Raziskovalni projekti so (so)financirani s strani Javne agencije za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije

 

Part production by material removal processes is still one of the most efficient ways to manufacture parts of devices considering the quality and production time. It is no secret that 3D printing technologies are continuously improving, and they offer unique advantages in terms of design flexibility and customization, making them a valuable addition to the manufacturing industry [1]. Nevertheless, 3D printing still has limitations in terms of surface quality and geometric accuracy. Therefore, traditional material removal technologies will certainly remain inevitable procedures in the coming decades, especially for metal workpieces, where high surface quality and geometric accuracy are essential.

 

The machining process and the result of material separation (e.g. surface quality) is highly influenced by many factors, such as cutting parameters, cooling and lubrication techniques, and wear condition of the machining tool. The surface quality plays a crucial role in determining the functionality, aesthetics, and overall quality of machined parts. Poor surface quality can lead to problems such as increased friction and wear, decreased lifespan of the part, and decreased product performance. Hence, there is a pressing need to improve surface quality in machining processes.

 

Tool life is a critical factor in advanced manufacturing processes, as it directly impacts the efficiency, productivity, and cost-effectiveness of the manufacturing process [2]. The prediction and estimation of tool life during the manufacturing process are crucial to avoid unnecessary unfinished parts and waste of resources [3]. Although the cost of tools is only approximately 3-10% of the entire production process, it is still not good if we change tools too early, because the proportion of downtime increases. If, on the other hand, the tool is changed too late, the tool may break in the workpiece, resulting in scrap. By collecting data and analyzing the factors that influence tool life, manufacturers can optimize tooling, reduce downtime, and improve the overall efficiency of the manufacturing process [4].

 

Another important demand in the industry is machining of materials of high hardness and strength to manufacture e.g. turbine blades, automotive and aerospace parts. The hardness of these materials can range from 45 HRC to as hard as 64 HRC [5]. Hard machining means special material removal conditions, so it requires a review of previously known relationships. Hard machining can be considered as an alternative to grinding and EDM traditional methods of machining difficult-to-machine materials [6].

 

In recent years, intensive research has been carried out related to machining of difficult-to-cut materials, effect of cooling and lubrication techniques, and tool life. Sultana et al. presented a review of the different cooling techniques and coolant types in metal cutting, but it was not focused on the machining of hard materials. Eltaggaz et Al investigated the influence of coolant strategy on tool life and surface roughness when machining ADI (Austempered Ductile Iron) [7]. Four different cooling strategies (dry, flood, MQL and MQL with nanofluid) were involved in the research, cutting experiments based on L24 mixed orthogonal array were carried out, and response surface methodology was applied to analyze and model the measured responses [8]. Shokrani et Al discussed the use of a hybrid cryogenic MQL (Minimum Quantity Lubrication) system to improve tool life in machining Ti-6Al-4V titanium alloy. The researchers proposed a new cutting tool design that uses cryogenic cooling and a new cutting tool geometry to achieve higher material removal rates [9]. Agrawal investigated the effect of cryogenic cooling on tool life, surface roughness, and carbon emissions compared to wet machining in turning of Ti–6Al–4V titanium alloy. The study concluded that cryogenic machining has significantly better potentials [10]. Yıldırım et Al investigated the influence of different cooling methods (dry, wet and MQL) on tool life, wear mechanisms, and surface roughness in the milling of nickel-based superalloy Waspaloy using uncoated carbide tools. Considering the production costs, the environment and employee health, they recommended the application of MQL system in the milling of Waspaloy [11]. Gan et al investigated the use of cryogenic cooling in the machining of difficult-to-machine materials, such as titanium alloys. They found that cryogenic cooling significantly improved tool life and reduced surface roughness, making it a viable option for sustainable machining [12].

 

One of the most important trends and aims of part manufacturing companies is the introduction of Industry 4.0 applications. Industry 4.0 is a term used to describe the fourth industrial revolution, which is characterized by the integration of advanced technologies such as artificial intelligence (AI), the Internet of Things (IoT), and big data analytics into manufacturing processes [13,14,15,16]. The impact of Industry 4.0 on the economy is expected to be significant, with the value creation potential for manufacturers and suppliers estimated to reach $3.7 trillion by 2025 [17].

