A COMPARATIVE STUDY OF FEATURE SELECTION FOR HIDDEN MARKOV MODEL-BASED MICRO-MILLING TOOL WEAR MONITORING

This paper presents a discriminant feature selection approach for hidden Markov model (HMM) modeling of micro-milling tool conditions. The approach is compared with other popular feature selection methods such as principal component analysis (PCA) and automatic relevance determination (ARD) according to their HMM classification rate. In tool condition monitoring (TCM), there are a lot of features that contain redundant information or less sensitive to tool state discrimination. These features are expected to be deleted for less computation and more robust modeling of tool conditions. Fisher's linear discriminant analysis (FDA) is modified for this purpose. The FDA is generally used for classification, and the features are mapped to another space and lose their physical meanings. In the modified discriminant feature selection, the features are selected in the original feature space by maximizing tool state separation and ranked by their separation ability between different tool states. Experimental results from both micro-milling of copper and steel under different working conditions indicate that the FDA is superior to both PCA and ARD for feature selection in HMM's classification. The reasons behind these differences are also discussed.     

航空钛合金Ti6Al4V微细铣削加工数值模拟与试验研究

根据实际微细铣削加工方法,采用DEFORM软件建立螺旋立铣刀铣削加工分析模型,利用该模型分析硬质合金刀具铣削加工航空用钛合金Ti6Al4V过程中的铣削力变化,在相同条件下进行铣削加工试验。试验结果表明:随着铣削的进行,刀具与切屑逐步接触,各个铣削方向切削力逐渐增加;随着铣削的进行,切削厚度逐渐减小、铣削温度升高、工件材料力学性能和铣削力开始降低;铣削深度、单齿进给量及铣削速度对铣削力均有不同程度的影响,其中单齿进给量影响最大。     

微细铣削切削力正交实验研究

在自行研制的三轴联动微细铣床上,选取典型微三维零件特征进行铣槽和侧铣两种工况正交铣削实验,对微细切削力进行测量和分析。深入研究了主轴转速、轴向切深、每齿进给量等工艺参数对微细切削力的影响规律,以优化加工参数,提高微铣削的加工效率和加工精度。     

Investigating material removal rate and surface roughness using multi-objective optimization for focused ion beam (FIB) micro-milling of cemented carbide

Cemented carbide has been investigated as a useful material for the fabrication of micro devices. Focused ion beam (FIB) micro-milling has been found to be one of the most appropriate methods for the fabrication of micro devices. The experimental FIB micro-milling on cemented carbide have been conducted according to the L₁₆ orthogonal array of Taguchi technique. Beam current, extraction voltage, angle of beam incidence, dwell time and percentage overlap between beam diameters have been considered as process variables of FIB micro-milling in experimental design. Material removal rate (MRR) and surface roughness have been determined experimentally for FIB micro-milling of cemented carbide and beam current has been identified as the most significant parameter. The minimum surface roughness of 5.6 nm has been reported on cemented carbide, which is not a usual practice to achieve on such polycrystalline material, and hence it may be considered as a significant research contribution. Maximum MRR of 0.4836 μm³/s has been reported. Moreover, genetic algorithm toolbox of MATLAB has been utilized for multi-objective optimization between MRR and surface roughness. The corresponding optimum values of MRR and surface roughness for multi-objective optimization have been represented by pareto optimum solution generated by genetic algorithm. The research work presented in this paper determines the setting of process parameters of FIB micro-milling for achieving a specific combination of MRR and surface roughness on cemented carbide.     

Thermal and mechanical modeling analysis of laser-assisted micro-milling of difficult-to-machine alloys

This study is focused on numerical modeling analysis of laser-assisted micro-milling (LAMM) of difficult-to-machine alloys, such as Ti6Al4V, Inconel 718, and stainless steel AISI 422. Multiple LAMM tests are performed on these materials in side cutting of bulk and fin workpiece configurations with 100-300 μm diameter micro endmills. A 3D transient finite volume prismatic thermal model is used to quantitatively analyse the material temperature increase in the machined chamfer due to laser-assist during the LAMM process. Novel 2D finite element (FE) models are developed in ABAQUS to simulate the continuous chip formation with varying chip thickness with the strain gradient constitutive material models developed for the size effect in micro-milling. The steady-state workpiece and tool cutting temperatures after multiple milling cycles are analysed with a heat transfer model based on the chip formation analysis and the prismatic thermal model predictions. An empirical tool wear model is implemented in the finite element analysis to predict tool wear in the LAMM side cutting process. The FE model results are discussed in chip formation, flow stresses, temperatures and velocity fields to great details, which relate to the surface integrity analysis and built-up edge (BUE) formation in micro-milling.     

单晶DD98微尺度铣削表面质量试验研究

为探究单晶DD98微尺度铣削的表面质量,采用直径为0.6mm的微铣刀对单晶DD98进行三因素五水平的微尺度铣削正交试验。通过极差分析和方差分析发现：主轴转速对DD98表面质量的影响最大,铣削深度的影响次之,进给速度的影响最小;单晶DD98表面质量最好的工艺参数组合为主轴转速36000r/min,铣削深度5μm,进给速度100μm/s。得到了主轴转速、铣削深度和进给速度对表面质量的影响规律,并对其机理进行了分析,从而为单晶DD98材料的微尺度铣削加工提供理论依据。     

单晶Ni3Al基高温合金微铣削表面粗糙度试验研究

为研究单晶高温合金的微铣削表面粗糙度,采用直径为0.8mm的双刃硬质合金微铣刀,对典型的单晶Ni3Al基高温合金IC10进行微尺度铣削的三因素五水平正交试验研究。通过极差分析找出主轴转速、进给速度、进给深度对微铣削表面质量影响的主次因素。通过优化获得理想的切削工艺参数组合,所获表面粗糙度为801nm。对其切削机理和影响表面质量的原因进行深入的分析,其结果对单晶高温合金的微加工理论的机理揭示具有一定的指导意义。     

超微粉碎对小麦胚芽膳食纤维物化性质的影响

研究了超微粉碎对麦胚膳食纤维的持水力、膨胀力、阳离子交换能力以及麦胚全粉水溶性的影响。结果表明,超微粉碎有助于麦胚膳食纤维的持水力和膨胀力以及麦胚全粉水溶性的增大,而阳离子交换能力却因微粉碎而降低。     

金刚石涂层微铣刀的铣削加工试验

为了掌握金刚石涂层对其铣削性能的影响,针对直径为50 μm级的硬质合金微铣刀,进行了金刚石涂层与未涂层硬质合金微铣刀具微槽铣削试验。通过使用线电极电火花磨削技术制备出直径为50 μm级的D形微铣刀,采用金刚石涂层和未涂层刀具在纯铜工件上开展微槽铣削工艺试验;使用白光干涉仪、超景深显微镜等仪器来观测微槽表面形貌、粗糙度等随铣削距离变化的规律,分析金刚石涂层对硬质合金微铣刀铣削加工质量的影响。结果表明：采用金刚石涂层刀具加工的微槽具有较少的毛刺,表面粗糙度值约为未涂层刀具铣削的粗糙度值的1/2,并且能够在一定距离内保持稳定的槽宽、粗糙度值和侧面形貌。     

开放式微细铣削数控系统的开发

简述了开放式数控系统的概念,并在此基础上提出了一套面向软件NC技术的开放式数控系统的设计方案,开发了基于DMC1842运动控制卡的数控系统界面软件,可完成对控制卡参数的在线修改和自动编程,实现对微细铣床的准确控制。本系统具有良好的开放性和较高的实用价值。