional tracings to be carried out on plane as well as on cylindrical parts. The surface profiles can be plotted in different ways. Roughness parameters, frequency spectra etc, can be computed digitally and all results can be stored. Scratches and irregularities on the surface can be identified and processed separately from the rest of the surface. The desk-top computer is connected to the university mainframe computer through a modem, this being of advantage in connection with graphic data processing. The capability of the equipment has been investigated and results from calibration are presented.