基于岭回归的数控机床温度布点优化及其热误差建模

提出一种基于岭回归分析的数控机床温度布点优化方法.数控机床热误差建模一般采用多元线性回归方法,在多元线性回归模型中,隐含着要求解释变量之间无强相关性的假定.然而在实际的建模中,各自变量与因变量之间的相互关系并不与简单相关系数所反映的情况完全吻合.通过岭迹对温度变量进行优化选择,实现了温度测点优化布置,并选用适当的岭参数k建立了数控机床热误差的多元线性回归优化模型,提高了热误差模型的精确性和鲁棒性.     

Optimal temperature variable selection by grouping approach for thermal error modeling and compensation

One of the difficult issues in a thermal error compensation scheme is to select appropriate temperature variables as well as to obtain accurate thermal error component models. In this research, an optimization method is presented to overcome this difficulty. The optimization objective function is formulated by a modified model adequacy criterion based on the Mallows' C_p statistic. A new search method is developed for discrete search domains with non-directional or unknown-order variables. The search process includes correlation grouping, representative searching, group searching and variable searching. It not only ensures optimal results but also reduces computational time greatly. One modeling example is presented. The optimal model is found with a 0.982 R²-value using four temperature variables selected from 46 candidates of temperature variables. The largest error residual is reduced down to 2.2 microns from 20.0 microns. The comparison of modeling results from the proposed approach and three other modeling methods is addressed as well.     

数控机床的热误差建模与补偿研究

数控机床的热变形误差是影响其加工精度的主要因素。针对当前机床热误差难以解决的问题,提出一种融合模糊聚类理论、灰色关联理论和多元线性回归理论的热误差建模及补偿原理,通过应用于实验室自主研制的AGPM,经机床温度场的测点优化分析、多元线性回归求解,建立了精确的热误差补偿模型。经补偿验证,该原理理论正确、简单易行、稳定可靠,可以大幅减小机床的热变形误差。     

基于神经网络和自适应残差补偿的炼铜转炉吹炼终点预报模型

讨论了权值初始化、变量的预处理、学习过程参数的自适应调节、网络拓扑结构等因素对学习和推广的影响,提出了一种改进的ＢＰ神经网络学习算法,在很大程度上改善了学习效率。采用改进的带有８个输入变量的ＢＰ神经网络算法和自适应残差补偿算法建立吹炼终点组合预报模型。利用某厂实际生产数据进行仿真运行的结果表明,利用该组合预报模型得到的平均相对预测误差为１．２％,最大误差为４％。     

机床热误差非线性组合预测模型研究

在精密及超精密加工过程中,数控机床热误差是影响加工精度的一项重要误差源,最经济和有效地减少热误差的方法是热误差补偿技术。针对热误差补偿预测模型的预测精度问题,提出一种非线性组合预测模型。该预测模型利用灰色关联度方法对单项预测模型进行筛选,对筛选出的单项预测模型基于不同优化准则进行线性组合,通过广义回归神经网络对该线性组合模型进行非线性组合,得到非线性组合预测模型。误差预测结果表明:对比典型的BP神经网络预测模型,非线性组合预测模型的预测精度更高,最大误差由4.78μm减小到0.7μm。     

数控机床热变形误差补偿技术

热变形误差是影响机床加工精度的重要因素之一,通过实时热变形误差补偿可以提高数控机床加工精度.本文在分析产生机床热误差的原理的基础上, 探讨了热误差的测量方法,利用多元线性回归方法建立了机床热变形与温升之间的数学模型.应用数控系统的PLC补偿功能,对XH178加工中心加工过程中的热误差进行了实时补偿.实验结果表明误差补偿量达到80%以上.     

