Prediction of burr height formation in blanking processes using neural network

Productivity and quality in sheet metal blanking processes part can be assessed by the burr height of the sheared edge after blanking. This paper combines predictive finite element approach with neural network modelling of the leading blanking parameters in order to predict the burr height of the parts for a variety of blanking conditions.Experiments on circular blanking operation has been performed to verify the validity of the proposed approach.The numerical results obtained by finite element computation including damage and fracture modelling and tool wear effects were utilized to train the developed simulation environment based on back propagation neural network modelling.A trained neural network system was used in predicting burr height of the blanked parts versus tool wear state and punch-die clearance.The comparative study between the results obtained by neural network computation and the experimental ones gives good results.     

Development of intelligent system to minimize burr formation in face milling

The exit burr generated in the face milling operation at the edge of the workpiece usually requires deburring processes to enhance the level of precision of the parts. This paper is to geometrically understand the formation of the exit burr in the face milling operation on the arbitrary shaped workpiece with multiple feature such as hole, spline, and arc so that we can suggest the cutting conditions and tool path to minimize the burr formation on the given workpiece in the early design stage. The burr formation mechanism in each type of burr is classified based on the experimental results. A database is developed to store and predict burr formation results. A Windows based program is developed with the algorithm including three steps, i.e., the feature identification, the cutting condition identification, and the analysis on exit burr formation. We can predict which portion of the workpiece would have the exit burr in advance so that we can manage to find a way to minimize the exit burr formation in an actual cutting. Here, the idea of critical burr length is introduced as a criterion in optimization.     

Influence of cutting edge radius on surface integrity and burr formation in milling titanium

The influence of the cutting edge micro geometry on cutting process and on tool performance is subject to several research projects. Recently, published papers mainly focus on the cutting edge rounding and its influence on tool life and cutting forces. For applications even more important, however, is the influence of the cutting edge radius on the integrity of the machined part. Especially for titanium, which is used in environments requiring high mechanical integrity, the information about the dependency of surface integrity on cutting edge geometry is important. This paper therefore studies the influence of the cutting edge radius on surface integrity in terms of residual stress, micro hardness, surface roughness and optical characterisation of the surface and near surface area in up and down milling of the titanium alloy Ti–6Al–4V. Moreover, the influence of the cutting edge radius on burr formation is analysed. The experiments show that residual stresses increase with the cutting edge radius especially in up milling, whereas the influence in down milling is less pronounced. The influence of the cutting edge radius on surface roughness is non-uniform. The formation of burr increases with increasing cutting edge radius, and is thus in agreement with the residual stress tests.     

Selection of optimum tool geometry and cutting conditions using a surface roughness prediction model for end milling

Influence of tool geometry on the quality of surface produced is well known and hence any attempt to assess the performance of end milling should include the tool geometry. In the present work, experimental studies have been conducted to see the effect of tool geometry (radial rake angle and nose radius) and cutting conditions (cutting speed and feed rate) on the machining performance during end milling of medium carbon steel. The first and second order mathematical models, in terms of machining parameters, were developed for surface roughness prediction using response surface methodology (RSM) on the basis of experimental results. The model selected for optimization has been validated with the Chi square test. The significance of these parameters on surface roughness has been established with analysis of variance. An attempt has also been made to optimize the surface roughness prediction model using genetic algorithms (GA). The GA program gives minimum values of surface roughness and their respective optimal conditions.     

In-process estimation of radial immersion angle using cutting force in face milling

In this paper, a on-line estimation method of the radial immersion angle using cutting force is presented. The ratio of cutting forces in feed and cross-feed directions acting on the single tooth at the immersion angle is a function of the immersion angle and the ratio of radial to tangential cutting force. It is found that the ratio of radial to tangential cutting force is not affected by cutting conditions and axial rake angle, which implies that the ratio determined by one preliminary experiment can be used regardless of the cutting conditions for a given tool and workpiece material. Using the measured cutting force during machining and predetermined ratio, the radial immersion ratio is estimated in process. Various experimental results show that the proposed method works within5% error range.     

In-process estimation of radial immersion ratio in face milling using cutting force

In order to prevent tool breakage in milling, maximum total cutting force is regulated at a specific constant level, or threshold, through feed rate control. Since the threshold is a function of the immersion ratio, an estimation of the immersion ratio is necessary to flexibly determine the threshold. In this paper, a method of in-process estimation of the radial immersion ratio in face milling is presented. When an insert finishes sweeping, a sudden drop in cutting forces occurs. These force drops are equal to the cutting forces that act upon a single insert at the swept cutting angle and they can be acquired from cutting force signals in the feed and cross-feed directions. Average cutting forces per tooth period can also be calculated from the cutting force signals in two directions. The ratio of cutting forces acting upon a single insert at the swept angle of cut and the ratio of average cutting forces per tooth period are functions of the swept angle of cut and the ratio of radial to tangential cutting force. Using these parameters, the radial immersion ratio is estimated. Various experiments are performed to verify the proposed method. The results show that the radial immersion ratio can be estimated by this method regardless of other cutting conditions.Nomenclature F_T, F_R tangential and radial forces - F_X, F_Y cutting forces in feed direction and cross feed direction - dF_X, dF_Y cutting force differences before and after the immersion angle in X and Y direction - K_s specific cutting pressure - a depth of cut - r ratio between tangential force and radial force - s_t feed per tooth - instantaneous angle of cut - _s swept angle of cut - _T tooth spacing angle - w radial width of cut - R cutter radius - z number of inserts     

