Figure 6 - uploaded by Ramon Quiza
Content may be subject to copyright.
1 Sample of a feed-forward neural network 

1 Sample of a feed-forward neural network 

Source publication
Chapter
Full-text available
This chapter aims to illustrate the application of computer-based techniques and tools in modelling and optimization of hard-machining processes. An overview of the current state-of-the-art in this wide topic is reflected. Computational methods are explained not only for modelling the relationships between the variables in the cutting process, but...

Context in source publication

Context 1
... but also other more conventional approaches having proved to be effective for this purpose. The second one describes the hard machining optimization problem and reviews the recently used tools, comparing their performance. A case of study is included in order to illustrate the combination of neural networks and genetic algorithms in solving a turning optimization problem. Finally, the future trends in these fields are roughly foreseen. Mathematical modelling of hard machining processes is carried out for two main purposes. On the first hand, it is used for obtaining relationships between cutting variables in order to be used in process planning and optimization. These models usually relate cutting parameters (depth of cut, feed, cutting speed, etc.) with important process variables, such as cutting temperature, tool life or obtained surface roughness. These relationships are mainly stationary, i.e., they do not explicitly include the cutting time. On the other hand, modelling allows monitoring the cutting processes, by establishing the relationship between some easy to obtain parameters, such as the cutting power or the spindle current, with other relevant variables, like the tool wear. Furthermore, this kind of modelling permits identifying certain values of the measured variables, indicating some important event into the machining process (in example, the cutting tool failure). In both cases, the relationship is transient, that is, it explicitly involves the time. It may be noted that most of the papers published on hard machining modelling, study the turning process [1-7], while only a few deal with other processes like milling [8, 9]. Another important fact is the studied material. The most popular used materials are AISI 52100 steel [1, 3, 5, 7, 10] and AISI D2 steel [2, 6-8, 11, 12], although some other ones have been also reported, for example, AISI 3020 austenitic steel [4], AISI AISI H11 (DIN X38CrMoV5) steel [9] and AISI H13 steel [13, 14]. Widely used, from the very beginning of the cutting process modelling, the statistic related techniques have proved being effective in solving an important part of the machining modelling problems, even in hard machining. Several recent published works have reported the successful use the regression models for different cutting parameters, mainly surface roughness [5], cutting force [9] and tool life [15]. Some researchers attempt to model more than one variable, such as Davim and Figueira [6], who consider surface roughness, cutting forces and tool flank wear and Arsecularatne et al. [12], who model surface roughness and cutting force components. Analysis of variance (ANOVA) has been used for computing the influence of cutting parameters on surface roughness, tool wear and cutting force components [6, 13]. Furthermore, this technique is widely used in multiple regressions in order to test the validity of the obtained model. Taguchi robust method is another reported technique, in hard turning modelling. It has been applied for modelling the effects of cooling on tool wear [16] and for predict tool wear and surface roughness versus cutting parameters [17]. Several recent papers [2, 4, 11, 14] compare performance of statistical multiple regressions and artificial neural networks in modelling some variables. They usually claim to have obtained better outcomes by using neural networks than by using conventional statistical tools. However, there is a lack of rigorous techniques for comparing these approaches, therefore, the shortcomings of the statistical approaches is not fully proved, although it is commonly accepted than cutting phenomena in hard turning are still not yet well understood [1]. Due to the complexity of cutting processes phenomena, there is a heavy non- linearity in the relationships between the involved variables. For this reason, several researchers have pointed the shortcomings of the statistical approaches in modelling these relationships [18]. On the contrary, some artificial intelligence based tools, have been proved their ability for matching complex non-linear relationships. The most popular and deeply studied techniques in soft computing are the artificial neural networks. They have been successfully used for modelling different phenomena in hard machining processes. Artificial neural networks arose as an attempt to model de brain structure and functioning. However, besides any neurological interpretation, they can be considered as a class of general, flexible, non-linear regression models [19]. The network is composed for several simple units, called neurons, arranged in certain topology, and connected with each other. Neurons are organized into layers. Depending upon their position, layers are denominated input layer, hidden layer or output layer. A neural network may contain several hidden layers. If, in a neural network, neurons are connected only with those ones in the following layers, it is called a feed-forward network (see Fig. 6.1). In this group are included multilayer perceptrons (MLP), radial basis function networks (RBF) and self-organizing maps (SOM). On the contrary, if recursive or feed-back connections exist between neurons in different layers, the network is called recurrent (see Fig. 6.2). Elman and Hopfield networks are typical samples of recurrent topologies. A