 

With the emergence of Industry 4.0, supported by the increasing accessibility of modern data collection devices and the available computation power, it has become more and more feasible to use machine learning (ML) methods in various industrial fields, including manufacturing. One prominent field of ML is to develop prediction models, which can be used to predict a multitude of factors, such as product quality [18] or tool life [19]. Such models are trained on large amounts of historical data, and following the training process they are capable of the prediction. Machine learning approaches were used successfully for training prediction models for the remaining useful life of machine components [20] or turning tools based on a Design matrix as per L9 orthogonal array [21]. These techniques can apply a wide variety of machine learning methods, such as artificial neural networks or image processing techniques supported by Fuzzy logic systems. Most of the researches related to prediction of tool life are based on experiments with a limited number of parameter combinations. In contrast, the current proposal aims to use full factorial series of experiments. It is also possible to use data originating from previous researches or researches presented in previous journal papers by other authors related to different scientific aims (not AI-based tool life or surface roughness prediction). Participants of this proposal carried out development of predictive models for surface roughness with data from historical experiments on micro milling [22].

 

Therefore, this research proposal aims to investigate the role of different machining parameters and process conditions on surface quality improvement in machining, especially in the case of hard-to-cut achining. To achieve this, statistical methods and advanced AI-based techniques (e.g. artificial neural networks, support vector machines, random forest) will be used.

Full factorial series of machining experiments will be carried out in order to collect data with various sensors (such as accelerometers, force sensors, thermal imaging, etc.). These experiments, combined with advanced analytical techniques, will generate the dataset on which the machine learning models will be trained, and the different methods will be evaluated. Apart from the prediction of the surface quality, this system will be used for tool condition monitoring as well, including the prediction of the remaining useful tool life, based on the current sensor signal. The developed AI-based predictive models are expected to provide a better estimation for the tool life than the traditional empirical or analytical models.

 

The outcome of the study will provide insights into the optimization of machining parameters for surface quality improvement and tool life utilisation, which can be useful for manufacturers and researchers in the field of machining. The research will also contribute to the development of effective cooling and lubrication techniques for difficult-tocut machining processes, which can improve the quality of manufactured components and reduce wear of cutting tools. The results can be basis for a decision support system related to the ideal timing of cutting tool change.

 

We would like to emphasize that the relationship between the participating Hungarian and Slovenian researches goes back many years. The participants researchers have long term experience on theoretical and experimental investigation of chip removal processes under different types of cooling/lubrication methods. Slovenian researcher investigated the residual stresses induced by dry turning of difficult-to-machine materials [23]. They carried out an intensive research work related to the investigation of cryogenic cooling, too [24,25,26]. They were also active on the field of tool wear analysis [27], and investigation of machinability of difficult-to-cut materials previously [28]. Innovative sequenced control of cooling/lubrication fluid with so called pulsating technique has been proposed and developed by the Slovenian researchers, where the advantages of conventional low-pressure flooding (lubrication) and high-pressure process (chip breakability) have been merged (Figure 1). This kind of cooling and lubricating method will also be involved in the current proposal.

 

Figure 1: Principle of pulsating high-pressure supply of cooling/lubricating fluid.

 

Hungarian researchers have long term experience on the field of theoretical and experimental investigation of hard cutting and micro machining [29,30,31,32]. They applied advanced design of experiments methods during research work related to metal cutting [33,34]. The colleagues dealt also with process monitoring [35,36,37,38], which is essential from the point of view of developing predictive models based on the data recorded by sensors and collected from measurements of the process characteristics.

 

All these topics are relevant in the case of the research work of the current proposal. The aforementioned knowledge and experience provide a solid basis for achieving the targeted aims.

The applied cooling method has strong effect on the results of the cutting process, such as surface roughness, and tool wear. Optimal cutting parameters have to be determined under different cooling and lubricating methods to ensure an efficient, economic and well repeatable cutting process.

1. How can the signals of different sensors in advanced machining processes be transformed into relevant data, which can be applied for training, testing, and validating of predictive models related to surface roughness and remaining useful tool life?

Sensors collecting force, vibration, acoustic emission and sound power signals can be applied in machining processes. It is always challenging to gain useful features from the raw signals. One of the goals of the research project is the detailed analysis, filtering, and processing of the raw signals, the identification of process-specific characteristics and features, and the conversion of these features into data, which can serve either as output or primarily as input data for predictive models.

2. How can artificial intelligence-based predictive models be applied to optimize cutting parameters for improved surface quality and better tool life utilization in advanced machining processes?

