Physics-guided logistic classification for tool life modeling and process parameter optimization in machining

This paper describes a physics-guided logistic classification method for tool life modeling and process parameter optimization in machining. Tool life is modeled using a classification method since the exact tool life cannot be measured in a typical production environment where tool wear can only be directly measured when the tool is replaced. In this study, laboratory tool wear experiments are used to simulate tool wear data normally collected during part production. Two states are defined: tool not worn (class 0) and tool worn (class 1). The non-linear reduction in tool life with cutting speed is modeled by applying a logarithmic transformation to the inputs for the logistic classification model. A method for interpretability of the logistic model coefficients is provided by comparison with the empirical Taylor tool life model. The method is validated using tool wear experiments for milling. Results show that the physics-guided logistic classification method can predict tool life using limited datasets. A method for pre-process optimization of machining parameters using a probabilistic machining cost model is presented. The proposed method offers a robust and practical approach to tool life modeling and process parameter optimization in a production environment.     

Intelligent tool wear monitoring based on parallel residual and stacked bidirectional long short-term memory network

Effective tool wear monitoring (TWM) is essential for accurately assessing the degree of tool wear and for timely preventive maintenance. Existing data-driven monitoring methods mainly rely on complex feature engineering, which reduces the monitoring efficiency. This paper proposes a novel TWM model based on a parallel residual and stacked bidirectional long short-term memory (PRes–SBiLSTM) network. First, a parallel residual network (PResNet) is used to extract the multi-scale local features of sensor signals adaptively. Subsequently, a stacked bidirectional long short-term memory (SBiLSTM) network is used to obtain the time-series features related to the tool wear characteristics. Finally, the predicted tool wear value is outputted through a fully connected network. A smoothing correction method is applied to improve the prediction accuracy. The proposed model is experimentally verified to have a high prediction accuracy without sacrificing its generalization ability. A TWM system framework based on the PRes–SBiLSTM network is proposed, which has a certain reference value for TWM in actual industrial environments.     

合金工具钢二次硬化能力的判别

为寻求在钢的成份和二次硬化能力之间的定量关系,对国内外40多种钢按作者提出的合金化参数进行计算和整理,证明了用“平衡碳”(Cp)和“碳饱和度”(A) 两个合金化参数判别 (预报) 钢的二次硬度的可能性。     

The statistical modeling of surface roughness in high-speed flat end milling

Surface roughness is one of the most important requirements in machining process. The surface roughness value is a result of the tool wear. When tool wear increase, the surface roughness also increases. The determination of the sufficient cutting parameters is a very important process obtained by means of both minimum surface roughness values and long tool life. The statistical models were developed to predict the surface roughness.This paper presents the development of a statistical model for surface roughness estimation in a high-speed flat end milling process under wet cutting conditions, using machining variables such as spindle speed, feed rate, depth of cut, and step over. First- and second-order models were developed using experimental results of a rotatable central composite design, and assessed by means of various statistical tests. The highest coefficient of correlation (R_adj²) (88%) was obtained with a 10-parameter second-order model. Meanwhile, a time trend was observed in residual values between model predictions and experimental data, reflecting the probable effect of the tool wear on surface roughness. Thus, in order to enhance the estimation capability of the model, another independent variable was included into the model to account for the effect of the tool wear, and the total operating time of the tool was selected as the most suitable variable for this purpose. By inserting this new variable as a linear term into the model, R_adj² was increased to 94% and a good fit was observed between the model predictions and supplementary experimental data.In this study, it was observed that, the order of significance of the main variables is as X₅>X₃>X₄>X₁>X₂ (total machining time, depth of cut, step over, spindle speed and feed rate, respectively).     

