Adaptive learning control for thermal error compensation of 5-axis machine tools

The research presented in this paper shows an adaptive approach for long-term thermal error compensation of 5-axis machine tools (MT). A system of differential equations is used to compute the model based compensation values. The model can predict thermal displacements of the tool center point (TCP) based on changes in the environmental temperature, load-dependent changes and boundary condition changes and states, like machining with or without cutting fluid. The model based compensation of the rotary axis of a 5-axis MT is then extended by on-machine measurements. The information gained by the process-intermittent probing is used to adaptively update the model parameters, so that the model learns how to predict thermal position and orientation errors and to maintain a small residual error of the thermally induced errors of the rotary axis over a long time. This approach not only increases the MT accuracy but also reduces the amount of time spent on preproduction model parameter identification. Additionally an algorithm has been developed to dynamically adjust the length of the on-machine measurement intervals to maintain a high productivity and a constant deviation of the machined parts.Experimental results confirm that the adaptive learning control (ALC) for thermal errors shows a desirable long-term prediction accuracy.     

基于LabVIEW的机床热误差检测系统设计

针对机床高速旋转主轴的安装偏心及各种外界干扰对热误差精确测量的影响,本文选用了精度较高的电容式位移传感器及NI数据采集卡,基于LabVIEW平台开发了一套机床温度和位移数据实时检测系统。该检测系统可实现在主轴高速旋转下位移数据的高速率采样,并采用软件数字滤波方法对位移数据处理。最后将该检测系统进行实验测量,实验结果表明该检测系统具有一定的实用性。     

数控机床反向误差测定评价及补偿

建立了反向误差补偿的数学模型,提出了数控机床的反向误差的软件补偿方法.对补偿前后的反向误差进行了精度评价,结果表明,经过反向误差的软件补偿,数控机床位置误差降低,实现了机床精度的软升级.     

数控机床液压系统故障溯源及分析*

以提高机床液压系统可靠性为目的,分析了液压传动的特点,并对常见的故障现象进行了整理,归纳出了振动异响、压力不足及波动大、流量不稳定、液压元器件损坏四种典型的故障模式。以某磨齿机为例,采用FTA(故障树分析)方法,对四种故障模式进行了故障原因溯源,找出了造成系统故障的根本原因。以压力故障为例进行了定量分析,对每个底事件的概率重要度和相对概率重要度进行了计算,并阐述了重要度分析在可靠性改进和控制过程中的重要作用。     

Web-based virtual operating of CNC milling machine tools

This paper attempts to propose a virtual operating system applied to operation training of manufacturing facility and manufacturing process simulation. The system is based on VRML and browser/server structure, so user only needs to install a free plug-in, and run the package normally via Microsoft Internet Explorer. Initially this paper studies the system framework, structure models and concept models. Then, a communication approach based on VRML, Java and HTML, which is key to realize the virtual operating of CNC machines, has been presented. The algorithm of material removed simulation based on VRML Z-map is also presented in this paper. It has the advantages such as a lower memory requirement, and a faster computation speed. Finally, in order to validate the feasibility of the proposed approach, the CNC milling machine has been taken as an illustrative example for the prototype development.     

Thermal error modelling of a gantry-type 5-axis machine tool using a Grey Neural Network Model

This paper presents a new modelling methodology for compensation of the thermal errors on a gantry-type 5-axis CNC machine tool. The method uses a “Grey Neural Network Model with Convolution Integral” (GNNMCI(1, N)), which makes full use of the similarities and complementarity between Grey system models and artificial neural networks (ANNs) to overcome the disadvantage of applying either model in isolation. A Particle Swarm Optimisation (PSO) algorithm is also employed to optimise the proposed Grey neural network. The size of the data pairs is crucial when the generation of data is a costly affair, since the machine downtime necessary to acquire the data is often considered prohibitive. Under such circumstances, optimisation of the number of data pairs used for training is of prime concern for calibrating a physical model or training a black-box model. A Grey Accumulated Generating Operation (AGO), which is a basis of the Grey system theory, is used to transform the original data to a monotonic series of data, which has less randomness than the original series of data. The choice of inputs to the thermal model is a non-trivial decision which is ultimately a compromise between the ability to obtain data that sufficiently correlates with the thermal distortion and the cost of implementation of the necessary feedback sensors. In this study, temperature measurement at key locations was supplemented by direct distortion measurement at accessible locations. This form of data fusion simplifies the modelling process, enhances the accuracy of the system and reduces the overall number of inputs to the model, since otherwise a much larger number of thermal sensors would be required to cover the entire structure. The Z-axis heating test, C-axis heating test, and the combined (helical) movement are considered in this work. The compensation values, calculated by the GNNMCI(1, N) model were sent to the controller for live error compensation. Test results show that a 85% reduction in thermal errors was achieved after compensation.     

