Prediction of tool wear using regression and ANN models in end-milling operation

Tool wear prediction plays an important role in industry for higher productivity and product quality. Flank wear of cutting tools is often selected as the tool life criterion as it determines the diametric accuracy of machining, its stability and reliability. This paper focuses on two different models, namely, regression mathematical and artificial neural network (ANN) models for predicting tool wear. In the present work, flank wear is taken as the response (output) variable measured during milling, while cutting speed, feed and depth of cut are taken as input parameters. The Design of Experiments (DOE) technique is developed for three factors at five levels to conduct experiments. Experiments have been conducted for measuring tool wear based on the DOE technique in a universal milling machine on AISI 1020 steel using a carbide cutter. The experimental values are used in Six Sigma software for finding the coefficients to develop the regression model. The experimentally measured values are also used to train the feed forward back propagation artificial neural network (ANN) for prediction of tool wear. Predicted values of response by both models, i.e. regression and ANN are compared with the experimental values. The predictive neural network model was found to be capable of better predictions of tool flank wear within the trained range.     

Micro-drilling of Ti–6Al–4V alloy: The effects of cooling/lubricating

This paper presents a series of experimental investigations of the effects of various machining conditions [dry, flooded, minimum quantity lubrication (MQL), and cryogenic] and cutting parameters (cutting speed and feed rate) on thrust force, torque, tool wear, burr formation, and surface roughness in micro-drilling of Ti–6Al–4V alloy. A set of uncoated carbide twist drills with a diameter of 700 μm were used for making holes in the workpiece material. Both machining conditions and cutting parameters were found to influence the thrust force and torque. The thrust force and torque are higher in cryogenic cooling. It was found that the MQL condition produced the highest engagement torque amplitude in comparison to the other coolant–lubrication conditions. The maximum average torque value was obtained in the dry drilling process. There was no substantial effect of various coolant–lubrication conditions on burr height. However, it was observed that the burr height was at a minimum level in cryogenic drilling. Increasing feed rate and decreasing spindle speed increased the entry and exit burr height. The minimum surface roughness values were obtained in the flood cooling condition. In the dry drilling process, increased cutting speed resulted in reduced hardness on the subsurface of the drilled hole. This indicates that the surface and subsurface of the drilled hole were subject to softening in the dry micro-drilling process. The softening at the subsurface of drilled holes under different cooling and lubrication conditions is much smaller compared to the dry micro-drilling process.     

HIGH THROUGHPUT DRILLING OF TITANIUM ALLOYS

The experiments of high throughput drilling of Ti-6Al-4V at 183 m/min cutting speed and 156 mm3/s material removal rate using a 4 mm diameter WC-Co spiral point drill are conducted. At this material removal rate, it took only 0.57 s to drill a hole in a 6.35 mm thick Ti plate. Supplying the cutting fluid via through-the-drill holes and the balance of cutting speed and feed have proven to be critical for drill life. An inverse heat transfer model is developed to predict the heat flux and the drill temperature distribution in drilling. A three-dimensional finite element modeling of drilling is con-ducted to predict the thrust force and torque. Experimental result demonstrates that, using proper machining process parameters, tool geometry, and fine-grained WC-Co tool material, the high throughput machining of Ti alloy is technically feasible.     

Effect of modified drill point geometry on drilling quality characteristics of metal matrix composite (MMCs)

The abrasive reinforcement present in ‘Metal matrix composites’ (MMCs) is responsible for numerous machining challenges for the research fraternity. The increase in tool wear, burr formation, surface roughness, and increase in cutting forces are few of such machining challenges during the drilling of MMCs. The present research investigation explores the effect of change in drill point geometry on the drilling Quality characteristics (QCs) of the drilled hole wall. The drilling QCs under investigation are, Specific cutting pressure (SCP) and Surface roughness (SR) of the drilled hole wall. The levels of the input process parameters for optimum values of the output responses were established by Taguchi’s methodology. SEM images and contour plots of drilled hole wall have been used to qualitatively explain the drilling behavior of MMCs. The chip formation mechanism observed during drilling establishes the cutting behavior of the different cutting edges of the modified drill point geometry. It has been observed that the single conical chips were produced by primary cutting edge and single ring type chips were produced by secondary cutting edge. The step diameter is the main factor which influences the SCP followed by the feed and point angle. The surface roughness of the drilled hole wall has been governed by the cutting speed, feed and step diameter. Burnishing and honing effect were observed on the drilled hole wall surface because of entrapped free SiC particles using SEM.

