Multiple-objective optimisation of machining operations based on neural networks

Metal cutting plays an important role in manufacturing industries. Optimisation of cutting parameters represents a key component in machining process planning. In this paper, a neural network based approach to multiple-objective optimization of cutting parameters is presented. First, the problem of determining the optimum machining parameters is formulated as a multiple-objective optimization problem. Then, neural networks are proposed to represent manufacturers' preference structures. To demonstrate the procedure and performance of the neural network approach, an illustrative example is discussed in detail.Nomenclature v cutting speed (m/min) - f feed rate per revolution (mm/rev) - d depth of cut per pass (mm) - T _p total operation time per part (min) - T _i set-up time per part (min) - T _c tool change time (min) - T _i idle time per part (min) - C _p cost per part ($) - C _t cost of tool per piece ($) - C _l labor cost per unit time ($/min) - C _o overhead per unit time ($/min) - V volume to be removed per part (mm³) - MRR metal removal rate (mm³/min) - TL tool life (min) - SR surface roughness (m) - H _p arithmetic centre-line average (m) - P cutting power (kW) - F cutting force (kg) - interface temperature (°C)     

零传动齿轮加工机床关键技术研究

突破传统的齿轮加工机床的结构设计原理,采用电主轴、DDR、DDL技术直接驱动齿轮加工机床的刀具、工作台的回转及直线进给系统,完全取消所有机械传动环节,实现动力源对机床工作部件的直接驱动,即零传动.文章就基于零传动原理对滚齿机的电主轴、DDR、DDL等关键技术作了详细分析和研究,对研究和开发我国高速、高精度零传动齿轮加工机床有重要的理论意义和实用价值.     

正确使用刀具半径补偿功能

大部分数控机床都具有刀具半径补偿功能，这就使编程人员可以直接根据零件图纸进行编程，而不必考虑刀具半径的尺寸因素。这里结合实例对刀具半径补偿的用途、过切情况、使用时应注意的问题进行了简单的分析。     

Development of novel sustainable neat-oil metal working fluids for stainless steel and titanium alloy machining. Part 1. Formulation development

This paper introduces and describes the development and application of methodologies for the formulation of novel sustainable neat-oil metal removal fluids. A further paper will describe the methodologies being employed and the results of the performance benchmarking of the final fluid formulations for stainless steel and aerospace-grade titanium alloy materials. In this paper, a stepwise approach to the development of novel sustainable neat-oil metal removal formulations is described with a detailed discussion and analysis of the approach taken and the methodologies developed and applied. Two target applications were identified for cutting stainless steel and aerospace-grade titanium alloys. The key required properties of the fluids for these applications were combined with targets identified for cost, low temperature properties, kinetic viscosity (KV) and oxidative stability. Samples of base oils were obtained and characterised. The oils ranged from commodity commercial and specialist natural vegetable oils to chemically modified vegetable-oil-derived fatty acid esters and polyols. The selected oils were used to create blends which were screened for their key properties. From this work, four blends of base oils were identified for being taken forwards to the formulation screening stage. These blends represented a range of natural and modified oils blended in such a way as to achieve all of the required key properties of cost, KV, melt/pour points and oxidative stability. To determine if the oils were likely to also perform well as metal cutting fluids, they were subjected to a range of tests with and without the addition of certain additives, and their performances were benchmarked against a range of mineral oil and polyol-ester-based commercial fluids currently supplied to the target applications areas. The tests employed were: SRV, microtap and oxidation stability. The issues involved in the extrapolation of results from tribological testing to the prediction of fluid cutting performance are highlighted and discussed. From this work, one base oil blend for each of the two target applications was identified and the best performing mineral and polyol ester benchmark fluids were selected. Full-scale drilling and rigid torque tapping tests were used to refine formulations and to screen other additives identified in parallel microtap tests. The durability, oxidation stability, machine tool compatibility and misting potentials of the final formulations were also benchmarked using a range of standard and novel methodologies—this work will be described in a later paper.     