机床热误差补偿群控系统研究

为提高热误差补偿精度和实现热误差补偿群控,提出了一种车间机床热误差补偿群控方法,采用分布式采集、补偿控制以及集中式建模计算,有效提高了采集端的扩展性,充分利用了服务端的高性能。基于CAN总线,构建了机床状态信息采集平台,结合PSO-BP神经网络进行了热误差建模研究,开发了热误差补偿群控系统,开展了机床状态信息采集监控及误差补偿实验。实验结果表明:该系统具有较好的扩展性,适应多类型机床信息采集与交互;热误差补偿群控模型有效提高了机床定位精度,具有较好的工程应用前景。     

精密加工中心直线轴复合误差建模研究北大核心

为提高精密机床加工精度,针对直线轴几何误差与热误差两类重要误差项进行分析,并提出一种复合定位误差建模方法。首先对两端固定式丝杠进给系统的热误差机制进行分析,建立正弦函数误差表达式,利用有限元法提取丝杠表面温度并作为输入量代入到热误差模型中。利用切比雪夫多项式建立静态几何误差预测模型。将两模型叠加,得到复合定位误差模型。对精密加工中心直线轴进行检测实验,实验值与预测模型对比后发现预测精度达到85%以上,验证了复合误差模型具有较高的预测精度,为直线轴定位误差补偿提供了参考。     

数控车床热误差实时补偿研究

热误差是数控加工中的主要误差源之一,对零件加工精度有非常大的影响。对数控车床热误差进行补偿可以有效地提高机床的加工精度。在数控车床的加工过程中,采用铂电阻温度传感器对数控加工中关键点的温度进行实时测量,再配合线性回归理论建立数控车床的热误差模型。最后根据热误差模型对数控车床的加工误差进行实时补偿,经验证该技术是可靠有效的。     

Accuracy enhancement of five-axis CNC machines through real-time error compensation

Although error modeling and compensation have given significant results for three-axis CNC machine tools, a few barriers have prevented this promising technique from being applied in five-axis CNC machine tools. One crucial barrier is the difficulty of measuring or identifying link errors in the rotary block of five-axis CNC machine tools. The error model is thus not fully known. To overcome this, the 3D probe-ball and spherical test method are successfully developed to measure and estimate these unknown link errors. Based on the identified error model, real-time error compensation methods for the five-axis CNC machine tool are investigated. The proposed model-based error compensation method is simple enough to implement in real time. Problems associated with the error compensation in singular position of the five-axis machine tool are also discussed. Experimental results show that the overall position accuracy of the five-axis CNC machine tool can be improved dramatically.     

数控机床主轴热误差的数据驱动模型研究

当实际工况与建模工况存在差异时,传统的热误差模型往往表现出较差的鲁棒性和预测精度,主要原因在于建模数据的局限性和模型的未建模动态。为了改善上述状况,提出了一种基于数据驱动的数控机床主轴补偿模型。此模型采用无模型自适应控制算法建模,结合机床运行中生成的数据(温度数据和误差数据)对热误差模型进行实时修正,使模型能快速适应新的加工工况,从而提高模型的鲁棒性。在一台数控车床主轴上进行了试验验证,结果表明:无模型自适应控制与多元回归模型比较,其标准差、最大残差和误差平方和分别提高了41%、62%和56%,此模型的鲁棒性和预测效果好。同时,此方法为大数据在机床主轴热误差补偿中的应用奠定了基础。     

Thermal error mode analysis and robust modeling for error compensation on a CNC turning center

In this paper a novel concept of thermal error mode analysis is proposed in order to develop a better understanding of the thermal deformation on a turning center. The thermal error of the machine can be treated as the superposition of a series of thermal error modes with corresponding mode shapes and time constants. The selection of sensor location can then be improved based on the thermal error mode analysis. A robust modeling approach is also proposed to minimize the errors due to temperature measuring noise and the adverse effect of environmental changes. Through the use of thermal error mode analysis and the robust modeling approach, the number of thermal sensors has been reduced from 16 to four. The thermal error compensation system has been applied to a turning center in daily production for more than two years and it has kept year-round accuracy. The thermal drift in workpiece diameter on the turning center has been reduced from 35 μm to 6 μm from its center of tolerance.     

基于CS-GMC(1,N)的数控机床全新热误差建模优化方法

为降低机床热误差对数控加工精度的影响,提高灰色模型GMC(1,N)的预测精度,将布谷鸟搜索（CS）算法引入GMC(1,N)灰色模型中,用于优化灰色模型GMC(1,N)的生成系数,构建了基于CS-GMC(1,N)的数控机床热误差预测模型。以小型三轴立式数控铣床为研究对象进行了主轴热误差实验,热误差预测性能分析结果表明：CS-GMC(1,N)模型的预测精度高于PSO-GMC(1,N)模型,为机床主轴热误差建模及后续热误差补偿提供了参考。     

