浏览全部资源
扫码关注微信
1. 福州大学 机械工程及自动化学院,福建 福州,350116
2. 福建工程学院 机械与汽车工程学院,福建 福州,350118
收稿日期:2015-12-11,
修回日期:2016-01-20,
纸质出版日期:2016-04-25
移动端阅览
叶建华, 高诚辉, 江吉彬. 五轴机床旋转轴误差的在机测量与模糊径向基神经网络建模[J]. 光学精密工程, 2016,24(4): 826-834
YE Jian-hua, GAO Cheng-hui, JIANG Ji-bin. On-machine measurement and fuzzy RBF neural network modeling for geometric errors of rotary axes of five-axis machine tools[J]. Editorial Office of Optics and Precision Engineering, 2016,24(4): 826-834
叶建华, 高诚辉, 江吉彬. 五轴机床旋转轴误差的在机测量与模糊径向基神经网络建模[J]. 光学精密工程, 2016,24(4): 826-834 DOI: 10.3788/OPE.20162404.0826.
YE Jian-hua, GAO Cheng-hui, JIANG Ji-bin. On-machine measurement and fuzzy RBF neural network modeling for geometric errors of rotary axes of five-axis machine tools[J]. Editorial Office of Optics and Precision Engineering, 2016,24(4): 826-834 DOI: 10.3788/OPE.20162404.0826.
考虑五轴机床中的旋转轴误差会影响加工精度和在机测量结果
本文研究了旋转轴误差的在机测量与建模方法。介绍了基于标准球和机床在机测量系统的旋转轴综合误差测量方法
采用随机Hammersely序列分组规划旋转轴的测量角位置
通过自由安放策略确定标准球初始安装位置。然后
引入模糊减法聚类和模糊C-均值聚类(Fuzzy C-means
FCM)建立旋转轴误差的径向基(Radial basis function
RBF)神经网络预测模型。最后
进行数学透明解析
从而为误差的精确解析建模提供新途径。利用曲面的在机测量实例验证了提出的旋转轴误差测量与建模方法。结果表明:利用所建模型计算的预测位置与实测位置的距离偏差平均值为9.6μm
最大值不超过15μm;利用所建模型补偿工件的在机测量结果后
其平均值由32.5μm减小到13.6μm
最大误差也由62.3μm减小到18.6μm。结果显示
提出的测量方法操作简单
自动化程度高;模糊RBF神经网络的学习速度快、适应能力强、鲁棒性好
能满足高度非线性、强耦合的旋转轴误差建模要求。
As geometric errors of rotary axes of a five-axis machine impact on its machining accuracy
the on-machine measurement of rotary axes and their error modeling were investigated. Firstly
the measurement method for comprehensive errors of rotary axes was presented based on a standard ball and an on-machine measurement system. The measurement angular positions of the rotation axes were planned by the random Hammersely sequence and the initial position of the standard ball was determined with a free installation strategy. Then
a Radial Basis Function (RBF) neural network model for predicting comprehensive errors of the rotary axes was built based on subtractive clustering and Fuzzy C-means(FCM) cluster. Finally
mathematical analysis was carried out to provide a new way to model accurately for geometric errors of rotary axes. A cambered measuring example was used to verify the proposed on-machine measurement method and modeling method.The experimental results indicate that the average deviation between the predicted points from the mathematics model and measured points is 9.6 μm and the maximum deviation is not more than 15 μm. After the measuring results are corrected by the mathematic model with a 3D coordinate measuring machine established by this paper
the average value is reduced to 13.6 μm from 33.5 μm and the maximum value is reduced to 18.6 μm from 62.3 μm. It concludes that the measurement method is simple to operate and has high automation. The neural network's training is not only fast speed
adaptable and good robust
but also can meet highly linear and strongly coupling of modeling of the geometric errors of rotary axes.