Optimization of machining parameters using genetic algorithm and experimental validation for end-milling operations

Optimization of cutting parameters is valuable in terms of providing high precision and efficient machining. Optimization of machining parameters for milling is an important step to minimize the machining time and cutting force, increase productivity and tool life and obtain better surface finish. In this work a mathematical model has been developed based on both the material behavior and the machine dynamics to determine cutting force for milling operations. The system used for optimization is based on powerful artificial intelligence called genetic algorithms (GA). The machining time is considered as the objective function and constraints are tool life, limits of feed rate, depth of cut, cutting speed, surface roughness, cutting force and amplitude of vibrations while maintaining a constant material removal rate. The result of the work shows how a complex optimization problem is handled by a genetic algorithm and converges very quickly. Experimental end milling tests have been performed on mild steel to measure surface roughness, cutting force using milling tool dynamometer and vibration using a FFT (fast Fourier transform) analyzer for the optimized cutting parameters in a Universal milling machine using an HSS cutter. From the estimated surface roughness value of 0.71 μm, the optimal cutting parameters that have given a maximum material removal rate of 6.0×10³ mm³/min with less amplitude of vibration at the work piece support 1.66 μm maximum displacement. The good agreement between the GA cutting forces and measured cutting forces clearly demonstrates the accuracy and effectiveness of the model presented and program developed. The obtained results indicate that the optimized parameters are capable of machining the work piece more efficiently with better surface finish.     

Machinability of Elongated Coarse Grain Fe-Based Superalloys

□ In conventional metal cutting process, materials are assumed to be homogeneous and isotropic structure. However, some materials with a single crystal or coarse elongated polycrystalline demonstrate strong anisotropic behavior in physical and mechanical properties in machining of some superalloy materials. The anisotropic structure always leads to variation at machinability properties of the material. In this study, machinability properties of ferritic superalloy PM2000, which had elongated a few coarse grains, were investigated. These properties were determined by investigation of chip formation, cutting forces and surface roughness. Machinability was assessed by single-point turning on a CNC lathe and turning forces were measured by using a Kistler Lathe Dynamometer. The chip formation mechanisms in machining of PM2000 at various cutting speeds were determined by using a quick-stop device (QSD). Chip roots and machined surfaces were analyzed by means of scanning electron microscopy (SEM). The results indicated that the machinability properties of the PM2000 were changed by orientated coarse grain structure. Three types chip formation mechanism were determined at the same cutting conditions. Also, surface roughness on the machined each grain changed with changing the grain to be cut. Surface roughness and force fluctuations decreased with increasing the cutting speed; however, tool wearing increased.     

时效态18Ni钢切削过程中的热塑剪切失稳实验

不同切削速度下对18Ni马氏体时效钢进行切削试验，并用光学显微镜和电子显微镜观察切屑根部，发现有热塑剪切失稳现象，分析其组织结构特征及影响因素；再按热塑剪切失稳判据及显微组织分析热处理对热塑剪切失稳的影响。     

轴类零件形位误差的数据处理

在万能工具显微镜上用光学分度头对典型轴类零件形位误差如圆度、轴线同轴度等的测量误差进行了探讨 ,并介绍了最小二乘法以及豪斯荷尔德分解法在进行数据处理时的应用及精度分析。     

重型车床切削加工中的工艺问题

从粗加工和精加工的角度,对重型车床切削中的刀具材料、刀具角度、切削用量的选择以及刀具和工件的安装等工艺问题进行分析,结合生产实际,给出合理的工艺方案。     

Quantification and visualization of anisotropy in trabecular bone

A number of methods for measuring anisotropy in trabecular bone using high‐resolution X‐ray computed tomography exist, which give different answers but have not been compared in detail. In this study, we examine the mean‐intercept length (MIL), star volume distribution (SVD) and star length distribution (SLD) methods, their algorithmic implementation for three‐dimensional (3D) data, and how their results relate to each other. A uniform ordered sampling scheme for determining which orientations to sample during analysis enhances the reproducibility of anisotropy and principal component direction determinations, with no evident introduction of biasing. This scheme also facilitates the creation of a 3D rose diagram that can be used to gain additional insights from the data. The directed secant algorithm that is frequently used for traversing pixel and voxel grids for these calculations is prone to bias unless a previously unreported normalization is used. This normalization ameliorates the bias present when using cubic voxels, and also permits calculations on data sets in which the slice spacing is not equal to the pixel spacing. Overall, the three methods for quantification of anisotropy give broadly similar results, but there are systematic divergences that can be traced to their differences in data and processing, and which may impact on their relative utility in estimating mechanical properties. Although discussed in the context of computed tomography of trabecular bone, the methods described here may be applied to any 3D data set from which fabric information is desired.