     

Tool wear monitoring in drilling using force signals

Utilization of force signals to achieve on-line drill wear monitoring is presented in this paper. A series of experiments were conducted to study the effects of tool wear as well as other cutting parameters on the cutting force signals and to establish the relationship between force signals and tool wear as well as other cutting parameters when drilling copper alloy. These experiments involve four independent variables; spindle rotational speed ranging from 600 to 2400 rev min⁻¹, feed rate ranging from 60 to 200 mm min⁻¹, drill diameter ranging from 5 to 10 mm, and average flank wear ranging from 0.1 to 0.9 mm. A statistical analysis provided good correlation between average thrust and drill flank wear. The relationship between cutting force signals and cutting parameters as well as tool wear is then established. The relationship can then be used for on-line drill flank wear monitoring. Feasibility studies show that the use of force signal for on-line drill flank wear monitoring is feasible.     

Cutting performance of an indexable insert drill for difficult-to-cut materials under supplied oil mist

In this study, the cutting performance of an indexable insert drill with an asymmetric geometry for cutting difficult-to-cut materials was investigated. A solid twist drill with a symmetric geometry was used to compare the cutting characteristics. The cutting characteristics were evaluated using the thrust force, inner-surface roughness of the drilled hole, wear behavior, and tool temperature. Workpieces made of stainless steel, titanium alloy, and nickel-based alloy were selected as difficult-to-cut materials, and carbon steel was also selected. The tool temperature was higher in the order of carbon steel, stainless steel, titanium alloy, and nickel-based alloy for every drill under minimum quantity lubrication cutting. The influence of the workpiece material on the thrust force was different from that of the tool temperature for the indexable insert drill, whereas that of the solid twist drill was similar to the tool temperature tendency. When cutting the titanium alloy and nickel-based alloy, the tool temperature and thrust force of the indexable insert drill were lower than those of the solid-type twist drill. The inner-surface roughness of a hole drilled with the indexable insert drill had almost the same quality as that of a hole drilled with the solid-type twist drill when cutting the difficult-to-cut materials. The wear behavior of the indexable insert drill was remarkably different from that of the solid-type twist drill, and the flaking of the coating and the abrasion wear at the rake face were notable in the indexable insert drill.     

Predicting drill wear using an artificial neural network

The present work deals with drill wear monitoring using an artificial neural network. A back propagation neural network (BPNN) has been used to predict the flank wear of high-speed steel (HSS) drill bits for drilling holes on copper work-piece. Experiments have been carried out over a wide range of cutting conditions and the effect of various process parameter like feedrate, spindle speed, and drill diameter on thrust force and torque has been studied. The data thus obtained from the experiments have been used to train a BPNN for wear prediction. The performance of the trained neural network has been tested with the experimental data, and has been found to be satisfactory.     

Performance prediction of high-pressure coolant assisted turning of Ti-6Al-4V

The present study focuses on the development of predictive models of average surface roughness, chip-tool interface temperature, chip reduction coefficient, and average tool flank wear in turning of Ti-6Al-4V alloy. The cutting speed, feed rate, cutting conditions (dry and high-pressure coolant), and turning forces (cutting force and feed force) were the input variables in modeling the first three quality parameters, while in modeling tool wear, the machining time was the only variable. Notably, the machining environment influences the machining performance; yet, very few models exist wherein this variable was considered as input. Herein, soft computing-based modeling techniques such as artificial neural network (ANN) and support vector machines (SVM) were explored for roughness, temperature, and chip coefficient. The prediction capability of the formulated models was compared based on the lowest mean absolute percentage error. For surface roughness and cutting temperature, the ANN and, for chip reduction coefficient, the SVM revealed the lowest error, hence recommended. In addition, empirical models were constructed by using the experimental data of tool wear. The adequacy and good fit of tool wear models were justified by a coefficient of determination value greater than 0.99.     