多传感器融合的数控机床热误差回归建模新方法

热误差对机床的加工精度影响很大,高性能的补偿系统依赖于多传感器融合建立的三维模型的精度、鲁棒性和合适的温度进行反馈输入。本文使用温度与位移传感器的模糊聚类进行温度分类,基于评价模型比对分析最优的温度分类,从每个分类中选择具有代表性温度作为候选温度。归纳试验数据,使用分段逆回归SIR模型进行热误差建模,SIR模型将高维前移回归问题转化为多个一维的回归问题,并且进一步消除了候选温度之间的耦合。热误差试验表明,SIR模型具有泛化能力强、预测精度高及鲁棒性好的特点,能够准确地描述多种典型工况条件下的实际热误差特性。     

基于LabVIEW数控机床几何误差补偿的研究方法

介绍一种由软件、硬件控制的数控机床几何误差补偿。误差补偿的原理主要是运用多体系统运动学理论建立机床几何误差模型,用硬件控制固化在程序存储器内的误差补偿程序完成补偿任务,并通过RS-232C实现数控机床与Windows平台通信与数据交换。     

基于嵌入式Linux的数控机床远程监控

为实现数控机床的网络化管理,针对目前一些老式机床无远程监控平台的问题,提出了基于嵌入式Linux的数控机床远程监控系统的设计与实现方案.该方案采用嵌入式Linux与ARM处理器为平台,软硬件结合,完成车间级监控主机与局域网内各机床之间的通信,并利用嵌入式数据库对机床状态信息进行实时备份,达到对局域网内多台机床进行集中监控管理的目的.该方案的智能控制模块可根据接收到的机床报警信息,向机床发送相应的控制命令,保护机床正常运行;车间级监控主机还可直接接入Intemet,以便将机床的数据发送到远程进行故障诊断.实验结果表明,该方案可以有效的对老式机床进行集中监控,实现了数控机床的网络化管理.     

基于状态监测的高档数控机床智能保障系统研究＊

分析数控机床做障产生的原因,研究制定相应的解决方案,同时为实现设备运行状态的可监控性,提高设备的可靠性,丌发集机床状念临测、故障预警、故障诊断和故障排除为一体的智能保障系统。通过对数控机床智能保障系统的研究、设计,介绍其实现的关键技术及方法。举丝杠运动状态监测为例,进行运动状态趋辨分析、智能故障诊断,从Ⅲ实现对数控机床的智能保障,验证智能保障系统的实用性。     

A universal velocity limit curve generator considering abnormal tool path geometry for CNC machine tools

Non-linear parametric curves, such as B-spline curves, are becoming increasingly available in modern CNC (Computer Numerical Control) systems. The smoothness of parametric curves offers higher order of continuity and thus invokes less vibration in machines as compared to short line segments. Nevertheless, the computations for velocity limit curves, velocity profiles and interpolation points are quite complicated and time-consuming and therefore approximation methods are applied. Unnecessary accelerations and decelerations, which cost additional time of motion, can be caused by inaccurate computations of the velocity limits around tiny corners. To overcome the problem, the unit arc length increment scanning method (UALISM) is proposed to reduce the time of movement and to improve the efficiency. The scanning interval is fixed at 1 BLU (basic length unit) which is irrelevant to the type, size and shape of the tool path curve. The constraints of chord height errors and axis accelerations are considered and the velocity limit for the specified scanning point is computed using the coordinates of multiple scanning points near the specified scanning point. Simulation results show that the unnecessary accelerations and decelerations can be avoided and thus the total motion time can be reduced by UALISM.     

The kinematic analyses of the 3-DOF parallel machine tools

A 3-degree-of-freedom (3-DOF) parallel machine tool based on a tripod mechanism is developed and studied. The kinematics analysis is performed, the workspace is derived, and an analysis on the number of conditions of the Jacobian matrix and manipulability is carried out. A method for error analysis and manipulability is introduced. Hence, the manipulability analysis of the parallel machine tool is accomplished.     