Selection of optimal cutting conditions for pocket milling using genetic algorithm

Pocket milling is the most known machining operation in the domains of aerospace, die, and mold manufacturing. In the present work, GA-OptMill, a genetic algorithm (GA)-based optimization system for the minimization of pocket milling time, is developed. A wide range of cutting conditions, spindle speed, feed rate, and axial and radial depth of cut, are processed and optimized while respecting the important constraints during high-speed milling. Operational constraints of the machine tool system, such as spindle speed and feed limits, available spindle power and torque, acceptable limits of bending stress and deflection of the cutting tool, and clamping load limits of the workpiece system, are respected. Chatter vibration limits due to the dynamic interaction between cutting tool and workpiece are also embedded in the developed GA-OptMill system. Enhanced capabilities of the system in terms of encoded GA design variables and operators, targeted cutting conditions, and constraints are demonstrated for different pocket sizes. The automatically identified optimal cutting conditions are also verified experimentally. The developed optimization system is very appealing for industrial implementation to automate the selection of optimal cutting conditions to achieve high productivity.     

Mathematical model for cutting force in rotary ultrasonic face milling of brittle materials

Rotary ultrasonic machining of brittle materials, such as glass, ceramics, silicon, and sapphire, has been explored in a large number of experimental and theoretical investigations. Mechanistic models have been developed to predict the material removal rate or cutting force in the rotary ultrasonic machining of brittle materials. However, most merely describe the rotary ultrasonic machining process of drilling holes in brittle materials. There are no reports on the development of a cutting force model for flat surface rotary ultrasonic machining, i.e., rotary ultrasonic face milling. This paper presents a mathematical model for the cutting force in the rotary ultrasonic face milling of brittle materials under the assumption that brittle fracture removal is the primary mode of material removal. Verification experiments are conducted for the developed cutting force model and show that the trends of input variables for the cutting force agree well with the trends of the developed cutting force model. The developed cutting force model can be applied to evaluate the cutting force in the rotary ultrasonic face milling of brittle materials.     

Prediction of tool breakage in face milling using support vector machine

A new approach is proposed using a support vector machine (SVM) to classify the feature of the cutting force signal for the prediction of tool breakage in face milling. The cutting force signal is compressed by averaging the cutting force signals per tooth to extract the feature of the cutting force signal due to tool breakage. With the SVM learning process, the output of SVM’s decision function can be utilized to identify a milling cutter with or without tool breakage. Experimental results are presented to verify the feasibility of this tool breakage prediction system in milling operations.     

Relationship between cutting conditions and chips morphology during milling of aluminium Al-2050

In the aeronautical field, some parts are forged and consequently some fibers orientation occurs. However, the thin walls are hard to get with forging method. Consequently, some machining operations are done to get a thin wall and reduce the weight of part. However, because of the size of part of the volume of chips can be significant. The ratio between the final weight of part and the final weight of chips is approximately 80 %. To improve the economical and the environmental sustainability, a method consists of recycling directly the chip after machining operations. However, studies show a great impact of different points on chip recyclability like chip thickness, chip roughness, or chip density. Consequently, control of the chip morphology is a first point in ensuring a good recyclability. This article concerns the relationship between the cutting conditions, the cutting tool geometries, the lubricant conditions, and the chips morphology. This analysis is decomposed on several points: chip length, chip morphology, chip thickness, and the chip formation. The observations show also a strong influence of cutting conditions on chip morphology where an increase of cutting conditions reduces drastically the chip size. Concerning the chip formation, because the chip is produced during milling where the uncut chip thickness varies, the chip microstructure is then affected.     

Tool wear monitoring system for CNC end milling using a hybrid approach to cutting force regulation

A tool wear monitoring system is indispensable for better machining productivity, with the guarantee of machining safety by informing of the time due for changing a tool in automated and unmanned CNC machining. Different from monitoring methods using other signals, the monitoring of the spindle current has been used without requiring additional sensors on the machine tools. For reliable tool wear monitoring, only the current signal from tool wear should be extracted from the other parameters to avoid exhaustive analyses on signals in which all of the parameters are fused together. In this paper, the influences of force components from different parameters on the measured spindle current are investigated, and a hybrid approach to cutting force regulation is employed for tool wear signal extraction from the spindle current. Finally, wear levels are verified with experimental results by means of real-time feedrate aspects, varied to regulate the force component from tool wear.     

