Predictive modeling of surface roughness and tool wear in hard turning using regression and neural networks

In machining of parts, surface quality is one of the most specified customer requirements. Major indication of surface quality on machined parts is surface roughness. Finish hard turning using Cubic Boron Nitride (CBN) tools allows manufacturers to simplify their processes and still achieve the desired surface roughness. There are various machining parameters have an effect on the surface roughness, but those effects have not been adequately quantified. In order for manufacturers to maximize their gains from utilizing finish hard turning, accurate predictive models for surface roughness and tool wear must be constructed. This paper utilizes neural network modeling to predict surface roughness and tool flank wear over the machining time for variety of cutting conditions in finish hard turning. Regression models are also developed in order to capture process specific parameters. A set of sparse experimental data for finish turning of hardened AISI 52100 steel obtained from literature and the experimental data obtained from performed experiments in finish turning of hardened AISI H-13 steel have been utilized. The data sets from measured surface roughness and tool flank wear were employed to train the neural network models. Trained neural network models were used in predicting surface roughness and tool flank wear for other cutting conditions. A comparison of neural network models with regression models is also carried out. Predictive neural network models are found to be capable of better predictions for surface roughness and tool flank wear within the range that they had been trained.Predictive neural network modeling is also extended to predict tool wear and surface roughness patterns seen in finish hard turning processes. Decrease in the feed rate resulted in better surface roughness but slightly faster tool wear development, and increasing cutting speed resulted in significant increase in tool wear development but resulted in better surface roughness. Increase in the workpiece hardness resulted in better surface roughness but higher tool wear. Overall, CBN inserts with honed edge geometry performed better both in terms of surface roughness and tool wear development.     

Statistical analysis of surface roughness and cutting forces using response surface methodology in hard turning of AISI 52100 bearing steel with CBN tool

The present work concerns an experimental study of hard turning with CBN tool of AISI 52100 bearing steel, hardened at 64 HRC. The main objectives are firstly focused on delimiting the hard turning domain and investigating tool wear and forces behaviour evolution versus variations of workpiece hardness and cutting speed. Secondly, the relationship between cutting parameters (cutting speed, feed rate and depth of cut) and machining output variables (surface roughness, cutting forces) through the response surface methodology (RSM) are analysed and modeled. The combined effects of the cutting parameters on machining output variables are investigated while employing the analysis of variance (ANOVA). The quadratic model of RSM associated with response optimization technique and composite desirability was used to find optimum values of machining parameters with respect to objectives (surface roughness and cutting force values). Results show how much surface roughness is mainly influenced by feed rate and cutting speed. Also, it is underlined that the thrust force is the highest of cutting force components, and it is highly sensitive to workpiece hardness, negative rake angle and tool wear evolution. Finally, the depth of cut exhibits maximum influence on cutting forces as compared to the feed rate and cutting speed.     

State of the art in hard turning

Hard turning is gaining grounds for machining hardened steels as it has several benefits over grinding. There are several issues, which should be understood and dealt with, to achieve successful performance of the process. Researchers have worked upon several aspects related to hard turning. The present work is an effort to review some of these works and to understand the key issues related to process performance. The review shows that the type of tool material, cutting edge geometry and cutting parameters affect the process efficiencies in terms of tool forces, surface integrities integrity, and white layer. Adequate machine rigidity is a must essential to minimize the process inaccuracies. Also moreover, for finish hard turning, where the depth of cut is less than the nose radius of the tool, the forces deviate from the conventional trends as the radial force component is the maximum and axial force component becomes minimum. The present work finally lists down certain areas that can be taken up for further research in hard turning.     

Reduction of wear induced surface zone effects during hard turning by means of new tool geometries

Tool wear during hard turning influences the properties of the workpiece surface and subsurface layer significantly. Due to increasing flank face wear at the cutting edge, the contact conditions between tool and workpiece are changed. The mechanical and thermal load in the workpiece surface increases during the process. This favors the formation of white layers and of residual stress gradients in the subsurface zone of hardened workpieces whereby the components life time is reduced. The article presents novel modifications of the tool geometry, which leads to a considerable prolongation of the tool life time. This advanced tool design enables the production of constant material properties in the surface and subsurface zone during a broad time window.     