数控龙门铣床数据采集系统综述

龙门铣床是机床族的重要机型,其应用广泛,尤其是数控龙门铣床在航空制造领域的地位举足轻重。数据采集系统是机床监控系统的前端子系统和关键组成部分,数据采集系统设计的成功与否,决定了机床监控系统的数据有效性。对应用于龙门铣床的数据采集系统进行研究,具较大的现实意义。在介绍数控龙门铣床的结构及功能的基础上,分析了数控龙门铣床的数据采集的核心需求,针对性地分析和总结了数据采集的手段和方法,并概述了数控龙门铣床数据采集系统的发展方向。为数控龙门铣床数据采集系统的设计提供了技术支撑。     

Spindle thermal error prediction approach based on thermal infrared images: A deep learning method

It is essential to precisely model the spindle thermal error due to its dramatic influence on the machining accuracy. In this paper, the deep learning convolutional neural network (CNN) is used to model the axial and radial thermal errors of horizontal and vertical spindles. Unlike the traditional CNN model that relies entirely on thermal images, this model combines the thermal image with the thermocouple data to fully reflect the temperature field of the spindle. After pre-processing and data enhancement of the thermal images, a multi-classification model based on CNN is built and verified for accuracy and robustness. The experimental results show that the model prediction accuracy is approximately 90 %–93 %, which is higher than the BP model. When the spindle rotation speed changes, the model also shows good robustness. Real cutting tests show that the deep learning model has good applicability to the spindle thermal error prediction and compensation.     

混联复合机床转台定位精度的激光测量与补偿

传统的数控机床进给轴定位精度的检测方法,存在精度低、方法落后、检验重复性差等缺点。因此,采用目前国际先进的激光干涉法检测混联复合机床转台的定位精度,以评价和提高其精度。对干涉仪的测量原理、测量方法和数据处理进行了分析,认为空气折射率是干涉仪应用中的主要误差来源,并分析了其原因和补偿方法。最后,给出了基于激光干涉仪的机床定位精度检测和补偿方案。     

基于UMAC的高精密机床开放式数控系统探析

文章以高精密五轴机床为对象、以UMAC为基础,开发了一套开放式数控系统。首先﹐在Windows 10操作系统下构建了硬件平台;然后,进行了相关的软件系统设计。在设计过程中,通过多种模块化的方法,实现系统的不同功能--包括对机床的控制、工艺参数设置以及人机交互等;最后,通过试验验证了开放式数控系统的可用性。     

机器视觉测量中透视投影误差分析控制与补偿

在机器视觉齿轮倒角的测量系统中,轮廓测量是实现齿轮中心定位的关键因素。传统镜头成像时,由于透视投影特性,会引起齿轮轮廓圆直径的测量误差,进而影响轮廓圆的定位精度。针对此建立了透视投影误差的非线性模型,并对不同厚度齿轮轮廓圆直径的测量进行了误差分析与补偿。实验结果表明,该方法具有一定的实用价值,满足了齿轮轮廓圆测量的要求。     

Geometric-thermal error control system for gear profile grinding machine

Geometric and thermal errors, which are the main error factors for reducing the machining accuracy, should be controlled. But the control effect is poor, which is a stumbling block to limit the wide application of the error control. In this study, a geometric-thermal error control system (GTECS) is designed for gear profile grinding machines. For the mist layer of GTECS, the wireless sensor network is designed to realize the data collection and transfer. For the edge layer of GTECS, the edge controller is designed to conduct the sensitive error analysis. For the fog layer, the control module is designed to conduct the geometric and thermal error prediction. In this layer, the analytical model of the rolling guide/slider system is proposed to calculate geometric errors of X- and Z- axes, and the thermal boundary conditions are calculated, and the thermal error models of the spindle and C-axis are proposed based on transfer learning model (TLM) of the sooty tern optimization (STO)-bilinear temporal convolutional network (BTCN). For the cloud layer, the data computation and management are realized by Hadoop and Yet Another Resource Negotiator (YARN), respectively. The geometric and thermal error models of X- and Z-axes, thermal errors models of the spindle and C-axis, and multi-source error model are embedded into it. With the execution of GTECS, the geometric precision for the total tooth profile deviation and tooth profile deviation are increased from ISO level 8 to ISO level 5 and from ISO level 5 to ISO level 3, respectively.     

柔性制造系统中CNC机床故障诊断机理研究

为了及时发现处理柔性制造系统数控机床的故障或异常现象,设计了CNC在线故障诊断测试系统。该系统不仅便于查找数控机床故障的一个或多个症结,可以快捷、准确地对CNC故障定位,而且解决了诊断处理与知识应用中的相关问题。为了对CNC设备终端提供可靠的故障排除建议,对伺服控制组件与后台服务关联关系进行深入剖析,并对故障数据库进行描述与测试程序设计,解决了系统维护、扩展与升级操作等问题。     

一种改进的数控机床工件坐标找正方法

测头测量存在随机误差,采用二点确定直线的方法进行坐标找正会带来较大误差,本文针对常用的测量垂直坐标系找正方法提出了一种改进算法,通过分别测量一组数据,采用最小二乘法拟合直线,可以较好的减小随机误差影响,得到更精确的坐标结果。