磨料水射流切割质量的神经网络预测

磨料水射流切割质量影响因素较多,难以建立有效的理论模型,结合实验结果,建立磨料水射流切割质量的神经网络预测模型。结果表明,对于所给定切割参数,该模型能快速、准确、可靠地预测出切割质量。     

Development of a dynamometer for measuring individual cutting edge forces in face milling

Cutting force information may be used for several tasks, such as tool design and trajectory optimization, tool condition monitoring, machinability testing and many others. Accordingly, cutting force measuring has become a crucial activity aimed at enhancing process performance. In this work, the development of an innovative rotating dynamometer for cutting force measurement in milling is illustrated. The device is capable of providing independent triaxial cutting force information from each cutting edge with a good dynamic response. Static and dynamic behavior of a simplified single-edge device was first investigated through the static calibration procedure, pulse tests and preliminary cutting tests. Afterwards, the dynamic properties of the final prototype clamped on the spindle of a high speed milling machine were assessed by means of standard and rotating pulse tests – i.e. pulse tests performed during spindle rotation. Eventually, cutting tests were performed on a benchmark workpiece. The experimental tests highlighted the superior features of the new device.     

Failure analysis of support during profile cutting process using horizontal milling machine

In this study, the effects of cutting forces on the support of horizontal woodworking milling machine are examined during profile cutting process using both experimental and analytical approaches. The support modeled in 3D using SolidWorks software is a crucial component of the horizontal milling machine used to locate and fix the wood workpiece during the cutting process on the workbench. The effects of cutting forces on the support specimens are measured experimentally considering vibration and failure analyses. Analytical stresses and modal analyses of the support were also calculated using finite element-based analysis approach. Chatter vibration forces of the cutting tool which resulted from cutting forces in x-, y-, and z-directions were calculated analytically during the profile cutting process. The results showed that both cutting and chatter forces are highly effective on the support component failure of the woodworking milling machines.     

Analysis of surface roughness and cutting force components in hard turning with CBN tool: Prediction model and cutting conditions optimization

In this study, the effects of cutting speed, feed rate, workpiece hardness and depth of cut on surface roughness and cutting force components in the hard turning were experimentally investigated. AISI H11 steel was hardened to (40; 45 and 50) HRC, machined using cubic boron nitride (CBN 7020 from Sandvik Company) which is essentially made of 57% CBN and 35% TiCN. Four-factor (cutting speed, feed rate, hardness and depth of cut) and three-level fractional experiment designs completed with a statistical analysis of variance (ANOVA) were performed. Mathematical models for surface roughness and cutting force components were developed using the response surface methodology (RSM). Results show that the cutting force components are influenced principally by the depth of cut and workpiece hardness; on the other hand, both feed rate and workpiece hardness have statistical significance on surface roughness. Finally, the ranges for best cutting conditions are proposed for serial industrial production.     

Effect of cutting speed on cutting forces and wear mechanisms in high-speed face milling of Inconel 718 with Sialon ceramic tools

In this paper, a series of milling tests were carried out in order to identify the effects of cutting speed on cutting forces and tool wear when high-speed face milling Inconel 718 with Sialon ceramic tools. Both down-milling and up-milling operations were conducted. The cutting forces, tool wear morphologies, and the tool failure mechanisms in a wide range of cutting speeds (600–3,000 m/min) were discussed. Results showed that the resultant cutting forces firstly decrease and then increase with the increase of cutting speed. Under relatively lower cutting speeds (600 and 1,000 m/min), the dominant wear patterns is notching. Further increasing the speed to more than 1,400 m/min, the notching decreases a lot and flank wear becomes the dominant wear pattern. In general, at the same cutting speed, flaking on the rake face and notching on the flank face are more serious in down-milling operation than that in up-milling operation with the same metal removal volume. However, the surface roughness values for down-milling are lower than that for up-milling.     

High-speed milling of CFRP composites: a progressive damage model of cutting force

Three-dimensional Hashin failure criterion and material stiffness degradation model were compiled by VUMAT subroutine. The Abaqus/Explicit solver was performed to establish progressive damage model of cutting force for CFRP high-speed milling, and high-speed milling experiments with different cutting parameters were carried out. Further, the impact mechanism of fiber cutting angle and cutting parameters on cutting force, stress, and material failure during milling was explored, and the material removal mechanism in high-speed milling of CFRP was revealed. The results show that the error between the experimental and simulated of cutting forces is less than 5%, which indicates that the progressive damage model is feasible. The fiber cutting angle has significant influence on cutting force and stress in cutting process, and the cutting direction has a significant influence on cutting force. In addition, cutting parameters play a critical role in cutting force, and the feed per tooth is the most significant factor affecting the cutting force. Simultaneously, the progressive damage model predicts that the shear failure of materials mainly concentrates in the cutting area and extends along the feed direction. Finally, the material removal mechanism of CFRP in high-speed milling was revealed combining cutting force experiment.