Fabio C. Zegarra, Juan Vargas-Machuca, Alberto M. Coronado
Accurately predicting machine tool wear requires models capable of capturing complex, nonlinear interactions in multivariate time series inputs. Recurrent neural networks (RNNs) are well-suited to this task, owing to their memory mechanisms and capacity to construct highly complex models. In particular, LSTM, BiLSTM, and GRU architectures have shown promise in wear prediction. This study demonstrates that RNNs can automatically extract relevant information from time series data, resulting in highly precise wear models with minimal feature engineering. Notably, this approach avoids the need for excessively large window sizes of data points during model training, which would increase model complexity and processing time. Instead, this study proposes a procedure that achieves low prediction errors with window sizes as small as 100 data points. By employing Bayesian hyperparameter optimization and two preprocessing techniques (detrend and offset), RMSE errors consistently fall below 10. A key difference in this study is the use of boxplots to provide a better representation of result variability, as opposed to solely reporting the best values. The proposed approach matches more complex state-of-the-art methods and offers a powerful tool for wear prediction in engineering applications.
1. 陈建军，陈建军，2013，制造工程与技术，普伦斯霍尔国际，皮尔森/普伦斯霍尔。谷歌学者
{"title":"A Comparative Study of CNN, LSTM, BiLSTM, and GRU Architectures for Tool Wear Prediction in Milling Processes","authors":"Fabio C. Zegarra, Juan Vargas-Machuca, Alberto M. Coronado","doi":"10.36897/jme/174019","DOIUrl":"https://doi.org/10.36897/jme/174019","url":null,"abstract":"Accurately predicting machine tool wear requires models capable of capturing complex, nonlinear interactions in multivariate time series inputs. Recurrent neural networks (RNNs) are well-suited to this task, owing to their memory mechanisms and capacity to construct highly complex models. In particular, LSTM, BiLSTM, and GRU architectures have shown promise in wear prediction. This study demonstrates that RNNs can automatically extract relevant information from time series data, resulting in highly precise wear models with minimal feature engineering. Notably, this approach avoids the need for excessively large window sizes of data points during model training, which would increase model complexity and processing time. Instead, this study proposes a procedure that achieves low prediction errors with window sizes as small as 100 data points. By employing Bayesian hyperparameter optimization and two preprocessing techniques (detrend and offset), RMSE errors consistently fall below 10. A key difference in this study is the use of boxplots to provide a better representation of result variability, as opposed to solely reporting the best values. The proposed approach matches more complex state-of-the-art methods and offers a powerful tool for wear prediction in engineering applications.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135884591","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}
Arash Ebrahimi Araghizad, Faraz Tehranizadeh, Kemal Kilic, Erhan Budak
1. BUDAK E., ALTINTAS Y., ARMAREGO E.J.A., 1996, Prediction of Milling Force Coefficients from Orthogonal Cutting Data, J. Manuf. Sci. Eng., 118/2, 216–224, https://doi.org/10.1115/1.2831.... CrossRef Google Scholar
1.BUDAK E., ALTINTAS Y., ARMAREGO E.J.A., 1996, Prediction of Milling Force Coefficients from Orthogonal Cutting Data, J. Manuf. Sci. Eng., 118/2, 216-224, https://doi.org/10.1115/1.2831....CrossRef Google Scholar
{"title":"Smart Tool-Related Faults Monitoring System Using Process Simulation-Based Machine Learning Algorithms","authors":"Arash Ebrahimi Araghizad, Faraz Tehranizadeh, Kemal Kilic, Erhan Budak","doi":"10.36897/jme/174018","DOIUrl":"https://doi.org/10.36897/jme/174018","url":null,"abstract":"1. BUDAK E., ALTINTAS Y., ARMAREGO E.J.A., 1996, Prediction of Milling Force Coefficients from Orthogonal Cutting Data, J. Manuf. Sci. Eng., 118/2, 216–224, https://doi.org/10.1115/1.2831.... CrossRef Google Scholar","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135944493","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}
1. DESSOLY V., MELKOTE S.N., LESCALIER C. 2004, Modeling and Verification of Cutting Tool Temperatures in Rotary Tool Turning of Hardened Steel, Int. J. Mach. Tools Manuf., 44, 1463–1470. Google Scholar
{"title":"Multi-Objective Optimization of the Rotary Turning of Hardened Mold Steel for Energy Saving and Surface Roughness Improvements","authors":"Tat Khoa Doan, Trung Thanh Nguyen, An-Le Van","doi":"10.36897/jme/172877","DOIUrl":"https://doi.org/10.36897/jme/172877","url":null,"abstract":"1. DESSOLY V., MELKOTE S.N., LESCALIER C. 2004, Modeling and Verification of Cutting Tool Temperatures in Rotary Tool Turning of Hardened Steel, Int. J. Mach. Tools Manuf., 44, 1463–1470. Google Scholar","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135477061","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}