Effect of tool wear on delamination in drilling composite materials

Among all machining operations, drilling using twist drill is the most frequently applied for secondary machining of composite materials owing to the need for structure joining. Delamination is mostly considered as the principal failure model in drilling of composite materials. Drill wear is a serious concern in hole-making industry, as it is necessary to prevent damage of cutting tools, machine tools and workpieces. The industrial experience shows the worn drill causes more delamination. This paper presents a comprehensive analysis of delamination caused by the drill wear for twist drill in drilling carbon fiber-reinforced composite materials. The critical thrust force at the onset of delamination for worn drill is predicted and compared with that of ideal drill. The experimental results demonstrate that though the critical thrust force is higher with increasing wear ratio, the delamination becomes more liable to occur because the actual thrust force increases to larger extent, as the thrust factor (Z) illustrates. Compared to sharp drill, the worn twist drill allows for lower feed rate below which the delamination damage can be avoided.     

Effect of different features to drill-wear prediction with back propagation neural network

In this paper, a back propagation neural network (BPNN) has been applied to predict the corner wear of a high speed steel (HSS) drill bit for drilling on different workpiece materials. Specially defined static and dynamic features extracted by a wavelet packet transform (WPT) from the resultant force converted from thrust and torque together with the cutting conditions (workpiece material, spindle speed, drill diameter, feed rate) are used as inputs to train the network to obtain a better output, drill corner wear. Drilling experiments have been carried out over a wide range and, features newly defined and conventional ones, features extracted from different frequency bands are compared.     

Tool life evaluation of CFRP drilling with three kinds of drill

Serious tool wear in CFRP drilling is one of the key problems to be solved urgently. Firstly, a suitable indirect evaluation index of tool life is selected according to the literature. The critical delamination force was obtained by blind hole pushing experiment. Then, tool wear experiments were carried out with double point angle drill, stepped drill and reverse edge compound drill to analyze the variation rules of the thrust force, exit burr, exit delamination and tear with tool wear. Threshold values of exit delamination, tearing and critical thrust force were compared with each evaluation index one by one to study the causes of drills failure. The results indicated that the maximum tool wear position was the outer corner. Among the three types drills, the thrust force, delamination factor and burr angle of the reverse edge compound drill are smaller. The double point angle drill fails due to the excessive thrust force, while the stepped drill and the reverse edge compound drill fail due to the hole exit delamination exceeding the threshold. The number of drilled holes of the reverse edge compound drill is 100 % and 25 % higher than that of the double point angle drill and the stepped drill, respectively. Therefore, the reverse edge compound drill is suitable for drilling CFRP.

     

模具钢铣削中刀具磨损的试验研究

以面铣刀刀片磨损为研究对象,结合类神经网络系统建构高速数控铣削加工的预测模型。以加工参数为模型输入条件,刀腹磨耗为输出条件。采用多因素试验方法,选择切削速度、进给速度、切削深度三个试验参数,利用直交表式的试验计划法设计试验点。依照试验点铣削工件后再测量刀具加工后的刀腹磨耗量,进而求得倒传递网络所需的36组训练范例与11组验证数据。刀腹磨耗预测模式是利用类神经网络中的倒传递网络原理,以田口法求得倒传递网络参数的最优值。试验结果显示,刀腹磨耗随着切削速度、进给速度、切削深度增加而上升。铣削模具钢后,刀具磨耗预测值的平均误差为4.72%,最大误差为11.43%,最小误差为0.31%。整体而言,类神经网络对于铣削加工可进行有效预测。     

Design and experimental study of an end effector for robotic drilling

This paper presents the development of a drill end effector for use on industrial robots. The end effector has low weight and high rigidity. The drill end effector is fully programmable and will realize different drilling mode. The real-time force feedback can detect dull or broken bits, drill to breakthrough, and plot thrust force while drilling. Additionally, the end effector can also be equipped with a coolant/lubricant device. Based on the drill end effector, an experimental study on dry drilling of Ti-6Al-4V alloy and 7075-T6 alloy bimetal stacks was performed by using an uncoated cemented carbide drill. The hole quality (hole size, surface roughness) and thrust force were evaluated at various spindle speeds, feed rates, stacking sequence, and clamp force. This study indicates that the spindle speed and feed rate have an effect on the hole quality and thrust force by means of changing the temperature and plastic deformation of cutting zone. The results show that drilling 7075-T6 alloy firstly would be most efficient because of the high hole quality and the low thrust force. It was also found that high clamp force is helpful to improve the hole quality.     