With the help of systematic experiments, we want to obtain suitable input and output data for advanced machining of difficult-to-machine materials. By using these data, we plan to develop models that provide predictions regarding the surface quality and the remaining useful tool life by applying artificial intelligence tools.

3. What are the most effective artificial intelligence-based modelling techniques for advanced machining processes?

In the case of machining operations, the available data for training, testing and validating the predictive models are very limited. Therefore, it is necessary to determine the machine learning method and training algorithm and their settings that result in the best estimation efficiency and accuracy. The aim of the research is to compare different machine learning algorithms.

4. Is it possible to achieve an acceptable efficiency level of prediction even with a limited amount of data?

Carrying out systematic machining experiments is very expensive and time-consuming. The aim of the research is to examine how much the model’s predicting efficiency changes in relation to the surface quality and the expected tool life if we reduce an entire set of factorial experimental results to a number of experiments corresponding to a given experimental design.

5. Is it possible to give an appropriate prediction for the surface roughness and tool life based on the current sensor signals in the case of machining hard materials?

The application of well-trained predictive models can contribute to a more efficient advanced machining process. The project aims the prediction of surface quality and remaining useful tool life based on one or more momentary sensor signals. The developed models can contribute to the application of optimized machining parameters and can help to decide on the ideal time for tool change.

6. What are the expected results?

The main aim of the research project is the detailed analysis of the characteristics of advanced machining of hard-tocut materials under different conditions, including innovative cooling methods and turning operations. A huge amount of process data will be available by recording sensor signals during full factorial cutting experiments.

Optimal machining parameters will be determined at the cutting of difficult-to-machine materials (e.g. super alloys) under different cooling and lubrication techniques, including pulsating HPJAM method.

Signal analysis and feature extraction methods will be available related to advanced machining, which can provide relevant data for predictive models.

 

The collection of vast amounts of process data will enable to train AI-based predictive models to determine the surface quality and the remaining useful tool life. Since the prediction of the remaining tool life enables an increased tool utilisation, and also reduces the risk of unexpected tool failure, the developed predictive models are expected to result in significant cost reductions.

 

Tool life will be determined with better estimation accuracy than with well-known traditional empirical and analytical calculations, and conditions that change from moment to moment can also be taken into account.

Effect of design of experiments on prediction efficiency of developed models will be available, which can support the more economical creation of data sets for model training by reducing the number of necessary cutting experiments.

1. Literature review on high-pressure cooling/lubrication

On the Slovenian side, we conducted a comprehensive literature review in the first year of the project [1], focusing on the use of high-pressure coolant and lubrication delivery in machining processes, particularly when machining difficult-to-cut materials such as titanium and nickel alloys and stainless steels. We analyzed the impact of various fluid delivery strategies (external nozzles, internal channels in the tool, different entry angles) on key process parameters such as tool wear, chip formation, surface roughness, and energy consumption. The main findings in the literature indicate that directed jets under high pressure allow for more effective penetration of the coolant into the cutting zone, reduce thermal loads, improve chip breakability, and extend tool life, while also reducing fluid consumption by up to four times compared to conventional flooding.

We also reviewed the field of pulsating high-pressure cooling, which is significantly less researched. We identified nine key studies dealing with directed delivery of emulsions or oils under a pulsing regime, typically with very low flow rates and frequencies between 5 and 12.5 Hz. Although rare, the results indicate significant advantages of this technology, such as lower cutting forces, reduced tool wear, and better control over chip length and shape. An important finding is that the field completely neglects the application of artificial intelligence, which represents an open research gap with great potential for the future.

We presented the results in November 2024 to Hungarian partners at a bilateral meeting in Budapest, where we harmonized terminology, identified opportunities for joint experimental work, and defined key challenges for further research.
• [1] Kern, M., Porenta, M., Pušavec, F. Literature review – High Pressure Machining, UL FS, November 2024. COBISS.SI-ID

2. Design of experiments

During the meeting in Budapest in November 2024, we defined the key input and output parameters to be monitored during the experimental work. Input parameters include cutting parameters (cutting speed, feed rate, depth of cut), workpiece material (and its mechanical and thermal properties), and coolant/lubrication fluid (CLF) delivery parameters. The research focuses on advanced cooling and lubrication technologies, such as pulsating high-pressure CLF delivery. The tool geometry will remain unchanged, which allows the study to focus on the influence of cutting parameters and cooling regimes.