HONG C F, IBAEAKI S, MATSUBARA A, Influence of position-dependent geometric errors of rotary axes on a machining test of cone frustum by five-axis machine tools[J]. Precision Engineering, 2011, 35(1):1-11.
XIANG S, YANG J. Using a double ball bar to measure 10 position-dependent geometric errors for rotary axes on five-axis machine tools[J].The International Journal of Advanced Manufacturing Technology, 2014. 75(1-4):559-572.
IBAEAKI S, NAGAI Y, OTSUBO H, et al.. R-Test analysis software for error calibration of five-axis machine tools-application to a five-axis machine tool with two rotary axes on the tool side[J].International Journal of Automation Technology, 2015, 9(4):387-395.
LEI W T, HSU Y Y. Accuracy enhancement of five-axis CNC machines through real-time error compensation[J]. International Journal of Machine Tools and Manufacture, 2003, 43(9):871-877.
WEIKERT S, KNAPP W.R-test, a new device for accuracy measurements on five axis machine tools[J].CIRP Annals-Manufacturing Technology, 2004, 53(1):429-432.
ZARGARBASHI S H H, MAYER J R R. Single setup estimation of a five-axis machine tool eight link errors by programmed end point constraint and on the fly measurement with Capball sensor[J].International Journal of Machine Tools and Manufacture, 2009, 49(10):759-766.
ISO 230-10:2011, Test Code for Machine Tools-Part 10:Determination of measuring performance of probing systems of numerically controlled machine tools[S]. 2010.
IBAEAKI S, OTA Y. Error calibration for five-axis machine tools by on-the-machine measurement using a touch-trigger probe[J].International Journal of Machine Tools &Manufacture, 2014, 8:20-27.
BI Q Z, HUANG N D, SUN C, et al.. Identification and compensation of geometric errors of rotary axes on five-axis machine by on-machine measurement[J]. International Journal of Machine Tools & Manufacture, 2015, 89:182-191.
ERKAN T, MAYER J R R, DUPONT Y.Volumetric distortion assessment of a five-axis machine by probing a 3D reconfigurable uncalibrated master ball artefact[J].Precision Engineering, 2011, 35(1):116-125.
ISO 230-7:2015, Test code for machine tools-Part7:Geometric accuracy of axes of rotation[S]. 2015.
谢春, 张为民. 车铣复合加工中心综合误差检测及补偿策略[J]. 光学精密工程, 2014, 22(4):1004-1011. XIE CH, AHANG W M.. Comprehensive measurement errors of 5-axis turning-milling centers and their compensation strategies[J].Opt. Precision Eng., 2014, 22(4):1004-1011. (in Chinese)
吕程, 刘子云, 刘子建, 等. 广义径向基函数神经网络在热误差建模中的应用[J]. 光学精密工程, 2015, 23(6):1705-1713. LU CH, LIU Z Y, LIU Z J, et al.. Application of generalized radial basis function neural network to thermal error modeling[J].Opt. Precision Eng., 2015, 23(6):1705-1713. (in Chinese)
张永志, 董俊慧. 基于模糊C均值聚类的模糊RBF神经网络预测焊接接头力学性能建模[J]. 机械工程学报, 2014, 50(12):58-64. ZHANG Y ZH, DONG J H. Modeling fuzzy RBF neural network to predict of mechanical properties of welding joints based on fuzzy C-means cluster[J].Journal of Mechanical Engineering, 2014, 50(12):58-64. (in Chinese)
温秀兰, 王东霞, 朱晓春, 等. 基于坐标测量机的自由曲面检测采样策略[J]. 光学精密工程, 2014, 22(10):2725-2732. WEN X L, WANG D X, ZHU X CH, et al.. Sampling strategy for free-form surface inspection by using coordinate measuring machines[J].Opt. Precision Eng., 2014, 22(10):2725-2732. (in Chinese)
0
浏览量
1383
下载量
3
CSCD
关联资源
相关文章
相关作者
相关机构