typical neuron consists of a linear activator followed by a non-linear inhibiting function (see Fig. 6.3). The linear activation function yields the sums of weighted inputs plus an independent term so-called bias, b . The non-linear inhibiting function attempts to arrest the signal level of the sum. Step, sigmoid and hyperbolic tangent functions are the most common functions used as inhibitors (see Fig. 6.4). Sometimes, purely linear functions are used for this purpose too, especially in output layers. The process of adjusting weights and biases, from supplied data, is called training and the used data, training set. The process of training a neural network can be broadly classified into two typical categories: • Supervised learning. Requires using both the input and the target values for each sample in the training set. The most common algorithm in this group is the back-propagation, used in the multilayer perceptron, but it also includes most of the training methods for recurrent neural networks, time delay neural networks and radial basis function networks. • Unsupervised learning. It is used when the target pattern is not completely known. It includes the methods based on the adaptive resonance theory (ART) and self-organizing maps. Back-propagation, which is applied to multilayer perceptrons is the most popular and well studied training algorithm. It is a gradient-descendent method that minimizes the mean square error of the difference between the network outputs and the targets in the training set. Non-linear function approximation is one of the most important applications of multi-layer neural networks. It has been probed that a two-layer neural network can approximate any continuous function, within any arbitrary pre-established error, provided that it has a sufficient number of neurons in the hidden layer. This is the so-called universal approximation property. In hard machining, artificial neural networks have been widely used, not only for modelling of variables [1, 2, 7, 11], but also for monitoring purposes [20]. A very interesting approach is presented by Umbrello and co-workers [3], who combine neural networks and finite element method to predict residual stresses and the optimal cutting conditions during hard turning. Even for the most widely implemented multilayer perceptron neural network (MLP), there are still no general rules to specify the number of hidden layers, the number of neurons for each layer, and the network connection to achieve an optimized modelling effect. If artificial neural network is selected as a tool wear modelling approach, such challenges must be carefully addressed [1]. Another drawback is that only few papers present the mathematical model of the trained neural network, i.e., the coefficients of weights and biases. This does not allow using the outcomes in other applications. Fuzzy logic, which is based on fuzzy sets theory, deals with uncertainty. While binary logic uses only two values for their sets (1 or 0), in fuzzy logic the degree of truth of a statement can range between 0 and 1. A fuzzy set is a subset of elements, each one having an associated value, from the interval [0, 1] which defines its membership to certain set. These values are also known as degree of truth, and their distribution is called membership function. For example, in Figure 6.5 membership functions for three subsets of cutting force, F C , are shown. They are called low, moderate and high. Therefore for a force F = 2500 N, the following statements have the indicate degree of ...

Similar publications

Article
Full-text available
In recent years, rapid developments in imaging concepts and computational methods have given rise to a new generation of imaging technologies based on chaos. These chaos-inspired imaging technologies (CI2-Tech) consist of two directions: non-invasive and invasive. Non-invasive imaging, a much older research direction with a goal of imaging through...

Citations

... Sample of a feed forward Neural Network[88] ...
Thesis
Full-text available
Metal Additive Manufacturing has earned significant industrial and research inclination in the recent years given faster production times and less wastage of material as compared to subtractive or traditional manufacturing. However, issues and concerns regarding quality, and process control, repeatability and consistency with Additive Manufacturing is still under works. With more demand for tailored manufacturing suitable for specific end-applications, controlling physical properties by modifying process parameters or by inclusion of complimentary processes to Additive Manufacturing has been well known. This proposed study aims at delivering an effective way of addressing the thermal distribution control in a Powder Bed Fusion process for Selective Laser Melting of 316 Stainless Steel. Selective heating of the powder bed through a co-axially integrated induction system with a conventional laser setup is proposed based on literature survey, simulation data and baseline experiments. A system suitable for the proposed concept is designed, fabricated, and assembled. Extensive experimental trials are conducted to study the effect of the auxiliary heating source on the microstructure and the variation in physical properties of the built deposits. Effect of controlling the cooling rate of the melt pool on the resulting mechanical properties is reviewed and discussed. Machine Learning to help predict physical properties and control the process flow given the complex nature, is proposed through a Digital Twin. Analytical data generated through the depositions is used to model the training and testing of the Digital Twin and a framework for a more comprehensive study of the same is laid. A proof of concept demonstrating the use of induction in controlling the microstructure is achieved as well as initial efforts towards the Digital Twin are also successfully achieved.