In line with the project’s objectives, which focus on advanced machining processes, we selected Ti6Al4V (titanium alloy), maraging steel, and stainless steel 316L as workpiece materials, as they are classified as difficult-to-machine due to their mechanical and thermal properties.

The output parameters were defined based on the needs of the AI model under development, aimed at predicting the remaining useful tool life and the expected surface quality (roughness). Tool wear will be monitored on the flank face according to standard machining practices, while surface roughness will be evaluated as both profile and/or area surface roughness. Input data for the AI model, which needs to be obtained during the experiments, includes mechanical and thermal tool loads during the cutting process—specifically, cutting forces (in all three components), vibrations (measured on the tool holder), and temperature (measured as close as possible to the cutting zone).

3. Setup and calibration of the measuring and data acquisition system

On the Slovenian side, we designed a comprehensive measuring system that includes temperature, force, and vibration sensors, all integrated into the tool holder. Temperature is measured using a thermal camera or pyrometer, positioned to measure temperature from below through a drilled hole in the holder, as close as possible to the cutting zone. Force is measured indirectly using strain gauges mounted on the holder, which detect deflection and allow force calculation. Vibrations are measured with an accelerometer placed directly on the holder. The integration of all sensors into the holder enables direct monitoring of the cutting zone and thus provides essential input data for predictive AI models, which is the core research concept of the project.

The system is not yet fully completed due to technical issues with the integration of the IR sensors for temperature measurement. Nevertheless, the concept remains unchanged, and development continues toward a functional prototype. During preliminary experiments, standard measuring equipment not integrated into the tool holder was used; however, it provided the first measurements that will serve as a basis for validating the integrated system.

4. Preliminary machining experiments with pulsating high-pressure cooling and lubrication (HPJAM)

As part of the preliminary experiments, we conducted initial turning tests using our in-house developed system to determine the characteristics of the pulsating CLF delivery system. This delivery method is based on sequential control of a hydraulic valve, which enables controlled alternation between high- and low-pressure jets. At a selected fluid supply pressure, the system allows adjustment of pulse frequency and phase durations, making it possible to tailor the cooling strategy to current process needs. This also enables the creation of chips of arbitrary length, which is particularly suitable for finishing operations on difficult-to-machine materials.

Flow rate measurements of the CLF were performed under various system configurations, including different nozzle selections and control parameter settings. A direct correlation was found between nozzle size, supply pipe diameter, valve opening and pressure, and the volumetric flow rate of the CLF. Additionally, the force of the jet was measured at various working pressures and pulse frequencies using a dedicated measuring assembly that simulates jet impact on a surface. These results are critical for understanding the mechanical impact of the jet on the chip and for optimizing process parameters in further experiments.

5. Evaluation of preliminary experiment results

The preliminary experiments demonstrated that HPJAM enables highly precise control over chip length. By selecting appropriate pressure settings and timing between high- and low-pressure phases, it was possible to produce short, uniformly broken chips or longer spiral chips, depending on the need.

HPJAM also proved to be an effective way to reduce thermal load in the cutting zone. The average tool temperature decreased by more than 50 °C compared to conventional flooding, and the surface roughness when machining Ti6Al4V dropped from 3.4 μm to 2.1 μm. Cutting forces were reduced by approximately 10%, indicating lower mechanical loads on the tool and greater process stability. Flank wear was reduced by up to 45%, directly contributing to extended tool life and fewer tool replacements. The overall results confirm that HPJAM not only enables better control over chips but also significantly improves both technological and economic aspects of machining. Therefore, integrating artificial intelligence into this approach appears logical and could offer substantial progress in advanced machining processes.

6. Review of the experimental plan

The proposed experimental plan adequately defines the input and output parameters relevant for studying the effect of HPJAM on the turning process. The structure of the plan allows for a reliable connection between process conditions and system responses and serves as a solid foundation for acquiring data for training predictive AI models. However, the plan currently lacks concrete values of the input parameters at which the experiments will actually be conducted. Determining these exact values will be necessary in the next phase of the project.

In the first year of the research project implementation, the focus was primarily on reviewing the current state of the art, developing research equipment, and conducting preliminary experiments that will serve as the foundation for further research with scientifically relevant results in the following phases of the project. The activities were aligned with the defined work plan and included the development of an innovative system for pulsating high-pressure coolant and lubrication fluid delivery, the design of a measurement system, and the definition of experimental parameters and process responses, which will serve as input data for artificial intelligence models.