ROTARY ULTRASONIC MACHINING OF CARBON FIBER-REINFORCED POLYMER: FEASIBILITY STUDY

Carbon fiber-reinforced polymer (CFRP) has been widely used in aircraft components, automotive parts, and sporting goods. Hole machining is the most frequently employed operation of secondary machining for fiber-reinforced composites. However, challenges (delamination, splintering, burr, short tool life, low machining precision, and low surface quality) still remain for their widespread applications. Rotary ultrasonic machining (RUM) is a non-conventional machining process that has been used to drill holes in composite materials. However, it has not been used to drill this type of CFRP. In this article, RUM is introduced into drilling holes in this type of CFRP for the first time. The feasibility to machine carbon fiber-reinforced epoxy using RUM is investigated experimentally. Chips, edge chipping, surface roughness, tool wear, and thrust force were measured. Effects of RUM process variables (rotation speed, vibration amplitude, and feedrate) on thrust force and surface roughness were studied. Results showed that RUM could be used to drill holes in CFRP with high productivity and low tool wear. A better surface was produced by higher rotation speed and lower feed rate.     

Effects of cutting parameters on tool wear in drilling of polymer composite by Taguchi method

Polymer composite products can be obtained by primary manufacturing processes such as contact molding, vacuum bag molding, resin transfer molding, or sheet molding compound and secondary processes such as drilling and saw cutting. Drilling is generally employed to make bolted or riveted assembles in composite structures. In drilling, some defects like delamination and crack are seen, and also undesired hole surface roughness related to tool wear is an another problem frequently encountered. In this study, tool wear in drilling of sheet molding compound (SMC) composite, consisted of 30?wt.% glass fiber, 25?wt.% polyester, and 45?wt.% calcium carbonate, was investigated. SMC composite was drilled under different cutting speeds, feeds, and drill point angles. Taguchi design of experiments and analysis of variance were utilized to determine the optimal cutting parameters and to analyze the effects of them on the tool wear. The feed followed by the drill point angle were found to be the important factors while cutting speed was the least effective parameter. Chip volume was accepted as a criterion to compare obtained data. Increasing feed and decreasing drill point angle reduced the tool wear. Multivariable linear regression analysis was also employed to determine the correlations between the factors and the tool wear. Finally, a model was generated and a good approximation was achieved in the comparison of the experimental data and the predicted data obtained from the model.     

Optimization of thrust force, torque, and tool wear in drilling of coir fiber-reinforced composites using Nelder–Mead and genetic algorithm methods

Machining of composite materials is an important and current topic in modern researches on manufacturing processes. Determination of optimal cutting parameters is one of the most important elements in the machinability study of composites. Optimization has significant practical importance particularly for operating the machineries. In order to increase the accuracy of drill holes, the tool must be in good condition always as much as possible. To achieve good condition of tool, the optimization of machining parameters like drill bit diameter, spindle speed, and feed rate are mandatory. The objective of this paper is to study the effect of these process parameters on thrust force, torque, and tool wear in drilling of coir fiber-reinforced composites. The optimal settings of the parameters were determined through experiments planned, conducted, and analyzed using the Box–Behnken design, Nelder–Mead, and genetic algorithm methods. This paper also aimed to increase the cutting condition of tool, i.e., minimization of tool wear by applying the optimized input parameters using Nelder–Mead and genetic algorithm techniques.     