... (Philipp Golda a ) the main influence factors for machining difficulties is the low thermal conductivity that leads to a concentration of the process-induced thermal energy in the cutting zone [5,6,7,8]. If this thermal energy cannot be dissipated adequately, it results in high process temperatures and subsequently high tool wear [7,9,10]. ...
Article
Full-text available
This work focuses on the cryogenic impingement cooling performance depending on the given inflow conditions. An experimental setup is presented which allows a detailed observation of the time dependent temperature distribution in a solid body via a thermal imaging camera during the cooling process. The space- and time-dependent heat transport from the solid to the impinging fluid is calculated from the gained temperature data using the so-called inverse global integration method (IGIM). This method allows an accurate determination of the heat flux density without the necessity of a precise calculation of the sensible temperature gradients. An investigation of the LN2-impingement conditions such as mass flow rates and fluid density is conducted to bridge the gap between the inflow conditions and the resulting heat fluxes. Moreover, a variation of the working pressure and the nozzle geometry is also performed to assess the main dependencies of the cooling performance. Thus, some important conclusions regarding the heat flux and its governing physical phenomena can be drawn. In order to simplify the application of the gathered information, the corresponding heat transfer coefficients are calculated as a function of the time dependent surface temperature and the set inflow conditions. It is shown that the usage of a constant value results in a high inaccuracy because the heat flux density and the heat transfer coefficient show no trivial correlation for arbitrary impingement conditions.
... (b) Synaptic weights, which are interneuron connections are used to store the knowledge. Figure 11: A diagram representing an artificial neural network [89]. ...
... The diagram below shows an example of a simple feedforward neural network. Figure 13: A feedforward artificial neural network [89]. ...
Thesis
Full-text available
Solar energy powered systems are increasingly being implemented in different areas due to the advances in solar energy technologies. Some of the major areas for solar energy applications include solar water heating, solar electric power generation, and solar water pumping. Solar water pumping has become the most adopted solar energy technology in the last decade. It has been considered as an attractive way to provide water in remote areas. A major advantage of using solar water pumps is that they are naturally matched with solar irradiation since usually water demand is high in summer when solar irradiation has its maximum values. However, solar energy powered systems are weather dependent. In most cases, a solar energy source has to be combined with another energy source to form a hybrid system to overcome the demerits of using solar alone. This thesis provides the detailed design, modelling and analysis of an Artificial Intelligence (AI) based solar/diesel hybrid water pumping system. This research aims to develop an optimization model that uses AI techniques to maximize the solar energy output and manage the energy flow within the solar/diesel hybrid water pumping. Thus, the proposed system is composed of solar photovoltaic modules, battery bank, Variable Speed Diesel Generator (VSDG), Adaptive Neuro-Fuzzy Inference System (ANFIS) based Maximum Power Point Tracking (MPPT) controllers and an Energy Management Controller (EMC). The EMC, which is based on Fuzzy Logic (FL), is responsible for managing the flow of energy throughout the hybrid system to ensure an undisturbed power supply to the water pump. The PV array, battery bank, VSDG are all sized to power a 5Hp DC water pump and the ANFIS based MPPT controllers are proposed for improving the efficiency of PV modules. The modelling of the system components is performed in the MATLAB/Simulink environment. For evaluation of the proposed system, several case scenarios were considered and simulated in the MATLAB/Simulink environment. The simulation results revealed the effectiveness of the proposed ANFIS based MPPT controllers since the controllers were able to extract maximum available power from PV modules for both steady-state and varying weather conditions. The proposed EMC demonstrated the successful management and control of the energy flow within the hybrid system with less dependency on the VSDG. The EMC was also able to regulate the charging and discharging of the battery bank.
