Modelling the correlation between cutting and process parameters in high-speed machining of Inconel 718 alloy using an artificial neural network

An artificial neural network (ANN) model was developed for the analysis and prediction of the relationship between cutting and process parameters during high-speed turning of nickel-based, Inconel 718, alloy. The input parameters of the ANN model are the cutting parameters: speed, feed rate, depth of cut, cutting time, and coolant pressure. The output parameters of the model are seven process parameters measured during the machining trials, namely tangential force (cutting force, F_z), axial force (feed force, F_x), spindle motor power consumption, machined surface roughness, average flank wear (VB), maximum flank wear (VB_max) and nose wear (VC). The model consists of a three-layered feedforward backpropagation neural network. The network is trained with pairs of inputs/outputs datasets generated when machining Inconel 718 alloy with triple (TiCN/Al₂O₃/TiN) PVD-coated carbide (K 10) inserts with ISO designation CNMG 120412. A very good performance of the neural network, in terms of agreement with experimental data, was achieved. The model can be used for the analysis and prediction of the complex relationship between cutting conditions and the process parameters in metal-cutting operations and for the optimisation of the cutting process for efficient and economic production.     

Optimization of machining parameters of Al/SiC-MMC with ANOVA and ANN analysis

In recent years, the utilization of metal matrix composites (MMC) materials in many engineering fields has increased tremendously. Accordingly the need for accurate machining of composites has also increased enormously. Despite the recent developments in the near net shape manufacture, composite parts often require post-mold machining to meet dimensional tolerances, surface quality and other functional requirements. In the present work, the surface roughness of Al–SiC (20 p) has been studied in this paper by turning the composite bars using coarse grade polycrystalline diamond (PCD) insert under different cutting conditions. Experimental data collected are tested with analysis of variance (ANOVA) and artificial neural network (ANN) techniques. Multilayer perceptron model has been constructed with back-propagation algorithm using the input parameters of depth of cut, cutting speed and feed. Output parameter is surface finish of the machined component. On completion of the experimental test, ANOVA and an ANN are used to validate the results obtained and also to predict the behavior of the system under any condition within the operating range.     

Role of temperature and surface finish in predicting tool wear using neural network and design of experiments

The present work focuses on the two of the techniques, namely design of experiments and the neural network for predicting tool wear. In the present work, flank wear, surface finish and cutting zone temperature were taken as response (output) variables measured during turning and cutting speed, feed and depth of cut were taken as input parameters. Predictions for all the three response variables were obtained with the help of empirical relation between different responses and input variables using design of experiments (DOE) and also through neural network (NN) program. Predicted values of the responses by both techniques, i.e. DOE and NN were compared with the experimental values and their closeness with the experimental values was determined. Relationship between the surface roughness and the flank wear and also between the temperature and the flank wear were found out for indirect measurement of the flank wear through surface roughness and cutting zone temperature.     

金属陶瓷刀具切削铸铁的磨损机理研究

利用真空烧结工艺制备了纳米复合Ti(C,N)基金属陶瓷刀片。进行铸铁的单因素切削试验,并利用SEM、EPMA对金属陶瓷刀具的磨损失效机理进行了详细的研究。结果表明:纳米复合Ti(C,N)基金属陶瓷刀片只适宜小切削用量下铸铁的切削加工,切削铸铁时主要以磨损的形式失效,其主要的磨损失效机理是冲击磨损和崩碎切屑的研磨。     

GA Approach for Optimization of Surface Roughness Parameters in Machining of Al Alloy SiC Particle Composite

Experiments were carried out using carbide turning inserts on AA7075/10?wt.% SiC (particle size 10-20???m) composites to get actual input values to the optimization problem, so that the optimized results are realistic. By using experimental data, the regression model was developed. This model was used to formulate the fitness function of the genetic algorithm (GA). This investigation attempts to perform the application of GA for finding the optimal solution of the cutting conditions minimum value of surface roughness. The analysis of this investigation shows that the GA technique is capable of estimating the optimal cutting conditions that yield the minimum surface roughness value. With the highest speed, the lowest feed rate, the lowest depth of cut, and the highest nose radius of the cutting conditions' scale, the GA technique recommends 1.039???m as the best minimum predicted surface roughness value. This means that the GA technique has decreased the minimum surface roughness value of the experimental sample data, regression modeling and desirability analysis by about 3%, 1%, and 2.8%, respectively.     