A comparison of dry and air-cooled turning of grey cast iron with mixed oxide ceramic tool

The present work compares the performance of a mixed oxide ceramic tool in dry and air-cooled turning of grey cast iron. First, the study was done in the range of process parameters where dry turning provided satisfactory performance. The contours of surface roughness and tool life were generated with the help of trained neural networks. A novel procedure of neural network training is used in this work. The study was extended to the range in which dry turning performed poorly in terms of tool life. Tool wear, surface roughness of the machined job and forces and vibration during the cutting were studied. It was observed that air-cooling significantly reduces the tool wear at high cutting speed. At higher cutting speeds, where the dry turning performs very poorly, the air-cooled turning provides an improved surface finish also apart from the reduction in tool wear. In all the cases, the cutting and feed forces get reduced in air-cooling. Thus, air-cooled turning of grey cast iron with mixed oxide ceramic tools offers a promising environment-friendly option.     

Tool wear and chip formation during hard turning with self-propelled rotary tools

This paper presents a performance assessment of rotary tool during machining hardened steel. The investigation includes an analysis of chip morphology and modes of tool wear. The effect of tool geometry and type of cutting tool material on the tool self-propelled motion are also investigated. Several tool materials were tested for wear resistance including carbide, coated carbide, and ceramics. The self-propelled coated carbide tools showed superior wear resistance. This was demonstrated by evenly distributed flank wear with no evidence of crater wear. The characteristics of temperature generated during machining with the rotary tool are studied. It was shown that reduced tool temperature eliminates the diffusion wear and dominates the abrasion wear. Also, increasing the tool rotational speed shifted the maximum temperature at the chip–tool interface towards the cutting edge.     

A cBN-TiN composite coating for carbide inserts: Coating characterization and its applications for finish hard turning

Cubic boron nitride (cBN)-titanium nitride (TiN) composite coating combines the thermal stability and super abrasiveness of cubic boron nitride (cBN) and the good lubricity of TiN, offering the opportunity for designing cutting tools with application specific new geometries (flat, chip breaker, and round shape) and cost effectiveness. In particular, the cBN based coating on carbide inserts is complementary to widely used polycrystalline cubic boron nitride (PCBN) compact tools for finish hard turning applications. This paper reports the results of a study addressing the surface morphology, surface roughness, coating cross section, chemical composition, crystal structure, microhardness, adhesion, and the wear life of this cBN-based coating deposited on carbide inserts (SNMG432) for finish turning of hardened AISI 4340 steel bars. The surface quality of machined workpieces in terms of their surface roughness and white layer formation are also analyzed and the results are presented.     

A comprehensive chatter prediction model for face turning operation including tool wear effect

This paper presents a three-dimensional mechanistic frequency domain chatter model for face turning processes, that can account for the effects of tool wear including process damping. New formulations are presented to model the variation in process damping forces along nonlinear tool geometries such as the nose radius. The underlying dynamic force model simulates the variation in the chip cross-sectional area by accounting for the displacements in the axial and radial directions. The model can be used to determine stability boundaries under various cutting conditions and different states of flank wear. Experimental results for different amounts of wear are provided as a validation for the model.     

Influence of tool edge preparation on performance of ceramic tool inserts when hard turning

Coating, as a form of tool edge preparation, changes the properties, geometry and roughness of the active parts of tool inserts. The performance of both uncoated and coated ceramics was tested in machining tests and the results were related to the tool edge and the machined surface as well as cost indices. The presented results show that tool edge preparation by coating does affect forces, tool wear and the machined surface, while friction force from scratch tests and the coating thickness and its hardness have been identified as being relevant to the results of machining tests. The relationship between the thickness of the surface layer and residual stress at the surface due to coating has been evaluated. Though the tool life of coated ceramics is shorter than that of cubic boron nitride, tool edge preparation by coating contributes to the reduction in machining costs due to the application of higher cutting speeds.     

Chip formation, cutting forces, and tool wear in turning of Zr-based bulk metallic glass

The chip light emission and morphology, cutting forces, surface roughness, and tool wear in turning of Zr-based bulk metallic glass (BMG) material are investigated. Machining results are compared with those of aluminum 6061-T6 and AISI 304 stainless steel under the same cutting conditions. This study demonstrates that the high cutting speeds and tools with low thermal conductivity and rake angle activate the light emission and chip oxidation in BMG machining. For the BMG chip without light emission, serrated chip formation with adiabatic shear band and void formation is observed. The cutting force analysis further correlates the chip oxidation and specific cutting energy and shows the significant reduction of cutting forces for machining BMG at high cutting speeds. The machined surface of BMG has better surface roughness than that of the other two work materials. Some tool wear features, including the welding of chip to the tool tip and chipping of the polycrystalline cubic boron nitride (PCBN) tool edge, are reported for turning of BMG. This study concludes that BMG can be machined with good surface roughness using conventional cutting tools.     