... Kekasaran permukaan mampu mempengaruhi fungsi suatu produk seperti gesekan permukaan, perpindahan panas, kemampuan penyebaran pelumasan dan pelapisan (Bagno & Di Bello, 2004). Machinability atau mampu mesin suatu material ditentukan oleh beberapa kriteria seperti umur pahat, keausan pahat, gaya potong, temperatur potong, kondisi permukaan, dan ketinggian bur (Davim, 2011). Menurut Ganguli (Ganguli & Kapoor, 2016) titanium merupakan material yang sulit untuk difrais, hal ini disebabkan karena konduktivitas panas bahan yang kurang baik sehingga saat proses pemesinan pada suhu tinggi menyebabkan terjadinya deformasi plastis pada pahat serta peningkatan reaktivitas kimia yang dihasilkan di zona pemotongan. ...
Article
Full-text available
Titanium Grade 2 termasuk jenis bahan yang sering dipergunakan di industri, utamanya pada bahan untuk implan biomedis. Titanium Grade 2 mempunyai sifat perbandingan kekakuan terhadap berat yang baik, tahan terhadap korosi dan memiliki sifat biokompatibel yang baik di dalam tubuh. Namun memiliki konduktifitas panas yang rendah, sehingga perlu memilih perameter pemesinan yang tepat untuk menghasilkan nilai kekasaran permukaan yang baik. Penelitian ini bertujuan untuk mengetahui karakteristik Titanium Grade 2 yaitu kekasaran permukaan hasil pemesinan frais. Desain penelitian menggunakan metode Taguchi L9, dengan 2 faktor dan 3 level. Parameter pemesinan yang digunakan ialah putaran spindel 500; 700; 900 rpm dan kecepatan pemakanan 25; 50; 75 mm/menit. Variabel respon yang diteliti ialah kekasaran permukaan. Proses frais dilakukan menggunakan Mesin CNC Dahlih. Kekasaran permukaan diukur menggunakan Mitutoyo surface roughess tester. Analisis data menggunakan analisis ANOVA. Hasil penelitian menunjukan bahwa ada pengaruh variasi parameter pemesinan terhadap respon kekasaran permukaan. Variabel putaran spindel mempunyai p-value sebesar 0,039 dan variabel gerak makan memiliki p-value sebesar 0,025. Hal ini menunjukkan bahwa kedua variabel bebas tersebut memiliki pengaruh yang signifikan terhadap respon kekasaran permukaan. Kekasaran permukaan terendah dapat dicapai dengan pengaturan putaran spindel sebesar 700 rpm dan kecepatan pemakanan sebesar 25 mm/menit. Kata kunci: titanium grade 2, kekasaran permukaan, frais, anova Daftar RujukanBagno, A., & Di Bello, C. (2004). Surface treatments and roughness properties of Ti-based biomaterials. Journal of Materials Science: Materials in Medicine. https://doi.org/10.1023/B:JMSM.0000042679.28493.7fBruce, 2011. (2013). Analisis Kekasaran Permukaan Dan Getaran Pada Pemesinan Bubut Menggunakan Pahat Putar Modular (Modular Rotary Tools) Untuk Material Titanium 6Al-4V Eli. Journal of Chemical Information and Modeling. https://doi.org/10.1017/CBO9781107415324.004Davim, J. P. (2011). Machining of hard materials. Machining of Hard Materials. https://doi.org/10.1007/978-1-84996-450-0Ganguli, S., & Kapoor, S. G. (2016). Improving the performance of milling of titanium alloys using the atomization-based cutting fluid application system. Journal of Manufacturing Processes. https://doi.org/10.1016/j.jmapro.2016.05.011Karkalos, N. E., Galanis, N. I., & Markopoulos, A. P. (2016). Surface roughness prediction for the milling of Ti-6Al-4V ELI alloy with the use of statistical and soft computing techniques. Measurement: Journal of the International Measurement Confederation. https://doi.org/10.1016/j.measurement.2016.04.039Kiswanto, G., Mandala, A., Azmi, M., & Ko, T. J. (2020). The effects of cutting parameters to the surface roughness in high speed cutting of micro-milling titanium alloy ti-6al-4v. Key Engineering Materials, 846 KEM, 133–138. https://doi.org/10.4028/www.scientific.net/KEM.846.133Mufarrih, A., Istiqlaliyah, H., & Ilha, M. M. (2019). Optimization of Roundness, MRR and Surface Roughness on Turning Process using Taguchi-GRA. In Journal of Physics: Conference Series. https://doi.org/10.1088/1742-6596/1179/1/012099Nithyanandam, J., Das, S. L., & Palanikumar, K. (2015). Inluence