Alexander Bott, Robin Stöbel, Gregor Osen, Jürgen Fleischer
For a comprehensive optimization and control of production processes, cyber-physical systems are necessary to include machines' time-dependent properties. These wear effects in machine tools, especially the feed axes, can significantly influence the process quality and are a steady research focus. However, the interaction of wear effects between different feed axes has received little attention. Especially models that represent the combined wear influence of different interacting feed axes on the control parameters and machine dynamics hold great potential. To close this knowledge gap, this paper proposes a cyber-physical test environment to identify the interaction of wear effects in feed axes. For this test environment, the relevant boundary conditions of different feed axes in machine tools and their systematic interaction are presented. Through these conditions, a physical test setup is derived and, analogous to this, a virtual model is created. This holistic approach represents the physical and virtual interaction between different components.
{"title":"Cyber-Physical Test Environment for the Identification of Interacting Wear Effects in Feed Axes","authors":"Alexander Bott, Robin Stöbel, Gregor Osen, Jürgen Fleischer","doi":"10.36897/jme/162266","DOIUrl":"https://doi.org/10.36897/jme/162266","url":null,"abstract":"For a comprehensive optimization and control of production processes, cyber-physical systems are necessary to include machines' time-dependent properties. These wear effects in machine tools, especially the feed axes, can significantly influence the process quality and are a steady research focus. However, the interaction of wear effects between different feed axes has received little attention. Especially models that represent the combined wear influence of different interacting feed axes on the control parameters and machine dynamics hold great potential. To close this knowledge gap, this paper proposes a cyber-physical test environment to identify the interaction of wear effects in feed axes. For this test environment, the relevant boundary conditions of different feed axes in machine tools and their systematic interaction are presented. Through these conditions, a physical test setup is derived and, analogous to this, a virtual model is created. This holistic approach represents the physical and virtual interaction between different components.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47416932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Moehring, Clemens Maucher, D. Becker, T. Stehlé, R. Eisseler
In recent years, metal additive manufacturing developed intensively and became a relevant technology in industrial production of highly complex and function integrated parts. However, almost all additively manufactured parts must be post-processed in order to fulfil geometric tolerances, surface quality demands and the desired functional properties. Thus, additive manufacturing actually means the implementation of additive-subtractive process chains. Starting with the most relevant additive processes (powder-based PBF-LB, LMD-p and wire-based WAAM and LMD-w/WLAM), considering intermediate process steps (heat treatment and shot peening) and ending up with post-processing material removal processes (with defined and undefined cutting edges), this paper gives an overview of recent research findings with respect to a comprehensive scientific investigation of influences and interactions within the additive-subtractive process chain. This includes both the macroscopic geometric scale and the microscopic scale of the material structure. Finally, conclusions and future perspectives are derived and discussed.
{"title":"The Additive-Subtractive Process Chain - a Review","authors":"H. Moehring, Clemens Maucher, D. Becker, T. Stehlé, R. Eisseler","doi":"10.36897/jme/162041","DOIUrl":"https://doi.org/10.36897/jme/162041","url":null,"abstract":"In recent years, metal additive manufacturing developed intensively and became a relevant technology in industrial production of highly complex and function integrated parts. However, almost all additively manufactured parts must be post-processed in order to fulfil geometric tolerances, surface quality demands and the desired functional properties. Thus, additive manufacturing actually means the implementation of additive-subtractive process chains. Starting with the most relevant additive processes (powder-based PBF-LB, LMD-p and wire-based WAAM and LMD-w/WLAM), considering intermediate process steps (heat treatment and shot peening) and ending up with post-processing material removal processes (with defined and undefined cutting edges), this paper gives an overview of recent research findings with respect to a comprehensive scientific investigation of influences and interactions within the additive-subtractive process chain. This includes both the macroscopic geometric scale and the microscopic scale of the material structure. Finally, conclusions and future perspectives are derived and discussed.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69778316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
An experimental process to build the models of surface roughness and tool wear in the finish milling of the Gleason circular bevel gears was carried out in this study. The experiments were conducted according to a Box-Behnken matrix. Three cutting parameters were adjusted in each experiment including cutting speed, feed rate, and depth of cut. From the experimental results, the influences of cutting parameters on the surface roughness and tool wear were analysed in detail. Two models of surface roughness and tool wear were established with high accuracy. The optimal values of the cutting parameters were also determined to simultaneously ensure the minimum values of two output parameters. The further research directions were also suggested at the end of this study.