Chipping minimization in drilling ceramic materials with rotary ultrasonic machining

Ultrasonic machining (USM) has been considered as a new cutting technology that does not rely on the conductance of the workpiece. USM presents no heating or electrochemical effects, with low surface damage and small residual stresses on workpiece material, such as glass, ceramics, and others; therefore, it is used to drill microholes in brittle materials. However, this process is very slow and tool wear dependent, so the entire process has low efficiency. Therefore, to increase microhole drilling productivity or hole quality, rotary ultrasonic machining (RUM) is considered as a strong alternative to USM. RUM, which presents ultrasonic axial vibration with tool rotation, is an effective solution for improving cutting speed, precision, tool wear, and other machining responses beyond those of the USM. This study aims to reduce the microchipping or cracking at the exit of the hole, which inevitably occurs when brittle materials are drilled, with consideration of tool wear. To this end, response surface analysis and desirability functions are used for experimental optimization. The experimental results showed that the proposed RUM scheme is suitable for microhole drilling.     

Taguchi method based optimisation of drilling parameters in drilling of AISI 316 steel with PVD monolayer and multilayer coated HSS drills

This paper focuses on the optimisation of drilling parameters using the Taguchi technique to obtain minimum surface roughness (Ra) and thrust force (Ff). A number of drilling experiments were conducted using the L16 orthogonal array on a CNC vertical machining centre. The experiments were performed on AISI 316 stainless steel blocks using uncoated and coated M35 HSS twist drills under dry cutting conditions. Analysis of variance (ANOVA) was employed to determine the most significant control factors affecting the surface roughness and thrust force. The cutting tool, cutting speed and feed rate were selected as control factors. After the sixteen experimental trials, it was found that the cutting tool was the most significant factor on the surface roughness and that the feed rate was the most significant factor on the thrust force. The results of the confirmation experiments showed that the Taguchi method was notably successful in the optimisation of drilling parameters for better surface roughness and thrust force.     

A step towards the in-process monitoring for electrochemical microdrilling

The bandsawing as a multi-point cutting operation is the preferred method for cutting off raw materials in industry. Although cutting off with bandsaw is very old process, research efforts are very limited compared to the other cutting process. Appropriate online tool condition monitoring system is essential for sophisticated and automated machine tools to achieve better tool management. Tool wear monitoring models using artificial neural network are developed to predict the tool wear during cutting off the raw materials (American Iron and Steel Institute 1020, 1040 and 4140) by bandsaw. Based on a continuous data acquisition of cutting force signals, it is possible to estimate or to classify certain wear parameters by means of neural networks thanks to reasonably quick data-processing capability. The multi-layered feed forward artificial neural network (ANN) system of a 6?×?9?×?1 structure based on cutting forces was trained using error back-propagation training algorithm to estimate tool wear in bandsawing. The data used for the training and checking of the network were derived from the experiments according to the principles of Taguchi design of experiments planned as L ₂₇. The factors considered as input in the experiment were the feed rate, the cutting speed, the engagement length and material hardness. 3D surface plots are generated using ANN model to study the interaction effects of cutting conditions on sawblade. The analysis shows that cutting length, hardness and cutting speed have significant effect on tooth wear, respectively, while feed rate has less effect. In this study, the details of experimentation and ANN application to predict tooth wear have been presented. The system shows that there is close match between the flank wear estimated and measured directly.     

Comparison between response surface methodology and radial basis function network for core-center drill in drilling composite materials

Drilling using twist drill is the most frequently used secondary machining for fiber-reinforced composite laminates and delamination is the most important concern during drilling. The drill design and drilling parameters associated with thrust distribution on the drilling-induced delamination are presented. The core-center drill has been found to be more advantageous than the core drill in reference and practice experiences. Response surface methodology (RSM) is a very practical, economical, and useful tool for the modeling and analysis of experimental results using polynomials as local approximations to the true input/output relationship. Due to the radial basis function network’s (RBFN) fast learning speed, simple structure, local tuning, and global generalization power, researchers in the field of manufacturing engineering have been using RBFN in nonlinear manufacturing studies. The present paper compares these two techniques using various drilling parameters (diameter ratio, feed rate, and spindle speed) to predict the thrust force for a core-center drill in drilling composite materials. The obtained results indicated that RBFN is a practical and an effective way for the evaluation of drilling-induced thrust force.