Neural network-based modelling and error compensation of thermally-induced spindle errors

This research is concerned with enhancing the accuracy of a machining centre by compensating for thermally induced spindle errors in real-time. A neural network model was developed for on-line thermal error monitoring. A PC-based error compensation scheme was also developed to upgrade a commercial CNC controller for real-time thermal error compensation without any hardware modifications to the machine. The spindle thermal errors of a vertical machining centre were reduced by 70% after compensation.     

利用自组织原理补偿主轴热误差的仿真研究

本文提出了一种基于自组织原理的主轴热误差补偿策略，它只需根据对主轴热倾斜状态的定性测量结果即可进行定量误差补偿，从而可以大大降低对误差测量精度的要求及测量成本，同时各补偿力间的协调关系根据自组织原则自动建立，简化了补偿算法。经过对某型卧式加工中心主轴热误差进行的自组织仿真补偿，其主轴热倾斜误差减小了92％以上，热偏移误差减小了46％以上。     

运用多体理论和神经网络的机床热误差补偿

利用多体系统理论,在典型体的坐标变换中,加入了位移误差矢量和位置误差矢量,形成了具有普遍意义的坐标变换,根据机床拓扑结构的低序体阵列,建立了机床通用误差计算模型。同时,对机床的主轴热变形和床身热变形进行了建模和辨识,通过5个温度敏感点的监测,用常规的5点法对机床主轴热变形进行研究,运用神经网络方法(RBF)建立温度与变形参数模型,将误差参数集成到通用误差模型中。在Makino四轴加工中心进行试验研究,设计出一套多个凸台的空间曲面,比较了不同凸台上的4个点补偿前后空间轮廓数据,误差减少60%,补偿效果显著。     

超精密加工误差补偿技术研究综述

超精密加工技术是高端制造领域的一项关键技术,当前超精密加工已进入纳米尺度,掌握超精密加工误差控制关键技术、保障并提高数控机床的加工精度,已经成为提高加工制造水平的研究热点。系统总结了超精密加工误差补偿技术研究现状及发展趋势,重点介绍了对超精密加工影响最大的几何误差、力诱导误差、热诱导误差及其补偿方法。在此基础上,深入探讨了超精密加工在几何误差分离,切削力、热诱导误差测量与补偿等方面存在的一系列问题,进一步指出超精密加工误差补偿技术还应关注其向高效、高精,通用化,模块化,智能化及柔性化的发展方向。     

Application of projection pursuit regression to thermal error modeling of a CNC machine tool

Thermal errors are the major contributor to the dimensional errors of a workpiece in precision machining. Error compensation technique is a cost-effective way to reduce thermal errors. Accurate modeling of errors is a prerequisite of error compensation. In this paper, a thermal error model was proposed by using projection pursuit regression (PPR). The PPR method improves the prediction accuracy of thermal errors in the computer numerical control (CNC) turning center. A thermal error compensation system was developed based on the PPR model, and which has been applied to the CNC turning center in daily production. The results show that the thermal drift in workpiece diameter has been reduced from 34 to 5???m.     

机床热变形的主动补偿

研究加工中心热变形的主动补偿,讨论补偿系统的设计和运行原理。通过监测机床温度分布,采用附加人工热源接规则进行补偿或平衡机床本机热源所引起的温度变化。实验证明,这种主动补偿可消除机床的大部分变形和加工误差。     

变工况下基于迁移学习融合域内对齐的机床主轴热误差模型

热误差建模和补偿是提高机床加工精度的重要手段。 将得到的热误差模型应用到类似或相近任务中,对减少模型构建 和数据收集的成本具有重要意义。 本文提出了一种简易迁移学习(EasyTL)融合域内对齐的主轴热误差建模方法,以实现不同 工况下误差模型的迁移复用。 建立基于域内对齐和距离矩阵全组合择优的热误差迁移模型参数选取方法,获得最优组合。 进 一步分析不同类型的域内对齐和距离矩阵各自对模型迁移性能的影响。 最后,将迁移模型与 kNN 典型机器学习模型和卷积神 经网络深度模型进行比较验证,分别预测不同工况下主轴 Z 向和 Y 向的热误差。 此外,根据预测的主轴热误差进行工件补偿 加工实验。 该方法为热误差建模及补偿提供了一种新思路。     

Modified Elman network for thermal deformation compensation modeling in machine tools

Thermal deformation is one of the most significant causes of machining errors in machine tools. One effective method is to build a compensation system to offset the thermal errors. Therefore, an accurate model is the key part of the compensation system. This study proposed a modified Elman network (EN) to improve the prediction accuracy of the compensation model in machine tools. And the improved EN can be regarded as a feed-forward neural network with feedback from hidden layer and output layer as an additional set of inputs. The structure of this network determines its dynamic characteristic with memory function. On the other hand, thermal deformation of the spindle contributes the largest part of total thermal errors in precision machining. Then a precise finite element model of machine tool spindle was established. And a new method for calculating the heat transfer convection coefficient on the surface of the spindle was proposed in this paper. The improved EN was used to map the nonlinear relationship between temperature field and thermal errors of the spindle. At last, a verification experiment was implemented on a CNC center and some satisfying results were achieved.     