White layer formation in hard turning of H13 tool steel at high cutting speeds using CBN tooling

White layers formed during machining have negative effects on surface finish and fatigue strength of products. The white layer is generally a hard phase and leads to the surface becoming brittle causing crack permeation and product failure. This is a major concern with respect to service performance especially in the aerospace and automotive industries. Numerous authors have investigated the formation of white layer under different manufacturing processes. In turning, it was suggested that the white layer structure is a martensitic phase whose formation is correlated to tool wear. Past studies have tended to concentrate on the formation of white layers at conventional cutting speeds, but never examined the formation at high cutting speeds. This paper reports on an investigation of white layer formation for wide range of cutting speeds in hard turning of 54-56 HRC H13 tool steel. The specimens were analysed using a micro hardness tester, SEM with EDAX software and Electron Micro-Probe. In addition tool wear and workpiece temperature were studied. The machined surface showed an increase in hardness with respect to the bulk material. Compositional gradients were noted for the white layer in terms of depletion of the elements iron and chromium coupled with an enrichment of carbon and oxygen content. The results showed that despite tool wear increasing with cutting speed, white layer depth and hardness actually reduced. This finding suggests that there may not be a direct relationship between white layer formation and wear, the correlation maybe linked to wear mode.     

Influence of refrigeration/lubrication condition on SAE 52100 hardened steel turning at several cutting speeds

Nowadays, the use of cutting fluids on machining operations has been questioned, due to problems they may cause to the environment, due to damage to human health and also more due to the severe laws regarding industrial waste that have been passed. Therefore, industries are being forced to review the production processes aiming either, at elimination or, when it is not possible, a sharp reduction in the use of these fluids. The technique of minimum volume of oil (MVO) has been studied in machining processes as one alternative to the use of abundant cutting fluid. Research has shown that this technique, which is the pulverisation of a minimum volume of oil in a flow of compressed air, in several cases, reduces tool wear when compared to complete dry cutting, causing the improvement of the workpiece surface quality and an increase in tool life. In this work, the influence of MVO (oil flow of 10 ml/h) in the wear of a cubic boron nitride (CBN) tool, when turning 52100 hardened steel, was studied. Aiming at a comparison of the results, the experiments were also carried out under two other conditions: dry cutting and cutting with abundant soluble oil (wet cutting). During the experiments, the influence of cutting speed on CBN tool wear for the three refrigeration conditions was also checked. Besides this, tool wear and workpiece surface roughness was also measured as cutting time elapsed.     

Accuracy of hard turning

Nowadays, hard turning is frequently used to replace grinding. The economic benefits of hard turning are obvious but for achievable accuracy the situation is somewhat ambiguous. Although machine tool factories offer lathes with the same accuracy as grinding machines in some cases problems may arise in keeping the prescribed geometrical accuracy. Investigations were performed in a working environment in order to determine the attainable size, form and positional accuracy obtained with hard turning. Error sources of machining errors that occurred in hard turning and in grinding were taken into account, giving typical differences between the two processes. In the parts produced in series, size deviations were measured as well as out-of-roundness, cylindricity error and parallelism error of the bore's generatrices. The workpieces used for the investigation are disc-type parts with bores, i.e., gears that are built into transmissions. Our first measuring series evaluates the achievable accuracy with hard turning while the second includes the comparison of grinding with hard turning. The most important error sources are identified. We present measures for keeping prescribed tolerances and propose methods for eliminating the means error source.     

A cutting power model for tool wear monitoring in milling

This paper describes a cutting power model in face milling operation, where cutting conditions and average tool flank wear are taken into account. The cutting power model is verified with experiments. It is shown with the simulations and experiments that the simulated power signals predict the mean cutting power better than the instantaneous cutting power. Finally, the cutting power model is used in a cutting power threshold updating strategy for tool wear monitoring which has been carried out successfully in milling operations under variable cutting conditions.     

A brief review: acoustic emission method for tool wear monitoring during turning

Research during the past several years has established the effectiveness of acoustic emission (AE)-based sensing methodologies for machine condition analysis and process monitoring. AE has been proposed and evaluated for a variety of sensing tasks as well as for use as a technique for quantitative studies of manufacturing processes. This paper reviews briefly the research on AE sensing of tool wear condition in turning. The main contents included are:

1. The AE generation in metal cutting processes, AE signal classification, and AE signal correction.

2. AE signal processing with various methodologies, including time series analysis, FFT, wavelet transform, etc.

3. Estimation of tool wear condition, including pattern classification, GMDH methodology, fuzzy classifier, neural network, and sensor and data fusion.