Vidosav D. Majstorovic, Vojin Vukadinovic, Jovan Zivkovic
1. KUSIAK A., 2018, Smart Manufacturing, International Journal of Production Research, 56/1–2, 508–517, https://doi.org/10.1080/002075.... CrossRef Google Scholar
{"title":"Towards the Digital Model of Tool Lifecycle Management in Sheet Metal Forming","authors":"Vidosav D. Majstorovic, Vojin Vukadinovic, Jovan Zivkovic","doi":"10.36897/jme/171664","DOIUrl":"https://doi.org/10.36897/jme/171664","url":null,"abstract":"1. KUSIAK A., 2018, Smart Manufacturing, International Journal of Production Research, 56/1–2, 508–517, https://doi.org/10.1080/002075.... CrossRef Google Scholar","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135437870","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}
Eddi Miller, Jan Schmitt, Tobias Kaupp, Bastian Engelmann
In today’s manufacturing systems, especially in Industry 4.0, highly autonomous production cells play an important role. To reach this goal of autonomy, different technologies like industrial robots, machine tools, and automated guided vehicles (AGV) are deployed simultaneously which creates numerous challenges on various automation levels. One of those challenges regards the scheduling of all applied resources and their corresponding tasks. Combining data from a real production environment and Constraint Programming (CP-SAT), we provide a cascaded scheduling approach that plans production orders for machine tools to minimize makespan and tool changeover time while enabling the corresponding robot for robot-collaborated processes. Simultaneously, AGVs provide all production cells with the necessary material and tools. Hereby, magazine capacity for raw material as well as finished parts and tool service life are taken into account.
{"title":"Advanced Cascaded Scheduling for Highly Autonomous Production Cells with Material Flow and Tool Lifetime Consideration using AGVs","authors":"Eddi Miller, Jan Schmitt, Tobias Kaupp, Bastian Engelmann","doi":"10.36897/jme/171749","DOIUrl":"https://doi.org/10.36897/jme/171749","url":null,"abstract":"In today’s manufacturing systems, especially in Industry 4.0, highly autonomous production cells play an important role. To reach this goal of autonomy, different technologies like industrial robots, machine tools, and automated guided vehicles (AGV) are deployed simultaneously which creates numerous challenges on various automation levels. One of those challenges regards the scheduling of all applied resources and their corresponding tasks. Combining data from a real production environment and Constraint Programming (CP-SAT), we provide a cascaded scheduling approach that plans production orders for machine tools to minimize makespan and tool changeover time while enabling the corresponding robot for robot-collaborated processes. Simultaneously, AGVs provide all production cells with the necessary material and tools. Hereby, magazine capacity for raw material as well as finished parts and tool service life are taken into account.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49025485","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}
Machine tools are the main driver of economic, environmental and social sustainability in industrial production. The ongoing shift from mass production to highly individualized, small batch manufacturing requires machine tools to be more flexible to changing needs while maintaining at least the same level of productivity. However, flexibility and productivity are at odds with the necessity for resource and energy efficiency. At the same time, more sophisticated workpiece specifications are pushing the boundaries regarding precision and dynamics of machine tools. In such a high-performance context, machine safety plays a major role and is becoming increasingly challenging due to higher kinetic energies of moving components. This paper examines recent advances in machine tool precision, sustainability, and safety. Six comprehensive case studies are provided to illustrate how these improvements contribute to an increased productivity. Hardware and software solutions for pose-controlled robotic manufacturing and thermoelectrically tempered high-performance spindles will be presented. Modular machine tool frames based on building blocks and an adaptive cooling system with thermoelectric generators for linear direct drives demonstrate their major impact on resource and energy efficiency. Machine safety is addressed through an analysis of potential hazards as well as improved protective measures. Model-based predictions precisely identify critical process parameters that lead to unbalance-induced failure of slim tool extensions, while on the protection side, new statistical models are applied to assess the protective performance of safeguards much more accurately. The cutting-edge technologies for machine tools presented in this paper will help manufacturers to cope with current and future challenges in industrial production.