Due to the focus on preparatory phases of the research work, no significant scientific publications were produced during this period. The first publishable scientific results are expected in the second year of the project, when the main experimental sets will be carried out and the predictive models validated.

A key outcome is the functional system for pulsating high-pressure coolant and lubrication fluid delivery (HPJAM). As part of its validation, system characteristics such as pulse duration, jet force, and the relationship between pressure and fluid flow were determined. Experiments were carried out on titanium alloy machining, in which the effects of HPJAM on chip length, cutting zone temperature, surface roughness, cutting forces, and tool wear were analyzed. The system enabled active regulation of chip length, which has important implications for safety, automation, and process quality.

One of the key technological achievements of the project is the concept of a so-called smart tool holder, which will integrate all necessary sensors for temperature, force, and vibration measurements into a self-contained unit. This solution will allow easier data collection and the use of the measurement system even outside a research environment, indicating strong potential for industrial application and further development toward smart manufacturing.

On the Hungarian side, significant preparatory activities were also accomplished in the first year of the project. Although not formally recorded in the COBISS system, these activities represent key foundations for further research work. A comprehensive literature review was conducted on various cooling and lubrication methods and vibration-assisted machining. The partners evaluated the advantages of individual approaches and their potential usefulness for further studies. They also analyzed state-of-the-art artificial intelligence methods, with a focus on machine learning techniques for tool wear prediction, degradation modeling, and surface quality estimation.

In addition, the requirements for AI algorithms were defined, including the specification of input and output parameters and the methods for their measurement. The first draft of the experimental plan was also completed, which will be used in the second year as the basis for performing analyses and training predictive models. The contribution of the Hungarian team thus fully aligns with the project goals and represents a key part of the joint research foundation.

In summary, we can conclude that in the first year, both teams established a solid scientific foundation for continuing the project: we conducted a comprehensive literature review, developed measurement and experimental approaches, and defined all the key parameters enabling the transition to the next phase of research.

[1] Zhang, H., et al. (2020). “Surface roughness and dimensional accuracy optimization for 3D printing of polymer parts: a review.” Virtual and Physical Prototyping 15(2): 107-122.

 

[2] Bazaz, Sara M., Juho Ratava, Mika Lohtander, and Juha Varis. “An Investigation of Factors Influencing Tool Life in the Metal Cutting Turning Process by Dimensional Analysis.” Machines 11, no. 3 (2023): 393.

 

[3] Bazaz, Sara Moghadaszadeh, Mika Lohtander, and Juha Varis. “The prediction method of tool life on small lot turning process–development of Digital Twin for production.” Procedia Manufacturing 51 (2020): 288-295.

 

[4] Graham Immermann: What is Tool Life? How to Optimize Tooling with Machine Data MachineMetrics, Tool Monitoring / October 28, 2021 https://www.machinemetrics.com/blog/tool-life

 

[5] Astakhov, Viktor P. “Machining of hard materials–definitions and industrial applications.” Machining of hard materials (2011): 1-32.

 

[6] Gopalsamy, Bala Murugan, Biswanath Mondal, Sukamal Ghosh, Kristian Arntz, and Fritz Klocke. “Investigations on hard machining of Impax Hi Hard tool steel.” International Journal of Material Forming 2 (2009): 145-165.

[7] Sultana, Ms Nazma, Nikhil Ranjan Dhar, and Prianka Binte Zaman. “A review on different cooling/lubrication techniques in metal cutting.” American Journal of mechanics and applications 7, no. 4 (2019): 71-87.

 

[8] Eltaggaz, A., P. Zawada, H. A. Hegab, I. Deiab, and H. A. Kishawy. “Coolant strategy influence on tool life and surface roughness when machining ADI.” The International Journal of Advanced Manufacturing Technology 94 (2018): 3875-3887.

 

[9] Shokrani, Alborz, Ihsan Al-Samarrai, and Stephen T. Newman. “Hybrid cryogenic MQL for improving tool life in machining of Ti-6Al-4V titanium alloy.” Journal of Manufacturing Processes 43 (2019): 229-243.

 

[10] Agrawal, Chetan, Jwalant Wadhwa, Anjali Pitroda, Catalin Iulian Pruncu, Murat Sarikaya, and Navneet Khanna. “Comprehensive analysis of tool wear, tool life, surface roughness, costing and carbon emissions in turning Ti–6Al– 4V titanium alloy: Cryogenic versus wet machining.” Tribology International 153 (2021): 106597.