On-line monitoring of flank wear in turning with multilayered feed-forward neural network

A multilayer feed-forward neural network (MLFF N-Network) algorithm is presented for on-line monitoring of tool wear in turning operations. The algorithm is based on the cutting conditions (cutting speed and feed rate) and measured cutting forces, which are used as inputs to a three-layer MLFF N-Network. The network is first trained using a set of workpiece material (P20 mold steel) and a tungsten carbide (H13A) cutting tool at various cutting conditions. The algorithm is later successfully verified on-line during turning of the same mold steel at conditions that differ from the data used in training. The algorithm is packaged in a software module, and integrated to an open Intelligent Machining Module used on industrial CNC systems.     

Development of flank wear prediction model of Zirconia Toughened Alumina (ZTA) cutting tool using response surface methodology

Flank wear is an important criterion for machinability assessment of a material. The present study is an attempt to evaluate the influence of factors such as cutting speed, feed rate and depth of cut on flank wear during hard turning of EN 24 steel with newly developed transformed toughened nano-composite Zirconia Toughened Alumina (ZTA) ceramic inserts. ZTA provides a cost effective materials solution to the most demanding applications which require wear resistance, corrosion resistance, high temperature stability and superior mechanical strength. Several machining experiments were performed and mathematical models for flank wear have been postulated by using Response Surface Methodology (RSM). The analysis was based on a first order model in which the flank wear (V_b) is expressed as a function of three independent variables i.e. cutting speed (V), feed rate (F) and depth of cut (T). Analysis of Variance (ANOVA) was applied to check the adequacy of the mathematical model and their respective parameters. Key parameters and their interactive effect on flank wears have also been presented in graphical contours which may help for choosing the process parameters and predict the cutting condition for maximum tool life.     

Wear behaviour of cryogenically treated tungsten carbide inserts under dry and wet turning conditions

Cryogenic treatment has been acknowledged as a means of extending the life of tungsten carbide inserts but no study has been reported in open literature regarding the effect of coolant on the performance of cryogenically treated tungsten carbide inserts in turning. In order to understand the effect of coolant, a comparative investigation of the wear behaviour of cryogenically treated tungsten carbide inserts in dry and wet orthogonal turning has been carried out in this study. The commercially available uncoated square-shaped tungsten carbide inserts with chip breakers were procured and cryogenically treated at ?196 °C and the cutting tests were executed in accordance to the International Standard Organisation, ISO 3685-1993 for continuous and interrupted machining mode. The criterion selected for determining the tool life was based on the maximum flank wear (0.6 mm) and the selection of cutting conditions was made to ensure the significant wear at a suitable time interval. The results showed that cryogenically treated tungsten carbide inserts performed significantly better in wet turning conditions under both continuous and interrupted machining modes especially at higher cutting speeds. A considerable increase in tool life was also recorded in interrupted machining mode as compared with continuous machining mode.     

Machinability of ultrafine-grained copper using tungsten carbide and polycrystalline diamond tools