Application of ACO-BPN to thermal error modeling of NC machine tool

Thermal errors are the major contributor to the dimensional errors of a workpiece in precision machining. Error compensation technique is a cost-effective way to reduce thermal errors. Accurate modeling of errors is a prerequisite of error compensation. In this paper, four key temperature points of a NC machine tool were obtained based on clustering method. A thermal error model based on the four key temperature points was proposed by using ant colony algorithm-based back propagation neural network (ACO-BPN). The ACO-BPN method improves the prediction accuracy of thermal deformation in the NC machine tool. A thermal error compensation system was developed based on the proposed model, and which has been applied to the NC machine tool in daily production. The results show that the thermal drift in workpiece diameter has been reduced from 33 to 8 μm from its center of tolerance.     

数控机床热变形误差研究及补偿应用

热变形误差是影响机床加工精度的重要因素之一,通过误差补偿的方法可以提高机床的加工精度。研究了通过实时补偿热变形误差提高数控机床加工精度的方法,阐述了热误差的基本原理,介绍了热误差的测量方法。采用模糊聚类的方法来布置测温点,利用多元线形回归方法建立了机床热变形与温升之间的数学模型。在PLC补偿系统的作用下,在加工过程中对XH718数控机床进行实时补偿。实验结果表明补偿效果很好。     

Thermal deformation analysis and compensation of the direct-drive five-axis CNC milling head

The machining precision of the milling head is primarily affected by the thermal errors that originated from the thermal deformation. Thermal error compensation is an economical and efficient method to overcome these thermal errors. The milling head’s heat source is analyzed to calculate the thermal boundary load based on component parameters of the milling head. The milling head’s thermal deformation is then simulated using ANSYS software to achieve the milling head’s temperature distribution and the amount of thermal deformation. Through the design and construction of the milling head temperature and thermal deformation experiment platform, the thermal deformation experiment of the milling head is performed. Accordingly, the measuring point temperature and the tooltip offset are obtained. Finally, a thermal error compensation method is proposed based on the homogeneous transformation. The research results give a theoretical reference and technical support for the thermal error compensation, optimized design, and development of milling heads.

     

无温度传感器的数控机床进给轴热误差补偿

分析了目前常见的进给轴热误差补偿方法的缺点,如需要多个温度传感器、模型的鲁棒性较差等。提出一种基于无温度传感器的、强鲁棒性的机床进给轴热误差补偿方法,在恒温环境下实现对运动生热导致的热误差的补偿。给出了热误差模型的推导过程以及应用ISIGHT平台进行参数优化的过程。热误差模型基于摩擦生热、热传导和散热机理实时预测滚珠丝杠的温度场,以实现预测并补偿丝杠热误差的目的。在一台立式加工中心VMC850上对x、y、z轴进行了热误差测试并给出了模型的仿真效果。在另一台立式加工中心VMC850上采用激光干涉仪进行了热误差补偿前后的对比试验和加工对比试验。试验结果表明,该热补偿方法具有很高的精度稳定性和强鲁棒性。     

Thermal growth measurement and compensation for integrated spindles

The errors which affect the processing tolerance of a machine tool are due to the built-in volumetric errors in the machine tool structure and also the thermal displacement of the machine tools during its cutting. In this paper, a dual-displacement meter compensation system is developed. The new model has a better tolerance control than the single-displacement compensation meter method; also, it has a great potential for saving a machine’s warm-up time as well as enhancing productivity. A dual-displacement meter is designed to detect the variation of spindle thermal growth and a differential amplifier is applied which ensure a precise output signal tolerance of spindle thermal growth. The unstable signal which is an effect of flatness tolerance of spindle surface is then omitted. Finally, the spindle thermal growth compensations are successfully reduced. It meets the requirement of high-speed machining and high-precision machining application.     