of Cutting Parameters in Machining of Titanium Alloy. Indian Journal of Science and Technology, 8(8), 556–562. https://doi.org/10.17485/ijst/2015/v8i/71291Oshida, Y. (2012). Bioscience and Bioengineering of Titanium Materials: Second Edition. Bioscience and Bioengineering of Titanium Materials: Second Edition. https://doi.org/10.1016/C2011-0-07805-5Setyowidodo, I., Sutanto, S., Mufarrih, A., & Sholehah, I. M. (2020). Exhaust temperature and peltier element optimization of thermoelectric generator output. In IOP Conference Series: Materials Science and Engineering. https://doi.org/10.1088/1757-899X/850/1/012007Shucai, Y., Chunsheng, H., & Minli, Z. (2019). A prediction model for titanium alloy surface roughness when milling with micro-textured ball-end cutters at different workpiece inclination angles. International Journal of Advanced Manufacturing Technology. https://doi.org/10.1007/s00170-018-2852-6Soepangkat, B. O. P., Pramujati, B., Effendi, M. K., Norcahyo, R., & Mufarrih, A. M. (2019). Multi-objective Optimization in Drilling Kevlar Fiber Reinforced Polymer Using Grey Fuzzy Analysis and Backpropagation Neural Network–Genetic Algorithm (BPNN–GA) Approaches. International Journal of Precision Engineering and Manufacturing. https://doi.org/10.1007/s12541-019-00017-zTapiero, H., Townsend, D. M., & Tew, K. D. (2003). Trace elements in human physiology and pathology. Copper. Biomedicine and Pharmacotherapy. https://doi.org/10.1016/S0753-3322(03)00012-XThepsonthi, T., & Özel, T. (2012). Multi-objective process optimization for micro-end milling of Ti-6Al-4V titanium alloy. International Journal of Advanced Manufacturing Technology. https://doi.org/10.1007/s00170-012-3980-zWennerberg, A., & Albrektsson, T. (2009). Effects of titanium surface topography on bone integration: A systematic review. Clinical Oral Implants Research. https://doi.org/10.1111/j.1600-0501.2009.01775.x
... However, recently manufacturers and researchers have focused on hard machining with a cutting tool as a replacement in order to reduce cost and process time. There have been many studies about optimizing the surface roughness in cutting hardened material and the results were satisfi ed [4,5]. As in [6] S Basak1, U S Dixit and J P Davim used radial basis function neural network in optimization of hard turning of AISI D2 steel with the hardness of 45 HRC. ...
... The optimum value of surface roughness found with GA was 0.32 μm. Nevertheless, J. Paulo Davim [4] pointed out limitation and drawbacks of hard machining. Besides the high cost of the cutting tool and the demand for rigidity of a supportive system, the most concern is the heat generated in cutting which is the reason for thermal shock, more tool wear, shorter tool life, deterioration of workpiece surface, and so on. ...
Article
Full-text available
Surface roughness is an important assessment of metal cutting. This paper presents an empirical investigation of cutting conditions on the surface roughness in hard milling SKD61 steel. The cutting speed, feed rate, depth of cut, and nanoparticle concentration were taken as the parameters in the experimental setup. The mixer of SiO2 particles with a size of 100nm based on cutting oil CT232 was used with 3 levels of concentration: 0, 2, and 4wt%. Twenty-seven experiments were carried out based on the DOE method developed by G. Taguchi. The best model from response surface methodology (RSM) was developed regarding the surface roughness. Further analysis with ANOVA method was performed to confirm the significant of the achieved model as well as machining parameters. According to experiment results, the weight percent of nanoparticles concentration had a great impact on the surface roughness, only after the feed rate. Additionally, the excellent effectiveness in reducing the roughness of MQL nanofluid has been demonstrated when compared with conventional MQL.