Equal channel angular extrusion (ECAE) is an effective process to produce bulk ultrafine-grained (UFG) materials from regular coarse-grained materials. Such ECAE-processed materials typically excel in strength, wear resistance, ductility, and high strain-rate superplasticity, with promising applications in lightweight transportation and medical industries. Precision machining work is generally indispensable for further applications after bulk materials are produced by ECAE. To effectively and efficiently machine such ECAE-processed materials for further broad applications, machining issues such as machinability and tool material selection should be considered. This study was undertaken to investigate the machinability of ECAE-processed pure copper using both tungsten carbide (WC) and polycrystalline diamond (PCD) cutting tools in order to facilitate broad applications of ECAE-processed UFG coppers. It is found that despite its higher cost, PCD is favored to machine UFG copper based on this study since it has better wear resistance, gives lower cutting forces, yields a better workpiece surface finish, and results in no smearing on the workpiece. In machining UFG copper, depth of cut notching was observed as the wear pattern and abrasion as the wear mechanism for the WC tool, while flank wear was observed as the wear pattern and diffusion as the wear mechanism for the PCD tool.     

Artificial Neural Networks for Surface Roughness Prediction when Face Milling Al 7075-T7351

In this work, different artificial neural networks (ANN) are developed for the prediction of surface roughness (R _a ) values in Al alloy 7075-T7351 after face milling machining process. The radial base (RBNN), feed forward (FFNN), and generalized regression (GRNN) networks were selected, and the data used for training these networks were derived from experiments conducted using a high-speed milling machine. The Taguchi design of experiment was applied to reduce the time and cost of the experiments. From this study, the performance of each ANN used in this research was measured with the mean square error percentage and it was observed that FFNN achieved the best results. Also the Pearson correlation coefficient was calculated to analyze the correlation between the five inputs (cutting speed, feed per tooth, axial depth of cut, chip’s width, and chip’s thickness) selected for the network with the selected output (surface roughness). Results showed a strong correlation between the chip thickness and the surface roughness followed by the cutting speed.     

Experimental evaluation on the effect of minimal quantities of lubricant in milling

Implementation of stricter Environmental Protection Agency (EPA) regulations associated with the use of ample amount of flood coolant has led to this study on minimal quantities of lubrication (MQL) technique on milling of ASSAB 718 HH steel at 35 HRc with uncoated carbide inserts while the MQL amount and flood coolant flow rate were 8.5 ml h⁻¹ and 42,000 ml min⁻¹, respectively. Unlike fracture in flood cooling or flaking in dry cutting the MQL used aided inserts were still in serviceable condition despite the presence of higher width of flank wear. Analyses of the cutting force, surface roughness, chip shape and EDX findings reveal that MQL may be considered as an economical and environmentally compatible lubrication technique for low speed, feed rate and depth of cut.     

Bar diameter as an influencing factor on temperature in turning

Factors such as cutting speed, feed rate, tool material, etc., are well known to have an effect on tool wear in metal turning. However, reliable methods of wear prediction over a broad spectrum of cutting circumstance remain elusive, suggesting that not all factors have been recognised as significant and thus considered. This paper demonstrates that one such factor is bar diameter. The findings are analysed in three separate ways. All tests were performed under identical cutting conditions, i.e. cutting speeds were constant as well as the feed rate and depth of cut, also the same bar was used except for varying the bar diameter. All experiments were performed in single point turning on solid carbon steel bar (BS970 080A42), by using uncoated ISO (4957) (BS 4659 BT42) HSS insert.     

Tool wear and machining performance of cBN–TiN coated carbide inserts and PCBN compact inserts in turning AISI 4340 hardened steel

PCBN is the dominant tool material for hard turning applications due to its high hardness, high wear resistance, and high thermal stability. However, the inflexibility of fabricating PCBN inserts with complex tool geometries and the prohibitive cost of PCBN inserts are some of the concerns in furthering the implementation of CBN based materials for hard turning. In this paper, we present the results of a thorough investigation of cBN plus TiN (cBN–TiN) composite-coated, commercial grade, carbide inserts (CNMA 432, WC–Co (6% Co)) for hard turning applications in an effort to address these concerns. The effect of cutting speed and feed rate on tool wear (tool life), surface roughness, and cutting forces of the cBN–TiN coated carbide inserts was experimented and analyzed using analysis of variance (ANOVA) technique, and the cutting conditions for their maximum tool life were evaluated. The tool wear, surface roughness, and cutting forces of the cBN–TiN coated and commercially available PCBN tipped inserts were compared under similar cutting conditions. Both flank wear and crater wear were observed. The flank wear is mainly due to abrasive actions of the martensite present in the hardened AISI 4340 alloy. The crater wear of the cBN–TiN coated inserts is less than that of the PCBN inserts because of the lubricity of TiN capping layer on the cBN–TiN coating. The coated CNMA 432 inserts produce a good surface finish (<1.6 μm) and yield a tool life of about 18 min per cutting edge. In addition, cost analysis based on total machining cost per part was performed for the comparison of the economic viability between the cBN–TiN coated and PCBN inserts.     

