热误差是影响高精密数控机床加工精度的重要因素。为了提高机床加工精度和性能,减少机床运行中产生的热误差,文章提出一种基于热图像的灰狼优化算法(grey wolf optimization algorithm,GWOA)和双向长短期记忆神经网络(bidirectional lon...热误差是影响高精密数控机床加工精度的重要因素。为了提高机床加工精度和性能,减少机床运行中产生的热误差,文章提出一种基于热图像的灰狼优化算法(grey wolf optimization algorithm,GWOA)和双向长短期记忆神经网络(bidirectional long short-term memory,BiLSTM)混合的热误差预测模型。首先,采用热成像仪获取机床主轴区域的温度场信息;其次,利用DBSCAN聚类(density-based spatial clustering of applications with noise)算法和相关系数法筛选出温度敏感点;然后,通过模拟灰狼群体捕食行为,在参数空间中进行搜索以找到BiLSTM所需的最优参数;最后,使用获得的机床温度敏感点和热位移数据进行热误差预测,并在试验机床上进行验证。实验结果表明,使用GWOA优化BiLSTM神经网络的预测模型相比BiLSTM神经网络预测模型的均方根误差(root mean square error,RMSE)和平均绝对误差(mean absolute error,MAE)分别减小了约0.5180、0.3823μm,决定系数R^(2)提升了0.0578。与BiLSTM神经网络模型相比,利用GWOA优化后的模型具有更加优良的预测性能。展开更多
The in-situ micro-nano Ti_(2)AlC particles reinforced TiAl(Ti_(2)AlC/TiAl)composite was fabricated using spark plasma sintering.The hot workability of Ti_(2)AlC/TiAl composite was studied,and the effect of micro-nano ...The in-situ micro-nano Ti_(2)AlC particles reinforced TiAl(Ti_(2)AlC/TiAl)composite was fabricated using spark plasma sintering.The hot workability of Ti_(2)AlC/TiAl composite was studied,and the effect of micro-nano particles on flow stress and dynamic recrystallization of composite was discussed.The results showed that the micro-nano Ti_(2)AlC particles included strengthening and softening effects during hot deformation,resulting in the fact that the Ti_(2)AlC/TiAl composite exhibited a higher flow stress and more sufficient dynamic recrystallization.The strengthening effect was mainly attributed to the Ti_(2)AlC particles induced refinement strengthening and hindered dislocation motion at the initial stage.Moreover,the precipitation of nano-TiCr2 particles induced by stress concentration during hot deformation also contributed to higher flow stress via impeding dislocation motion.Meanwhile,the refined microstructure and dislocation pile-up caused by micro-nano particles during deformation provided more nucleation sites for dynamic recrystallization,which significantly promoted the dynamic recrystallization of the second stage.The present results reveal that the Ti_(2)AlC/TiAl composite exhibited excellent hot workability,which is important to promote the application of TiAl alloys.展开更多
双主轴数控机床是一种具有两个独立的加工主轴的先进数控机床。本文以某机床厂研发的G650双主轴数控机床工作台为研究对象,采用CAD软件建立了其三维模型,并采用有限元法及其软件对工作台进行了静力学分析和模态分析,研究了工作台在铣削...双主轴数控机床是一种具有两个独立的加工主轴的先进数控机床。本文以某机床厂研发的G650双主轴数控机床工作台为研究对象,采用CAD软件建立了其三维模型,并采用有限元法及其软件对工作台进行了静力学分析和模态分析,研究了工作台在铣削加工状态下的静力学特性和约束状态下的模态特性。通过分析结果可知,工作台的最大形变约2.30 μm、最大应力约9.78 MPa,前四阶固有频率分别为952.86 Hz、1003.30 Hz、1360.60 Hz、1428.90 Hz。分析结果表明了该工作台能确保待加工零件的加工精度和定位精度,为后续的优化设计工作奠定了基础。Double spindle CNC machine tool is an advanced CNC machine tool with two independent machining spindles. This paper takes the table of G650 double spindle CNC machine tool developed by a machine tool factory as the research object, establishes its three-dimensional model by using CAD software, and carries out static analysis and modal analysis of the table by using the finite element method and its software to study the static characteristics of the table in the milling machining state and the modal characteristics of the constrained state. It was found that the maximum deformation of the panel was approximately 2.30 µm, the maximum stress was approximately 9.78 MPa and the first four eigenfrequencies were 952.86 Hz, 1003.30 Hz, 1360.60 Hz and 1428.90 Hz. The analysis results show that the table can ensure the machining accuracy and positioning accuracy of the parts to be machined, which lays the foundation for the subsequent optimisation design work.展开更多