数控机床热误差补偿建模综述

热误差建模技术是决定热误差补偿能否有效进行的关键,对提高数控机床的加工精度至关重要。介绍数控机床热误差建模的国内外研究状况,阐述国内外常用的几种主要的热误差建模方法,即人工智能法、统计分析法、灰色系统法等,探讨各种方法的特点,指出目前研究存在的问题,并展望未来的发展。     

基于SSA-BP的电主轴热误差优化建模

为解决某加工中心电主轴的热误差补偿问题，建立预测精度高、鲁棒性强的热误差补偿模型。搭建实验台，利用美国雄狮回转误差分析仪采集电主轴的温度场和热误差数据。介绍麻雀搜索算法(SSA)原理、具体优化流程。采用SSA优化BP神经网络的权值和阈值，建立SSA-BP神经网络预测模型。与之前建立的BP神经网络预测模型相比，优化后预测效果更优，为电主轴热误差建模提供新的思路。     

高速电主轴热误差实验与预测建模

数控加工中心采用高速电主轴,由于电主轴发热导致主轴工作端明显热延伸,严重影响加工精度。以数控精雕机用永磁同步电主轴为研究对象,通过建立热特性实验平台,测试电主轴在不同转速、不同工作条件下的特征温度和热误差数据,建立基于自然指数函数的电主轴轴向热误差预测模型。在不同的工况下对模型的补偿结果进行实验验证,验证结果表明:该预测模型简单、精度较高,且建模成本较低,可以快速应用到实际的加工环境中。     

数控机床热误差建模及预测方法分析

热误差作为制约数控机床加工精度的关键因素,在重型数控机床上表现得尤为明显。以重型落地镗铣床为例,根据热误差测量试验数据,分析重型数控机床温度场特性,并基于兼顾相关系数和欧式距离的系统聚类准则,对温度测点系统进行优化,以减小温度测点间共线性。通过优化温度测点,采用多元线性回归分析,建立重型数控机床热误差预测模型。由现场试验可知,建立的热误差预测模型可将均方根误差控制在10μm以内,有效地提高了热误差预测精度。     

A review on spindle thermal error compensation in machine tools

Thermal error caused by the thermal deformation is one of the most significant factors influencing the accuracy of the machine tool. Among all the heat sources which lead to the thermal distortions, the spindle is the main one. This paper presents an overview of the research about the compensation of the spindle thermal error. Thermal error compensation is considered as a more convenient, effective and cost-efficient way to reduce the thermal error compared with other thermal error control and reduction methods. Based on the analytical calculation, numerical analysis and experimental tests of the spindle thermal error, the thermal error models are established and then applied for implementing the thermal error compensation. Different kinds of methods adopted in testing, modeling and compensating are listed and discussed. In addition, because the thermal key points are vital to the temperature testing, thermal error modeling, and even influence the effectiveness of compensation, various approaches of selecting thermal key points are introduced as well. This paper aims to give a basic introduction of the whole process of the spindle thermal error compensation and presents a summary of methods applied on different topics of it.     

Tool path accuracy enhancement through geometrical error compensation

Kinematic and geometric errors of CNC machine tools, introduce large deviations in the real path traveled by the cutting tool. Tool path deviation reduces geometrical and dimensional accuracy of the machined features of the component. Tool path modification is an effective strategy to increase accuracy of the machined features. An improved error estimation model based on kinematic transformation concepts has been developed and used to calculate the volumetric overall error. These calculations are applicable for each arbitrary target positions of the machine's work space. Also a NC Program editor software has been developed in order to manage the calculations, modifications and to generate the new compensated NC program. The compensation procedure includes: fragmentation of nominal tool path to small linear elements, translating nominal position of elements to real positions using the Kinematics error model, finding compensated positions using the error compensation algorithm, converting newly generated elements to new tool paths using the packing algorithms and finally editing old NC program using NC code generator algorithm. Experimental tests showed 4-8 times accuracy improvement for linear, and S-pline tool paths deviations.     

基于多体系统理论的精密加工中心综合误差建模

基于多体系统理论,针对一台含有工作台站的精密加工中心,建立其综合误差模型,分析并解决了交换工作台站的运动误差对综合误差的误差传递问题,改进了各轴热漂移误差的综合误差建模方法。运用该误差模型进行实时补偿,能有效提高加工中心的加工精度。