{"title":"Recent Advances in Precision, Sustainability and Safety of Machine Tools","authors":"Uhlmann Eckart","doi":"10.36897/jme/169941","DOIUrl":"https://doi.org/10.36897/jme/169941","url":null,"abstract":"Machine tools are the main driver of economic, environmental and social sustainability in industrial production. The ongoing shift from mass production to highly individualized, small batch manufacturing requires machine tools to be more flexible to changing needs while maintaining at least the same level of productivity. However, flexibility and productivity are at odds with the necessity for resource and energy efficiency. At the same time, more sophisticated workpiece specifications are pushing the boundaries regarding precision and dynamics of machine tools. In such a high-performance context, machine safety plays a major role and is becoming increasingly challenging due to higher kinetic energies of moving components. This paper examines recent advances in machine tool precision, sustainability, and safety. Six comprehensive case studies are provided to illustrate how these improvements contribute to an increased productivity. Hardware and software solutions for pose-controlled robotic manufacturing and thermoelectrically tempered high-performance spindles will be presented. Modular machine tool frames based on building blocks and an adaptive cooling system with thermoelectric generators for linear direct drives demonstrate their major impact on resource and energy efficiency. Machine safety is addressed through an analysis of potential hazards as well as improved protective measures. Model-based predictions precisely identify critical process parameters that lead to unbalance-induced failure of slim tool extensions, while on the protection side, new statistical models are applied to assess the protective performance of safeguards much more accurately. The cutting-edge technologies for machine tools presented in this paper will help manufacturers to cope with current and future challenges in industrial production.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47254890","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}
Fabio C. Zegarra, J. Vargas-Machuca, A. Roman-Gonzalez, A. Coronado
{"title":"Unsupervised and Supervised Machine Learning Methods for Cutting Tool Path Clustering and RUL Estimation in Manufacturing","authors":"Fabio C. Zegarra, J. Vargas-Machuca, A. Roman-Gonzalez, A. Coronado","doi":"10.36897/jme/171432","DOIUrl":"https://doi.org/10.36897/jme/171432","url":null,"abstract":"","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46534485","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}
Single-pass honing is used as a finishing process to meet high demands regarding form and dimensional accuracy of drilled holes. The disadvantages of single-pass honing compared to the conventional long-stroke honing are high process forces and torques as well as an increased risk of chip space clogging of the abrasive stones. Following this, the oscillation-superimposed single-pass honing without cutting fluid has been conducted in this work, which is promising when it comes to the environmentally friendly improvement of machining processes. It was shown that the omitted lubrication and flushing effect of the contact zone between the tool and the workpiece could be compensated with the aid of the superimposed oscillations. The process forces of the dry honing process are up to 37% lower compared to the conventional process, the height of the surface profile Rz decreases by 33% and the form deviations decrease up to 47%. Hence, the new method allows the saving of resources, while improving the work results.