文摘热误差是影响高精密数控机床加工精度的重要因素。为了提高机床加工精度和性能,减少机床运行中产生的热误差,文章提出一种基于热图像的灰狼优化算法(grey wolf optimization algorithm,GWOA)和双向长短期记忆神经网络(bidirectional long short-term memory,BiLSTM)混合的热误差预测模型。首先,采用热成像仪获取机床主轴区域的温度场信息;其次,利用DBSCAN聚类(density-based spatial clustering of applications with noise)算法和相关系数法筛选出温度敏感点;然后,通过模拟灰狼群体捕食行为,在参数空间中进行搜索以找到BiLSTM所需的最优参数;最后,使用获得的机床温度敏感点和热位移数据进行热误差预测,并在试验机床上进行验证。实验结果表明,使用GWOA优化BiLSTM神经网络的预测模型相比BiLSTM神经网络预测模型的均方根误差(root mean square error,RMSE)和平均绝对误差(mean absolute error,MAE)分别减小了约0.5180、0.3823μm,决定系数R^(2)提升了0.0578。与BiLSTM神经网络模型相比,利用GWOA优化后的模型具有更加优良的预测性能。
基金supported by the National Natural Science Foundation of China(No.52001262)the Natural Science Foundation of Zhejiang Province,China(No.LZY22E010001)the Natural Science Foundation of Shaanxi Province,China(No.2020JC-50)。
文摘The in-situ micro-nano Ti_(2)AlC particles reinforced TiAl(Ti_(2)AlC/TiAl)composite was fabricated using spark plasma sintering.The hot workability of Ti_(2)AlC/TiAl composite was studied,and the effect of micro-nano particles on flow stress and dynamic recrystallization of composite was discussed.The results showed that the micro-nano Ti_(2)AlC particles included strengthening and softening effects during hot deformation,resulting in the fact that the Ti_(2)AlC/TiAl composite exhibited a higher flow stress and more sufficient dynamic recrystallization.The strengthening effect was mainly attributed to the Ti_(2)AlC particles induced refinement strengthening and hindered dislocation motion at the initial stage.Moreover,the precipitation of nano-TiCr2 particles induced by stress concentration during hot deformation also contributed to higher flow stress via impeding dislocation motion.Meanwhile,the refined microstructure and dislocation pile-up caused by micro-nano particles during deformation provided more nucleation sites for dynamic recrystallization,which significantly promoted the dynamic recrystallization of the second stage.The present results reveal that the Ti_(2)AlC/TiAl composite exhibited excellent hot workability,which is important to promote the application of TiAl alloys.
文摘双主轴数控机床是一种具有两个独立的加工主轴的先进数控机床。本文以某机床厂研发的G650双主轴数控机床工作台为研究对象,采用CAD软件建立了其三维模型,并采用有限元法及其软件对工作台进行了静力学分析和模态分析,研究了工作台在铣削加工状态下的静力学特性和约束状态下的模态特性。通过分析结果可知,工作台的最大形变约2.30 μm、最大应力约9.78 MPa,前四阶固有频率分别为952.86 Hz、1003.30 Hz、1360.60 Hz、1428.90 Hz。分析结果表明了该工作台能确保待加工零件的加工精度和定位精度,为后续的优化设计工作奠定了基础。Double spindle CNC machine tool is an advanced CNC machine tool with two independent machining spindles. This paper takes the table of G650 double spindle CNC machine tool developed by a machine tool factory as the research object, establishes its three-dimensional model by using CAD software, and carries out static analysis and modal analysis of the table by using the finite element method and its software to study the static characteristics of the table in the milling machining state and the modal characteristics of the constrained state. It was found that the maximum deformation of the panel was approximately 2.30 µm, the maximum stress was approximately 9.78 MPa and the first four eigenfrequencies were 952.86 Hz, 1003.30 Hz, 1360.60 Hz and 1428.90 Hz. The analysis results show that the table can ensure the machining accuracy and positioning accuracy of the parts to be machined, which lays the foundation for the subsequent optimisation design work.