{"title":"Modeling of Surface Roughness and Tool Wear when Finishing Milling Process of the Circular Bevel Gear","authors":"D. Pham, T. Hoang","doi":"10.36897/jme/161927","DOIUrl":"https://doi.org/10.36897/jme/161927","url":null,"abstract":"An experimental process to build the models of surface roughness and tool wear in the finish milling of the Gleason circular bevel gears was carried out in this study. The experiments were conducted according to a Box-Behnken matrix. Three cutting parameters were adjusted in each experiment including cutting speed, feed rate, and depth of cut. From the experimental results, the influences of cutting parameters on the surface roughness and tool wear were analysed in detail. Two models of surface roughness and tool wear were established with high accuracy. The optimal values of the cutting parameters were also determined to simultaneously ensure the minimum values of two output parameters. The further research directions were also suggested at the end of this study.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41713153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The paper presents the transformations taking place in length and angle metrology related to Metrology 4.0, a measurement strategy resulting from Industry 4.0. Metrology in an industrial conditions is gradually focusing more and more on advanced measurement systems. The coming reality will see the development of communication between systems and their components, as well as the individual sensors belonging to them. The Internet of Things and artificial intelligence as well as the possibility of using augmented or virtual reality will play a momentous role. The demand for these technologies results in the development of new specialized software and hardware solutions, the use and availability of which are diametrically different compared to the past. Also, the use of AI and cybersecurity in metrology is a topic that is receiving increasing attention. Metrology 4.0 is therefore becoming a very important part of the functioning of industry, changing the philosophy and organization of measurements carried out on the basis of new measurement techniques.
{"title":"Towards Metrology 4.0 in Dimensional Measurements","authors":"M. Wieczorowski, J. Trojanowska","doi":"10.36897/jme/161717","DOIUrl":"https://doi.org/10.36897/jme/161717","url":null,"abstract":"The paper presents the transformations taking place in length and angle metrology related to Metrology 4.0, a measurement strategy resulting from Industry 4.0. Metrology in an industrial conditions is gradually focusing more and more on advanced measurement systems. The coming reality will see the development of communication between systems and their components, as well as the individual sensors belonging to them. The Internet of Things and artificial intelligence as well as the possibility of using augmented or virtual reality will play a momentous role. The demand for these technologies results in the development of new specialized software and hardware solutions, the use and availability of which are diametrically different compared to the past. Also, the use of AI and cybersecurity in metrology is a topic that is receiving increasing attention. Metrology 4.0 is therefore becoming a very important part of the functioning of industry, changing the philosophy and organization of measurements carried out on the basis of new measurement techniques.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44347076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
All mechanical systems behave nonlinearly to a certain extent since there are always reasons for nonlinearities, such as friction and slip effects, in the actual structures. It is important to detect and identify the nonlinearity due to friction and contact in order to investigate their effect on the global behavior of the workpiece-fixture system. That is a prerequisite for modeling the dynamic contact behavior at the interface between the workpiece and clamping elements. In this research, the workpiece-fixture system was excited with a shaker using the swept sine signal. The nonlinearities could be detected by comparing and analyzing the frequency responses of the structures in Bode plots. However, the nonlinearities behaved differently at various frequencies within the observation range. Different mechanisms such as nonlinear stiffness and damping, micro-slip friction, are responsible for that. Then the nonlinear contact behavior at the clamping positions was successfully identified by means of the Hilbert transform. In addition, the clamping force directly influenced the nonlinear stiffness of the workpiece-fixture system.
{"title":"Detection and Identification of Nonlinear Contact Dynamics at Workpiece Clamping Positions","authors":"Qi Feng, W. Maier, Steffen Braun, H. Möhring","doi":"10.36897/jme/161718","DOIUrl":"https://doi.org/10.36897/jme/161718","url":null,"abstract":"All mechanical systems behave nonlinearly to a certain extent since there are always reasons for nonlinearities, such as friction and slip effects, in the actual structures. It is important to detect and identify the nonlinearity due to friction and contact in order to investigate their effect on the global behavior of the workpiece-fixture system. That is a prerequisite for modeling the dynamic contact behavior at the interface between the workpiece and clamping elements. In this research, the workpiece-fixture system was excited with a shaker using the swept sine signal. The nonlinearities could be detected by comparing and analyzing the frequency responses of the structures in Bode plots. However, the nonlinearities behaved differently at various frequencies within the observation range. Different mechanisms such as nonlinear stiffness and damping, micro-slip friction, are responsible for that. Then the nonlinear contact behavior at the clamping positions was successfully identified by means of the Hilbert transform. In addition, the clamping force directly influenced the nonlinear stiffness of the workpiece-fixture system.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49603695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the current investigation, two primary indicators, including the average roughness (AR) and Brinell hardness (BH) of the roller burnishing operation are enhanced using the optimal inputs (the spindle speed-S, feed rate-f, and depth of penetration-D). The performance measures are developed using the Kriging approach and optimal outcomes are generated by the Crow Search Algorithm (CSA). The optimal outcomes generated by the CSA of the S, f, and D were 832 rpm, 112 mm/min, and 0.12 mm, while the AR was reduced by 37.0% and the BH was increased by 29.9%, respectively. The optimal findings could be utilized in the practice for enhancing the burnished quality and to develop a professional system related to the roller burnishing operation. The Kriging-based AR and BH correlations could be used to present nonlinear experimental data. The optimizing technique could be utilized to deal with optimizing problems for different machining operations.