Monitoring of flank wear of coated tools in high speed machining with a neural network ART2

A monitoring system for classifying the levels of the tool flank wear of coated tools into some categories has been developed using an unsupervised and self-organizing artificial neural network, ART2. The input pattern used for the ART2 was an array of normalized mean wavelet coefficients of the feed force, which was affected by not only the flank wear but also the severe crater wear observed in high speed machining. The outputs of ART2 were classified into four or five categories of wear levels: the incipient stage, one or two intermediate stages, final stage and hazardous stage. For two apparently different series of input data obtained under the same cutting conditions, which are often experienced in the experiment, the ART2 neural network showed very similar classification of tool wear levels from the beginning to the end of cutting. Further study proved that this monitoring system detected the excessive wear in the hazardous stage for different cutting speeds 5–7 m/s and different feed rates 0.10–0.20 mm/rev.     

Face milling of the EN AB-43300 aluminum alloy by PVD- and CVD-coated cemented carbide inserts

Two commercially available WC-6Co cemented carbide substrates (Extramet EMT100 and Pramet H10), were industrially coated with PVD TiB₂ or CVD diamond. Subsequently, the coated inserts were submitted to dry sliding tests (slider on cylinder contact geometry) against the aluminum alloy EN AB-43300, for preliminary performance ranking and identification of basic wear mechanisms. The best substrate/coating combination (CVD-Diamond coated Extramet EMT100) was then tested in face milling EN AB-43300 with milling tool characterized by two different geometries (A and B), using PCD inserts as a reference for comparison. In milling tests, the influence of both insert geometry and cutting fluid feed rate were taken into account. The geometry of the tool was identified as the main parameter in influencing the tool performance. In particular, in the case of the A geometry, the relative flank wear of CVD coated tools increased abruptly during the test due coating detachment, whilst with the B geometry no catastrophic failure of the CVD coated insert was observed. The influence of Cutting Fluid Feed Rate (CFFR) also changed with tool geometry: in particular, with the B geometry, which allowed to obtain the best results with the CVD coated inserts, a decrease of CFFR from 100 to 25% did not affect significantly the wear resistance of CVD-coated inserts and allowed to maintain the roughness of the workpiece (R_a) below 0.6 μm, notwithstanding a slightly increased tendency towards the formation of Al-based transfer layers.     

Face milling of the EN AB-43300 aluminum alloy by PVD- and CVD-coated cemented carbide inserts

Two commercially available WC-6Co cemented carbide substrates (Extramet EMT100 and Pramet H10), were industrially coated with PVD TiB₂ or CVD diamond. Subsequently, the coated inserts were submitted to dry sliding tests (slider on cylinder contact geometry) against the aluminum alloy EN AB-43300, for preliminary performance ranking and identification of basic wear mechanisms. The best substrate/coating combination (CVD-Diamond coated Extramet EMT100) was then tested in face milling EN AB-43300 with milling tool characterized by two different geometries (A and B), using PCD inserts as a reference for comparison. In milling tests, the influence of both insert geometry and cutting fluid feed rate were taken into account. The geometry of the tool was identified as the main parameter in influencing the tool performance. In particular, in the case of the A geometry, the relative flank wear of CVD coated tools increased abruptly during the test due coating detachment, whilst with the B geometry no catastrophic failure of the CVD coated insert was observed. The influence of Cutting Fluid Feed Rate (CFFR) also changed with tool geometry: in particular, with the B geometry, which allowed to obtain the best results with the CVD coated inserts, a decrease of CFFR from 100 to 25% did not affect significantly the wear resistance of CVD-coated inserts and allowed to maintain the roughness of the workpiece (R_a) below 0.6 μm, notwithstanding a slightly increased tendency towards the formation of Al-based transfer layers.     