加工中心热误差补偿的研究

热误差是加工中心的最大误差源。通过对机床热特性的实验和分析，利用神经网络模型对热误差进行了补偿，取得比较好的效果。     

Thermal error modeling of machine tool based on fuzzy c-means cluster analysis and minimal-resource allocating networks

Thermal deformation in machine tools is one of the most significant causes of machining errors. A new approach to predict the thermal error of machine tool is proposed. The temperature variables and the thermal errors are measured using the Pt-100 thermal resistances and eddy current sensors respectively. Fuzzy c-means clustering method is conducted to identify the temperatures, and the representative as an independent variable are selected meanwhile it eliminates the coupling among the variables. The learning and prediction of the thermal errors is achieved using minimal-resource allocating networks by treating the issue as functional mapping between the thermal shifts and the temperature variables. The network is made to predict the error map of a machining center. A traditional radial basis function model is introduced for comparison. The experiment result shows that the fuzzy c-means clustering method and minimal-resource allocating networks combination is a fast and accurate method for thermal error compensation in machine tools.     

基于多体理论模型的加工中心热误差补偿技术

基于多体系统理论，建立了数控加工中心热误差模型，并提出其误差补偿方法。以三坐标ＭＡＫＩＮＯ加工中心为例，建立了具体模型并进行参数辨识。优选了４个测温点，实时测量其温度，作为误差参数辨识模型的输入值，实现了软件实时补偿。在该加工中心上分别沿３个坐标方向加工一系列表面并比较加入热误差补偿的结果，测量结果表明补偿效果显著。实践说明所建热误差模型的有效性和补偿方法的可行性。     

复杂曲面零件在线检测与误差补偿方法

复杂曲面零件的高精度加工与精密检测一直是数字化制造领域的研究热点。为提高复杂曲面零件的加工精度、检测精度,提出一种集数控机床在线检测、加工误差分解与补偿加工为一体的集成化方法。介绍集成化在线检测方法及补偿系统的基本原理,分析数控加工后曲面零件测点数据的误差组成,提出一种基于空间统计分析的加工误差分解方法,在建立基于B样条曲面的确定性曲面回归模型的基础上,对回归模型残差进行空间独立性分析,分解出系统误差和随机误差,进而通过数控代码的修改,实现零件加工过程的系统误差补偿。列举一个曲面零件的加工与检测实例,进行方法有效性验证。通过加工工件的在线检测、误差分解、代码修改及补偿加工等环节,实例零件的加工精度有了大幅提高,而该系统的检测精度也通过与三坐标测量机(Coordinate measuring machine, CMM)检验结果的对比,得到了有效验证。     

Thermal error analysis,modeling and compensation of five-axis machine tools

The role of five-axis CNC machine tools (FAMT) in the manufacturing industry is becoming more and more important, but due to the large number of heat sources of FAMT, the thermal error caused by them will be more complicated. To simplify the complicated thermal error model, this paper presents a new modelling method for compensation of the thermal errors on a cradle-type FAMT. This method uses artificial neural network (ANN) and shark smell optimization (SSO) algorithm to evaluate the performance of FAMT, and developing the thermal error compensation system, the compensation model is verified by machining experiments. Generally, the thermal sensitive point screening is performed by a method in which a large number of temperature sensors are arranged randomly, it increases the workload and may cause omission of the heat sensitive point. In this paper, the thermal imager is used to screen out the temperature sensitive points of the machine tool (MT), then the temperature sensor is placed at the position of the heat sensitive point of the FAMT, and the collected thermal characteristic data is used for thermal error modeling. The C-axis heating test, spindle heating test, and the combined movement test are applied in this work, and the results show that the shark smell optimization artificial neural network (SSO-ANN) model was compared to the other two models and verified better performance than back propagation artificial neural network (BP-ANN) model and particle swarm optimization neural network (PSO) model with the same training samples. Finally, a compensation experiment is carried out. The compensation values, which was calculated by the SSO-ANN model are sent to the real-time error compensation controller. The compensation effect of the model is then tested by machining the ‘S’-shaped test piece. Test results show that the 32 % reduction in machining error is achieved after compensation, which means this method improves the accuracy and robustness of the thermal error compensation system.

     

XH718加工中心的热误差补偿研究

在分析某XH718加工中心主轴及主轴箱结构和热源的基础上,在主轴箱上初步选择多个测温点,根据测温点温度和主轴热误差的数据,应用模糊聚类分析和相关性分析对测温点进行了优化,确定最小数量的关键测温点。然后应用多元线性回归理论建立了关键测温点的温升和热误差的数学模型。数学模型在加工中心上补偿后的数据表明,可以在很大程度上改进加工中心的精度,达到了客户需要的精度要求。     

基于误差补偿的加工中心在线检测软件的开发

对加工中心在线检测软件误差补偿技术进行研究，基于Windows平台开发了在线检测误差补偿软件。并对软件开发中的关键技术检测系统的几何误差模型的建立、测头误差处理技术进行了研究。可以同时对测头误差、机床几何误差进行补偿，有效地提高了在线检测精度。软件系统在MAKINO立式加工中心上进行了实验验证。