在目前的研究中，两个主要指标，包括平均粗糙度(AR)和布氏硬度(BH)辊抛光操作使用最佳输入(主轴速度s，进给速度f，和穿透深度d)得到提高。使用克里格方法开发性能度量，并通过乌鸦搜索算法(CSA)生成最佳结果。S、f和D的最佳CSA值分别为832 rpm、112 mm/min和0.12 mm, AR和BH分别降低了37.0%和29.9%。优化结果可用于提高滚轮抛光质量的实践，并可开发与滚轮抛光操作相关的专业系统。基于kriging的AR和BH相关可以用来表示非线性实验数据。该优化技术可用于解决不同加工工序的优化问题。
{"title":"Performance optimization of multi-roller flat burnishing process in terms of surface properties","authors":"Minh-Thai Le, A. Văn, T. Nguyen","doi":"10.36897/jme/161661","DOIUrl":"https://doi.org/10.36897/jme/161661","url":null,"abstract":"In the current investigation, two primary indicators, including the average roughness (AR) and Brinell hardness (BH) of the roller burnishing operation are enhanced using the optimal inputs (the spindle speed-S, feed rate-f, and depth of penetration-D). The performance measures are developed using the Kriging approach and optimal outcomes are generated by the Crow Search Algorithm (CSA). The optimal outcomes generated by the CSA of the S, f, and D were 832 rpm, 112 mm/min, and 0.12 mm, while the AR was reduced by 37.0% and the BH was increased by 29.9%, respectively. The optimal findings could be utilized in the practice for enhancing the burnished quality and to develop a professional system related to the roller burnishing operation. The Kriging-based AR and BH correlations could be used to present nonlinear experimental data. The optimizing technique could be utilized to deal with optimizing problems for different machining operations.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49003029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Robin Ströbel, Yannik Probst, Louisa Hutt, Jürgen Fleischer
Advancing climate change, tense world markets, and political pressure steadily increase the demand for resource-optimized production solutions. Herby, the positioning of the raw material in the machine tool is an important factor that has received little attention. Traditionally, this is done centrally on the machine table, which leads to locally increased wear of the feed axis. Furthermore, positioning directly influences energy consumption during machining. Consequently, the longest possible component utilization through optimum wear and energy optimization creates a direct conflict of objectives. To solve this conflict, this paper presents an automated approach for software-defined workpiece positioning and NC-Code optimization regarding the axis-specific energy consumption and the spindle condition of ball screws. An approach for mapping the energy consumption and the directly measured spindle condition is presented. Both represent input variables of the cost function. Approaches for the optimization of the position as well as for the practical implementation are proposed.
{"title":"Software-Defined Workpiece Positioning for Resource-Optimized Machine Tool Utilization","authors":"Robin Ströbel, Yannik Probst, Louisa Hutt, Jürgen Fleischer","doi":"10.36897/jme/161660","DOIUrl":"https://doi.org/10.36897/jme/161660","url":null,"abstract":"Advancing climate change, tense world markets, and political pressure steadily increase the demand for resource-optimized production solutions. Herby, the positioning of the raw material in the machine tool is an important factor that has received little attention. Traditionally, this is done centrally on the machine table, which leads to locally increased wear of the feed axis. Furthermore, positioning directly influences energy consumption during machining. Consequently, the longest possible component utilization through optimum wear and energy optimization creates a direct conflict of objectives. To solve this conflict, this paper presents an automated approach for software-defined workpiece positioning and NC-Code optimization regarding the axis-specific energy consumption and the spindle condition of ball screws. An approach for mapping the energy consumption and the directly measured spindle condition is presented. Both represent input variables of the cost function. Approaches for the optimization of the position as well as for the practical implementation are proposed.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48963925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
C. Ramsauer, David Leitner, C. Habersohn, T. Schmitz, K. Yamazaki, F. Bleicher
Variation in cutting forces with cutting parameter selection, tool geometry, and wear status plays an important role for milling process evaluation and modeling. While piezoelectric force measurement is commercially available, it is often considered a precise but expensive method. This paper presents a novel solution for vector-valued cutting force measurement. The table-mounted, flexure-based kinematics provide three degrees of freedom that are used to measure the in-process milling force vector components in the working plane by low-cost optical sensors. Based on analytical models and FEM analysis, an appropriate design was derived. The assembly and testing of the developed dynamometer are presented. A test setup based on a machining center was used for the system evaluation and the data are compared to the forces measured by a commercially available, piezoelectric cutting force dynamometer.