Experimental Investigations to Study the Effects of Microwave Treatment Strategy on Tool Performance in Turning Operation

In the present study, microwave treatment has been used to enhance the tribological properties of single-point tungsten carbide (WC) cutting tool inserts such as wear resistance and hardness. The tool hardness and cutting parameters were considered to evaluate the performance of microwave-treated WC inserts in turning operation. The optimum cutting parameters were identified using response surface method (RSM)-based desirability approach. The relationship between cutting parameters and output responses, viz. flank wear, cutting force and surface roughness, was developed using the RSM. The investigations revealed that the increase in tool hardness due to complex carbide formation results in a significant reduction in tool wear, cutting forces and improvement in the surface finish of workpiece. Further, the statistical models results were validated with the experimental results. Metallurgical properties of treated and untreated tool inserts were analyzed using scanning electron microscope, x-ray diffraction method and Vickers microhardness tests. The results highlighted the importance of microwave treatment in enhancing the machining performance in turning operation.     

Experimental study on ultrasonic elliptical vibration cutting of hardened steel using PCD tools

Diamond tools cannot usually be applied for machining hardened steels while applying conventional cutting technique. As an alternative, ultrasonic elliptical vibration cutting (UEVC) technique was successfully applied for obtaining mirror surface on such steels using single crystal diamond (SCD) tools. In order to reduce production cost without compromising mirror surface quality, polycrystalline diamond (PCD) tools may be tested against highly expensive SCD tools. However, study on machining of hardened steel using PCD tools applying the UEVC technique has not yet been reported. The current research presents an experimental study on UEVC of hardened stainless steel (a typical Stavax, hardness 49 HRC) using the PCD tools. Face turning experiments were carried out to investigate the effects of three machining parameters: nominal depth of cut, feed rate, and nominal cutting speed on output performances such as cutting force, tool flank wear, surface roughness, and chip formation. Experimental results show that nominal cutting speed has very strong influence on the output performances, compared to the other two parameters. The surface roughness improves with a decrease in cutting speed. A mirror-like surface of approximately 804 mm² with a roughness value R_a of 11 nm was achieved at a lower cutting speed. Theoretical explanations have been given to support the results drawn from the UEVC experiments. It can be concluded that, while applying the UEVC technique, the inexpensive PCD tools instead of the SCD tools can be effectively applied to obtain optical surface for producing precise molds from the hardened steel.     

Evaluation of machinability in turning of microalloyed and quenched-tempered steels: Tool wear,statistical analysis,chip morphology

The machinability of microalloyed steel (30MnVS6) and quenched-tempered (QT) steels (AISI 1045 and AISI 5140), at different cutting condition, is presented in the paper. An experimental investigation was conducted to determine the effects of cutting speed, feed rate, hardness, and workpiece material on the flank wear land and tool life of coated cemented carbide inserts in the hard turning process. It was tried that for any test condition the hardness of these steels became almost identical by using appropriate heat-treatment processes. The statistical analysis was used for evaluation of different factors on cutting forces. Chips characteristics and chip/tool contact length were also investigated. The different sections (shear plane, microcrack, thickness and edge) of the chip were examined by scanning electron microscope (SEM). Shear planes and microcracks of the chips in microalloyed steel show that the chips of microalloyed steel are regular and discontinuous. Crater wear of the tools was studied by using video microscope in turning process. The results showed that the tool life and machinability of the microalloyed steel is better than the QT steels at identical cutting condition.