 

[11] Yıldırım, Çagrı Vakkas, Turgay Kıvak, and Fehmi Erzincanlı. “Influence of different cooling methods on tool life, wear mechanisms and surface roughness in the milling of nickel-based waspaloy with WC tools.” Arabian Journal for Science and Engineering 44 (2019): 7979-7995.

 

[12] Gan, Yongquan, Yongqing Wang, Kuo Liu, Siqi Wang, Qingbo Yu, Chang Che, and Haibo Liu. “The development and experimental research of a cryogenic internal cooling turning tool.” Journal of Cleaner Production 319 (2021): 128787.

 

[13] Abdelmajied, FathyElsayed Youssef. “Industry 4.0 and its implications: Concept, opportunities, and future directions.” (2022).

 

[14] Ortiz, Jesús Hamilton. “Industry 4.0: Current status and future trends.” (2020).

 

[15] Basheer Shaheen, István Németh: Machine Learning Approach for Degradation Path Prediction Using Different Models and Architectures of Artificial Neural Networks. Periodica Polytechnica Mechanical Engineering, 66(3), pp. 244–252, 2022. https://doi.org/10.3311/PPme.20145

 

[16] Shaheen, Basheer Wasef; Németh, István: Integration of Maintenance Management System Functions with Industry 4.0 Technologies and Features—A Review, Processes, 2022, 10, 2173 , 27 p. (2022)

[17] McKinsey&Company: What are Industry 4.0, the Fourth Industrial Revolution, and 4IR? https://www.mckinsey.com/featured-insights/mckinsey-explainers/what-are-industry-4-0-the-fourth-industrialrevolution-and-4ir, 2022

 

[18] Minghui Cheng, Li Jiao, Pei Yan, Siyu Li, Zhicheng Dai, Tianyang Qiu, Xibin Wang, Prediction and evaluation of surface roughness with hybrid kernel extreme learning machine and monitored tool wear, Journal of Manufacturing Processes,Volume 84, 2022, Pages 1541-1556, ISSN 1526-6125, https://doi.org/10.1016/j.jmapro.2022.10.072.

 

[19] Minh-Quang Tran, Hoang-Phuong Doan, Viet Q. Vu, Lien T. Vu, Machine learning and IoT-based approach for tool condition monitoring: A review and future prospects,Measurement,Volume 207, 2023, ISSN 0263-2241, https://doi.org/10.1016/j.measurement.2022.112351.

 

[20] Basheer Shaheen, Ádám Kocsis, István Németh: Data-driven failure prediction and RUL estimation of mechanical components using accumulative artificial neural networks, Engineering Applications of Artificial Intelligence, Volume 119, March 2023, 105749.

 

[21] P.J. Bagga, K.S. Bajaj, M.A. Makhesana, K.M. Patel, An online tool life prediction system for CNC turning using computer vision techniques, Materials Today: Proceedings, Volume 62, Part 6, 2022, Pages 2689-2693, ISSN 2214-7853, https://doi.org/10.1016/j.matpr.2021.11.482.

 

[22] Adizue, U. L., B. Z. Balazs, and M. Takacs. “Surface roughness prediction applying artificial neural network at micro machining.” In IOP Conference Series: Materials Science and Engineering, vol. 1246, no. 1, p. 012034. IOP Publishing, 2022.

 

[23] OUTEIRO, J.C., PINA, J.C., M’SAOUBI, R., PUŠAVEC, Franci, JAWAHIR, I.S. Analysis of residual stresses induced by dry turning of difficult-to-machine materials. CIRP annals, ISSN 0007-8506, 2008, letn. 57, št. 1, str. 77- 80

 

[24] PUŠAVEC, Franci, STOIĆ, Antun, KOPAČ, Janez. The role of cryogenics in machining processes. Tehnički vjesnik : znanstveno-stručni časopis tehničkih fakulteta Sveučilišta u Osijeku, ISSN 1330-3651, 2009, vol. 16, no. 4, str. 3-9

 

[25] KOPAČ, Janez, PUŠAVEC, Franci, KROLCZYK, Grzegorz M. Cryogenic machining, surface integrity and machining performance. Archives of materials science and engineering: international scientific journal published monthly as the organ of the Committee of Materials Science of the Polish Academy of Science, ISSN 1897-2764. [Print ed.], Feb. 2015, vol. 71, iss. 2, str. 83-93.