{"title":"Flexure-based dynamometer for vector-valued milling force measurement","authors":"C. Ramsauer, David Leitner, C. Habersohn, T. Schmitz, K. Yamazaki, F. Bleicher","doi":"10.36897/jme/161234","DOIUrl":"https://doi.org/10.36897/jme/161234","url":null,"abstract":"Variation in cutting forces with cutting parameter selection, tool geometry, and wear status plays an important role for milling process evaluation and modeling. While piezoelectric force measurement is commercially available, it is often considered a precise but expensive method. This paper presents a novel solution for vector-valued cutting force measurement. The table-mounted, flexure-based kinematics provide three degrees of freedom that are used to measure the in-process milling force vector components in the working plane by low-cost optical sensors. Based on analytical models and FEM analysis, an appropriate design was derived. The assembly and testing of the developed dynamometer are presented. A test setup based on a machining center was used for the system evaluation and the data are compared to the forces measured by a commercially available, piezoelectric cutting force dynamometer.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46124025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This work provided a new chemical-mechanical polishing mixture with MgO, sodium metasilicate pentahydrate, ZrO 2 abrasive particles, and deionized water. With chemical-mechanical slurry (CMS) proposed for polishing yttrium aluminum oxide (Y 3 Al 5 O 12 ) the surface reaction layer formed with significantly reduced hardness compared to other Y 3 Al 5 O 12 materials, these products combine with MgO to form montmorillonites (3MgO–Al 2 O 3 –3SiO 2 –3Y 2 O 3 – 5Al 2 O 3 ). With this formation, the surface layer of Y 3 Al 5 O 12 material becomes soft and is easily removed by ZrO 2 abrasive particles under the influence of mechanical polishing, resulting in superfine surfaces generated from the proposed CMS model. The experimental results show that the surface quality with CMS proposed gives the surface quality with Ra = 0.471 nm along with the material removal rate 31 (nm/min). Surface quality is improved by 71% along with a superior material removal rate (increased by 287%) compared to silica slurry. The results show excellent polishing ability from CMS proposed for polishing Y3Al5O12 materials.
本工作提供了一种新的化学机械抛光混合物，其中含有MgO、五水偏硅酸钠、ZrO2磨料颗粒和去离子水。采用化学机械浆料（CMS）抛光钇铝氧化物（Y 3 Al 5 O 12），与其他Y 3 Al 2 O 12材料相比，形成的表面反应层硬度显著降低，这些产物与MgO结合形成蒙脱石（3MgO–Al 2 O 3–3SiO 2–3Y 2 O 3-5Al 2 O 3）。通过这种形成，Y3Al5O12材料的表面层变得柔软，并且在机械抛光的影响下很容易被ZrO2磨粒去除，从而产生由所提出的CMS模型产生的超细表面。实验结果表明，所提出的CMS的表面质量给出了Ra=0.471nm的表面质量以及31（nm/min）的材料去除率。与二氧化硅浆料相比，表面质量提高了71%，材料去除率更高（提高了287%）。结果表明，CMS对Y3Al5O12材料具有良好的抛光性能。
{"title":"A New Chemical Mechanical Slurry for Polishing Yttrium Aluminium Garnet Material with Magnesium oxide, Sodium Metasilicate Pentahydrate and Zirconium Dioxide Abrasive Particles","authors":"LeManh Duc, P. Hiếu, N. Quang","doi":"10.36897/jme/159661","DOIUrl":"https://doi.org/10.36897/jme/159661","url":null,"abstract":"This work provided a new chemical-mechanical polishing mixture with MgO, sodium metasilicate pentahydrate, ZrO 2 abrasive particles, and deionized water. With chemical-mechanical slurry (CMS) proposed for polishing yttrium aluminum oxide (Y 3 Al 5 O 12 ) the surface reaction layer formed with significantly reduced hardness compared to other Y 3 Al 5 O 12 materials, these products combine with MgO to form montmorillonites (3MgO–Al 2 O 3 –3SiO 2 –3Y 2 O 3 – 5Al 2 O 3 ). With this formation, the surface layer of Y 3 Al 5 O 12 material becomes soft and is easily removed by ZrO 2 abrasive particles under the influence of mechanical polishing, resulting in superfine surfaces generated from the proposed CMS model. The experimental results show that the surface quality with CMS proposed gives the surface quality with Ra = 0.471 nm along with the material removal rate 31 (nm/min). Surface quality is improved by 71% along with a superior material removal rate (increased by 287%) compared to silica slurry. The results show excellent polishing ability from CMS proposed for polishing Y3Al5O12 materials.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49365487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anh-Tu Nguyen, Van-Hai Nguyen, Tien-Thinh Le, N. Nguyen