Novel methods for rapid assessment of tool performance in milling

The paper examines the effectiveness of two innovative techniques designed to rapidly optimize a milling application. One of them relates to quantifying the relative wear of different insert grades concurrently in a single cutting test, by mounting the inserts in the same cutter, for a quick comparative performance evaluation. Experimental results that illustrate the validity and limitation of this concept, and a scheme for enhancing the reliability of the test method are presented. The other technique refers to rapid identification of the optimum feed/tooth that corresponds to maximum tool life. This entails a test wherein individual inserts in the cutter are subject to feed/tooth that are multiples of a base value, by selectively leaving appropriate number of consecutive insert pockets unoccupied. These novel techniques complement known accelerated tool life tests, and are expedient for industries that engage short production runs, in terms of selecting a suitable insert grade for an application, and determining optimal cutting conditions for the selected grade.     

Influence of radial and axial runouts on surface roughness in face milling with round insert cutting tools

In face milling processes, the surface quality of the machined part depends on many factors, including feed, cutting tool geometry and tool errors. In this work, a numerical model for predicting the surface profile and surface roughness as a function of these factors is presented, incorporating a random values generation algorithm that makes it possible to determine the variation in surface roughness from the values that can be adopted by tool errors. This work is focused on round insert cutting tools and the influence of tool errors such as radial and axial runouts. The results that correspond to a number of teeth equal to 4, insert diameter of 12 mm, depth of cut of 0.5 mm, cutting speed of 120 m/min and feed of 0.4–1.4 mm/rev are analysed. Milling experiments are made to verify the validity of the model and the discrepancies between the experimental and theoretical surface profiles are assumed to be a consequence of different factors such as the variation in undeformed chip thickness along the surface profile.     

变形体温度场和位移场的计算

本文用热源法对简单热传导问题进行了解析解的计算，并应用PDE工具箱求解热传导偏微分方程得到数值解。通过两种温度场的计算结果求出相应的位移场结果，比较可知MATLAB中PDE工具箱对难以用解析法求解的热传导问题有一定的指导作用。     

High-speed milling of titanium alloys using binderless CBN tools

The performance of conventional tools is poor when used to machine titanium alloys. In this paper, a new tool material, which is binderless cubic boron nitride (BCBN), is used for high-speed milling of a widely used titanium alloy Ti–6Al–4V. The performance and the wear mechanism of the BCBN tool have been investigated when slot milling the titanium alloy in terms of cutting forces, tool life and wear mechanism. This type of tool manifests longer tool life at high cutting speeds. Observations based on the SEM and EDX suggest that adhesion of workpiece and attrition are the main wear mechanisms of the BCBN tool when used in high-speed milling of Ti–6Al–4V.     

平砧拔长矩形截面毛坯的理论

从理论上分析与论证了平砧拔长矩形截面毛坯只有砧宽比(W/H)一个工艺参数是不足的,认为应增加,个工艺参数料宽比(B/H),才能正确描述拔长毛坯中心区域的应力状态与有效控制锻件质量。该理论已被实验验证。     

Tool design in a multi-stage drawing and ironing process of a rectangular cup with a large aspect ratio using finite element analysis

Tool design is carried out for a multi-stage deep drawing and ironing process of a rectangular cup with the large aspect ratio using the result of the finite element analysis. The analysis incorporates three-dimensional continuum elements for an elasto-plastic finite element method with the explicit time integration scheme using LS-DYNA3D. The analysis simulates the five-stage deep drawing and ironing process with the thickness control of the cup wall. Simulation is performed in order to investigate the failure by tearing during the forming process at the initial state of tool design. The analysis reveals that the difference of the drawing ratio within the cross section induces non-uniform metal flow which causes severe local extension. The irregular contact condition between the blank and the die also induces non-uniform metal flow which causes local wrinkling. This paper identifies such unfavorable mechanism in the rectangular cup drawing with ironing and proposes a new tool design with the guideline for modification in the design of the process and the sequential tool shape. The finite element analysis result with the improved tool design confirms that the proposed design not only reduces the possibility of failure but also improves the quality of a deep-drawn product. The numerical result shows fair coincidence with the experimental result.