... One of the most important aspects of increasing wear resistance is tool edge preparation [8]. In machining of hardened steels, the most common cutting tool edge profiles are the chamfered edge (T-type), the rounded edge (E-type), and the chamfered and rounded edge S-type [9]. Little information on the performance of S-type mixed ceramic tools in finishing of hardened steels is still available. ...
... Little information on the performance of S-type mixed ceramic tools in finishing of hardened steels is still available. Despite the importance of the tool geometry for turning and its effect on the chip formation, machining forces, tool wearing, surface finish and surface integrity [4,9,10], the influence of the cutting parameters on the tool failures has not been investigated. ...
Article
Full-text available
In this study, the performance and the useful life of a mixed ceramic tool with S-type edge microgeometry are evaluated for the case of dry turning of AISI 4140 steel hardened to 55 HRC. The influence of the cutting speed and feed rate of the cutting parameters on the tool failure was investigated. The experiments were designed and analysed using the complete factorial design technique. Our results indicate that the cutting speed and feed rate values exert significant influence on the tool lifespan. Crater and flank wear occur in all cutting conditions. The predominant tool wear mechanisms are diffusion, abrasion, and adhesion, which are also known as attrition. The tool life curve and equation were established for the machining conditions of this investigation to achieve the subsequent optimisation of this process.
... High-hardness materials include various hardened alloy steels, case-hardened steels, super alloys, nitridesteels; hard-chrome coated steels, and heat-treated powder metallurgical parts. Hardened steel such as AISI 52100 steel for bearing applications, 16MnCr5 for automotive gears and shaftswere early recognized by the automotive industry for transmission components [1]. ...
Conference Paper
Full-text available
The degree of holding temperature and time play a major role in nano-case treatment of cutting tools which immensely contributed to its performance during machining operation. The objective of this research work is to carryout comparative study of performance of nano-case treatment tools developed using low and medium carbon steel as work piece. Turning operation was carried out under two different categories with specific work piece on universal lathe machine using HSS cutting tools 100 mm × 12mm × 12mm that has been nano-case treated under varying conditions of temperatures and timeof 800,850, 900, 950°C and 60, 90, 120 mins respectively. The turning parameters used in evaluating this experiment were cutting speed of 270, 380 and 560mm/min, feed rate of 0.15, 0.20 and 0.25 mm/min, depth of cut of 2mm, work piece diameter of 25mm and rake angle of 7° each at three levels. The results of comparative study of their performances revealed that the timespent in the machining of low carbon steel material at a minimum temperature and time of 800°C, 60 mins were1.50, 2.17 mins while at maximum temperature and time of 950°C, 120 mins were 1.19, 2.02 mins. It was also observed that at a corresponding constant speed of 270,380 and 560mm/min at higher temperature and time, a relative increased in the length of cut were observed. Critical observation of the result showed that at higher case hardening temperature and time (950°C/120mins), the HSS cutting tool gave a better performance as lesser time was consumed during the turning operation.
... Furthermore, other major issues associated with machining of titanium alloys include generation of high mechanical pressure, high dynamic loads, high cutting temperature, and tendency to adhesion and forming built up edge [3,4]. In view of their potential market, lots of large companies (e.g., Rolls Royce) present different studies to develop appropriate techniques for machining titanium alloys in order to minimize machining cost, achieve excellent surface quality, and achieve reasonable production rates by considering the unique characteristics of titanium alloys and developing new sustainable energy systems [4,5]. ...
... The developed models using MWCNT nanofluid for flank wear and power consumption are provided as shown in Eqs. (4)(5), respectively. ...
Article
Full-text available
Owing to their superior mechanical, physical, and chemical characteristics, titanium and its alloys are broadly used in different industrial applications such as military, aerospace, power generation, and automotive. However, titanium alloys are inherently difficult to cut materials due to the high generated temperature during machining. In addition to flood cooling, several other techniques were employed to reduce the harmful effect and the generated temperature and generally improve titanium alloys machinability. In this paper, an attempt is made to utilize nano-additives to improve the cooling efficiency of minimum quantity lubrication (MQL) during machining titanium alloys. The main objective of the current research is to investigate the influence of dispersed multi-walled carbon nanotubes (MWCNTs) into vegetable oil by implementing the MQL technique during turning of Ti–6Al–4V. The novelty here lies on enhancing the MQL heat capacity using different concentrations of nano-fluid in order to improve Ti–6Al–4V machinability. Different cutting tests were performed and relevant data were collected. The studied design variables were cutting speed, feed rate, and percentage of added nano-additives (wt%). It was found that 2 wt% MWCNT nano-fluid reduced the power consumption by 11.5% in comparison with tests performed without any nano-additives, while the same concentration reduced the flank wear by 45%.