This work focuses on optimizing process parameters in turning AISI 4340 alloy steel. A hybridization of Machine Learning (ML) algorithms and a Non-Dominated Sorting Genetic Algorithm (NSGA-II) is applied to find the Pareto solution. The objective functions are a simultaneous minimum of average surface roughness (Ra) and cutting force under the cutting parameter constraints of cutting speed, feed rate, depth of cut, and tool nose radius in a range of 50–375 m/min, 0.02–0.25 mm/rev, 0.1–1.5 mm, and 0.4–0.8 mm, respectively. The present study uses five ML models – namely SVR, CAT, RFR, GBR, and ANN – to predict Ra and cutting force. Results indicate that ANN offers the best predictive performance in respect of all accuracy metrics: root-mean-squared-error (RMSE), mean-absolute-error (MAE), and coefficient of determination ( R 2 ). In addition, a hybridization of NSGA-II and ANN is implemented to find the optimal solutions for machining parameters, which lie on the Pareto front. The results of this multi-objective optimization indicate that Ra lies in a range between 1.032 and 1.048 µm, and cutting force was found to range between 7.981 and 8.277 kgf for the five selected Pareto solutions. In the set of non-dominated keys, none of the individual solutions is superior to any of the others, so it is the manufacturer's decision which dataset to select. Results summarize the value range in the Pareto solutions generated by NSGA-II: cutting speeds between 72.92 and 75.11 m/min, a feed rate of 0.02 mm/rev, a depth of cut between 0.62 and 0.79 mm, and a tool nose radius of 0.4 mm, are recommended. Following that, experimental validations were finally conducted to verify the optimization procedure.
{"title":"A Hybridization of Machine Learning and NSGA-II for Multi-Objective Optimization of Surface Roughness and Cutting Force in ANSI 4340 Alloy Steel Turning","authors":"Anh-Tu Nguyen, Van-Hai Nguyen, Tien-Thinh Le, N. Nguyen","doi":"10.36897/jme/160172","DOIUrl":"https://doi.org/10.36897/jme/160172","url":null,"abstract":"This work focuses on optimizing process parameters in turning AISI 4340 alloy steel. A hybridization of Machine Learning (ML) algorithms and a Non-Dominated Sorting Genetic Algorithm (NSGA-II) is applied to find the Pareto solution. The objective functions are a simultaneous minimum of average surface roughness (Ra) and cutting force under the cutting parameter constraints of cutting speed, feed rate, depth of cut, and tool nose radius in a range of 50–375 m/min, 0.02–0.25 mm/rev, 0.1–1.5 mm, and 0.4–0.8 mm, respectively. The present study uses five ML models – namely SVR, CAT, RFR, GBR, and ANN – to predict Ra and cutting force. Results indicate that ANN offers the best predictive performance in respect of all accuracy metrics: root-mean-squared-error (RMSE), mean-absolute-error (MAE), and coefficient of determination ( R 2 ). In addition, a hybridization of NSGA-II and ANN is implemented to find the optimal solutions for machining parameters, which lie on the Pareto front. The results of this multi-objective optimization indicate that Ra lies in a range between 1.032 and 1.048 µm, and cutting force was found to range between 7.981 and 8.277 kgf for the five selected Pareto solutions. In the set of non-dominated keys, none of the individual solutions is superior to any of the others, so it is the manufacturer's decision which dataset to select. Results summarize the value range in the Pareto solutions generated by NSGA-II: cutting speeds between 72.92 and 75.11 m/min, a feed rate of 0.02 mm/rev, a depth of cut between 0.62 and 0.79 mm, and a tool nose radius of 0.4 mm, are recommended. Following that, experimental validations were finally conducted to verify the optimization procedure.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46827989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：