 

[26] HRIBERŠEK, Matija, PUŠAVEC, Franci, RECH, Joël, KOPAČ, Janez. Modeling of machined surface characteristics in cryogenic orthogonal turning of inconel 718. Machining science and technology, ISSN 1091-0344, May 2018, vol. 22, iss. 5, str. 829-850.

 

[27] ČERČE, Luka, PUŠAVEC, Franci, KOPAČ, Janez. Novel spatial cutting tool-wear measurement system development and its evaluation. V: ERKOYUNCU, John (ur.). CIRPe 2015: understanding the life cycle implications of manufacturing, (Procedia CIRP, ISSN 2212-8271, Vol. 37). [Amsterdam etc.]: Elsevier. 2015, vol. 37, f. 170-175.

 

[28] PUŠAVEC, Franci, DESHPANDE, Ashish, YANG, Shu, M’SAOUBI, Rachid, KOPAČ, Janez, DILLON, Oscar W., JAWAHIR, I. S. Sustainable machining of high temperature Nickel alloy – Inconel 718. Part 2, Chip breakability and optimization. Journal of cleaner production, ISSN 0959-6526. [Print ed.], Jan. 2015, vol. 87, str. 941-952.

 

[29] Balázs, B Z ; Takács, M: Finite element modelling of thin chip removal process, IOP CONFERENCE SERIES: MATERIALS SCIENCE AND ENGINEERING 426 Paper: 012002 (2018).

 

[30] B Z, Balázs ; T, Szalay ; M, Takács: Investigation of Micro Milled Surface Characteristics, In: Tomaz, Pepelnja; Zlatan, Car; Jan, Kudlacek (szerk.) International Conference on Innovative Technologies: IN-TECH 2017, Faculty of Engineering University of Rijeka, (2017) pp. 161-164. , 4 p.

 

[31] M, Takács; B, Verő; I, Mészáros: Micromilling of Metallic Materials, JOURNAL OF MATERIALS PROCESSING TECHNOLOGY 138 pp. 152-155. , 4 p. (2003)

 

[32] Takács, M ; Verő, B: Material Structural Aspects of Micro-Scale Chip Removal, MATERIALS SCIENCE FORUM 414-415 pp. 337-342. , 6 p. (2003)

 

[33] Biró, István ; Szalay, Tibor ; Geier, Norbert: Effect of cutting parameters on section-borders of the empirical specific cutting force model for cutting with micro-sized uncut chip thickness, In: Bachrathy, Dániel; Stépán, Gábor (szerk.) 8th CIRP Conference on High Performance Cutting : HPC 2018, Budapest, Magyarország : BME Műszaki Mechanikai Tanszék, (2018) Paper: 66 , 4 p.

 

[34] Biró István ; Szalay, Tibor: Extension of empirical specific cutting force model for the process of fine chipremoving milling, INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 88 : 9 pp. 2735-2743. , 9 p. (2017)

 

[35] J C, Jáuregui ; J R, Reséndiz ; S, Thenozhi ; T, Szalay ; Á, Jacsó ; M, Takács: Frequency and Time-Frequency Analysis of Cutting Force and Vibration Signals for Tool Condition Monitoring, IEEE ACCESS 6 pp. 6400-6410. , 11 p. (2018)

 

[36] Patra, K ; Jha, AK ; Szalay, T ; Ranjan, J ; Monostori, L: Artificial neural network based tool condition monitoring in micro mechanical peck drilling using thrust force signals, PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY 48 pp. 279-291. , 13 p. (2017)

 

[37] Patra, Karali ; Jha, Amit ; Szalay, Tibor: Tool condition monitoring in micro-drilling using vibration signals and artificial neural network: TCM in micro-drilling using vibration signals, In: Radionov, A A (szerk.) International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM), Saint Petersburg, Oroszország : IEEE, (2017) Paper: 8076196 , 5 p.

 

[38] Norbert, Geier ; György, Póka ; Tibor, Szalay: Direct monitoring of hole damage in carbon fibre-reinforced polymer (CFRP) composites, IOP CONFERENCE SERIES: MATERIALS SCIENCE AND ENGINEERING 448 : 1 pp. 1-7. , 7 p. (2018)

 

Pojdi na vsebino