A review of AE-based tool wear monitoring in turning is an important step for improving and developing new tool wear monitoring methodology.     

Real time implementation of on-line tool condition monitoring in turning

This paper describes a real-time tool condition monitoring system for turning operations. The system uses a combination of static and dynamic neural networks with off-line and on-line training and cutting force components are used as diagnostic signals. The system is capable of monitoring several wear components simultaneously. The wear estimation system has been implemented experimentally to evaluate its suitability for use in shop floor conditions. The tests were performed in real time with different cutting conditions. The experimental results showed that the system was successful in predicting three wear components in real time. However, the accuracy of the wear prediction was not the same for all three wear components. The crater wear predictions were less accurate partly because of the opposing effects of crater and flank wear components on cutting force components.     

Multiclassification of tool wear with support vector machine by manufacturing loss consideration

Tool wear is a dynamic process, as a tool progresses from sharp to worn state and possibly to breakage. Thus the multiclassification of tool states is preferred, which can provide more timely and accurate estimation of tool states. Based on acoustic emission (AE) sensing, this paper proposes a new performance evaluation function for tool condition monitoring (TCM) by considering manufacturing loss. Firstly, two types of manufacturing loss due to misclassification (loss caused by under prediction and loss caused by over prediction) are analyzed, and both are utilized to compute corresponding weights of the proposed performance evaluation function. Then the expected loss of future misclassification is introduced to evaluate the recognition performance of TCM. Finally, a revised support vector machine (SVM) approach coupled with one-versus-one method is implemented to carry out the multiclassification of tool states. With this approach, a tool is replaced or continued not only based on the tool condition alone, but also the risk in cost incurred due to underutilized or overused tool. The experimental results show that the proposed method can reliably perform multiclassificaion of tool flank wear, and reduce the potential manufacturing loss.     

Surface finish generated in hard turning of quenched alloy steel parts using conventional and wiper ceramic inserts

Significant progress has already been achieved in green manufacturing including dry and hard, often high-speed, machining technologies. For instance, the demand for higher productivity has resulted in the wider application of ceramic and PCBN tools with special multi-radii (wiper) geometry. This paper reports some important characteristics of the surface roughness produced in the turning of a hardened low-chromium alloy steel using mixed alumina–titanium carbon (TiC) ceramic cutting tools equipped with both conventional and wiper inserts. The characteristic geometrical features of surfaces obtained in both these turning operations have been assessed by means of representative two-dimensional (2D) surface roughness parameters, and some 3D visualizations, which allowed more complete characterization of the surface topography and prediction of its service properties. Results show that keeping equivalent feed rates, i.e. 0.1 mm/rev for conventional and 0.2 mm/rev for wiper tools, the surfaces obtained have similar 3D height roughness parameters, and comparable values of skew and kurtosis. At defined cutting parameters, surfaces produced by wiper tools contain blunt peaks with distinctly smaller slopes resulting in better bearing properties. Only marginal changes of Ra parameter were recorded during 15 min machining trials.     

Sensor signals for tool-wear monitoring in metal cutting operations—a review of methods

The state of a cutting tool is an important factor in any metal cutting process as additional costs in terms of scrapped components, machine tool breakage and unscheduled downtime result from worn tool usage. Several methods to develop monitoring devices for observing the wear levels on the cutting tool on-line while engaged in cutting have been attempted. This paper presents a review of some of the methods that have been employed in tool condition monitoring. Particular attention is paid to the manner in which sensor signals from the cutting process have been harnessed and used in the development of tool condition monitoring systems (TCMSs).     

Effect of tool nose radius and tool wear on residual stress distribution in hard turning of bearing steel

This study presents a experimental investigation to clarify the effects of tool nose radius and tool wear on residual stress distribution in hard turning of bearing steel JIS SUJ2. Three types of CBN tools with different nose radius (0.4, 0.8 and 1.2 mm) were used in this study. The residual stresses beneath the machined surface were measured using X-ray diffraction technique and electro-polishing technique. The results obtained in this study show that the tool nose radius affects the residual stress distribution significantly. Especially the effect on the residual stresses at the machined surface at early stage of cutting process is remarkable. For the tool wear, as the tool wear increases, the residual stress at the machined surface shifts to tensile stress range and the residual compressive stress beneath the machined surface increases greatly.