... Regarding the hard turning characteristics, it has advantages like process flexibility, material removal rate, set up time and environmental compatibilityand is mainly applied to machining multi-body and complex geometry components, i.e., gear shaft (multi-body, pulley cone, continuous and interrupted cut). The technology spread out was based on machine tools with high stiffness and dynamic stability combined with ceramic and PCBN tool materials [1][2][3][4]. Furthermore, the hard turning process feasibility is strongly dependent on the ceramic and PCBN tool behaviorthe tool wear level and the tool wear mechanism [5][6][7][8][9][10] and its relationship with the cutting conditions [11][12][13][14]. ...
... The typical hard turning definition found in literature describes the process when the machined material hardness is above 45 HRC [2]. Klocke [15] supports the definition when machined material hardness is above 50 HRC. ...
... In addition, Luo, Liao and Tsai [19] observed lower tool wear level (flank wear) with the steel at 50 HRC, when turning of AISI 4340 steel (35-45-50-55 and 60 HRC) with ceramic and CBN tools. The thermo-mechanical processes and phenomena described are the critical issue that make it not possible to compare hard turning to conventional turning [2,20]. ...
Article
Hard turning has been applied in a wide range of mechanical components based on ferrous materials. The application of these components is a function of mechanical properties and microstructure – that also has manufacturing process influences, i.e., cutting mechanism. This research aims to discuss the tool wear level and the correlation with the wear mechanisms in turning with PCBN tools, which deals with three steel alloys (AISI 4340, AISI 52100 and AISI D2) and considers six levels of hardness (on the interval from 35 to 60 HRC), applying the novel three-dimensional wear parameters based on Focus Variation Microscope (FVM) to wear evaluation. Considering the wear parameters that represent the amount of material removed from the tool (WRM) and tool affected area (WAA), tool wear intensity and abrasion wear mechanisms have a decreasing trend with the increase of hardness in the range of 35–50 HRC. Above 50 HRC, however, there is a tendency of increased tool wear intensity when steel hardness is increased. The fraction volume of carbides in the steel microstructures intensifies the abrasion wear mechanism. The adhesion wear mechanism showed a reduction with an increase of the steel's hardness – identified by wear parameters WAM (adhered material volume on the tool). Based on crater wear formation, the diffusion wear mechanism had an inverse behavior when compared to adhesion. Better results concerning tool wear can be achieved when turning steels with 50 HRC. It was evidenced that the three-dimensional wear parameters applied open new possibilities to understanding complex and specific phenomena occurring in machining processes, particularly in the machining of hardened steels.
... In most of the cases, cemented carbide degradation starts from the cobalt binder and the WC-cobalt cohesion. 9 Ghani et al. 10 studied the tool wear mechanism of TiN coated carbide and uncoated cermets tools in machining of hardened AISI H13 tool steel. The results of their investigation indicated that both the inserts experience uniform and gradual wear on the flank face, and diffusion and oxidation have also been experienced under higher cutting conditions. ...
Article
Full-text available
The aim of the present investigation is to identify the wear mechanisms of multilayer coated carbide tool under different machining conditions during turning of hardened AISI 4340 steel. The chemical vapor deposited multilayer coated (TiN/MT TiC,N/Al2O3) carbide tool was used. The worn surfaces of the cutting tools were examined under digital optical microscope, scanning electron microscope, and elemental analysis. The investigation results showed a strong correlation between the cutting conditions and tool wear. The cutting speed and feed rate ensure the dominant effects on the tool wear followed by the depth of cut and also the progress of tool wear were verified under different intervals of time. The flank and rake faces of the cutting tool were severely gouged by the hard particles of workpiece material exhibited abrasive wear phenomenon. Intermittently, chipping at cutting edge, notching and catastrophic failure modes were observed in continuous machining.