{"title":"Method of the environmentally friendly dry single-pass honing with use of the superimposed low frequency oscillations","authors":"Rozek André, Uhlmann Eckart","doi":"10.36897/jme/171391","DOIUrl":"https://doi.org/10.36897/jme/171391","url":null,"abstract":"Single-pass honing is used as a finishing process to meet high demands regarding form and dimensional accuracy of drilled holes. The disadvantages of single-pass honing compared to the conventional long-stroke honing are high process forces and torques as well as an increased risk of chip space clogging of the abrasive stones. Following this, the oscillation-superimposed single-pass honing without cutting fluid has been conducted in this work, which is promising when it comes to the environmentally friendly improvement of machining processes. It was shown that the omitted lubrication and flushing effect of the contact zone between the tool and the workpiece could be compensated with the aid of the superimposed oscillations. The process forces of the dry honing process are up to 37% lower compared to the conventional process, the height of the surface profile Rz decreases by 33% and the form deviations decrease up to 47%. Hence, the new method allows the saving of resources, while improving the work results.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44559103","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 study aims to investigate the interplay between cutting speed and Thermal-Assisted Machining (TAM) concerning surface roughness during the high-speed machining of SKD11 steel. The integration of pre-cutting workpiece heating introduces a temperature factor that intricately affects surface roughness. The primary objective is to ascertain optimal speed and temperature ranges that synergistically enhance machining efficiency, curtail costs, and elevate surface quality. The experimental protocol initiates with room temperature milling of SKD11 steel, progressively elevating the temperature gradient to systematically appraise temperature's impact on surface roughness under both conventional and elevated cutting speeds. Subsequent experimentation, conducted within specific temperature thresholds, entails stepwise augmentation of cutting speed to elucidate the influence of high-speed conditions on surface roughness. The ensuing analysis meticulously examines the ramifications of distinct cutting speed intervals on surface roughness. Ultimately, the study furnishes pragmatic recommendations for judiciously selecting cutting speeds and heating temperature parameters across diverse machining scenarios.
{"title":"Surface Roughness Investigation Through Interplay of Cutting Speed and Thermal-Assisted Machining in High-Speed Machining of SKD11 Steel","authors":"Long-Vinh Bui, Thi-Bich Mac, D. Nguyen","doi":"10.36897/jme/170980","DOIUrl":"https://doi.org/10.36897/jme/170980","url":null,"abstract":"This study aims to investigate the interplay between cutting speed and Thermal-Assisted Machining (TAM) concerning surface roughness during the high-speed machining of SKD11 steel. The integration of pre-cutting workpiece heating introduces a temperature factor that intricately affects surface roughness. The primary objective is to ascertain optimal speed and temperature ranges that synergistically enhance machining efficiency, curtail costs, and elevate surface quality. The experimental protocol initiates with room temperature milling of SKD11 steel, progressively elevating the temperature gradient to systematically appraise temperature's impact on surface roughness under both conventional and elevated cutting speeds. Subsequent experimentation, conducted within specific temperature thresholds, entails stepwise augmentation of cutting speed to elucidate the influence of high-speed conditions on surface roughness. The ensuing analysis meticulously examines the ramifications of distinct cutting speed intervals on surface roughness. Ultimately, the study furnishes pragmatic recommendations for judiciously selecting cutting speeds and heating temperature parameters across diverse machining scenarios.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46608721","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}
Cuong Van Nguyen, Longji Dang, A. Le, Danh Thanh Bui
This study investigated the influence of print orientation on the mechanical properties of 17-4 PH stainless steel parts fabricated using material extrusion technology. Tensile test specimens were 3D printed in different orientations (flat, on-edge, and upright), and their mechanical properties were evaluated. The results showed that the print orientation significantly affected the ultimate tensile strength, yield strength, and elongation at failure of the specimens. The flat and on-edge orientations exhibited similar mechanical properties, while the upright orientation resulted in lower strength and higher fracture susceptibility. Hardness measurements also indicated variations in hardness distribution among the orientations. The findings emphasize the importance of optimizing the print orientation parameter to achieve desired mechanical characteristics in 17-4 PH stainless steel parts.
{"title":"A Study on the Influence of Printing Orientation in Metal Printing Using Material Extrusion Technology on the Mechanical Properties of 17-4 Stainless Steel Products","authors":"Cuong Van Nguyen, Longji Dang, A. Le, Danh Thanh Bui","doi":"10.36897/jme/170509","DOIUrl":"https://doi.org/10.36897/jme/170509","url":null,"abstract":"This study investigated the influence of print orientation on the mechanical properties of 17-4 PH stainless steel parts fabricated using material extrusion technology. Tensile test specimens were 3D printed in different orientations (flat, on-edge, and upright), and their mechanical properties were evaluated. The results showed that the print orientation significantly affected the ultimate tensile strength, yield strength, and elongation at failure of the specimens. The flat and on-edge orientations exhibited similar mechanical properties, while the upright orientation resulted in lower strength and higher fracture susceptibility. Hardness measurements also indicated variations in hardness distribution among the orientations. The findings emphasize the importance of optimizing the print orientation parameter to achieve desired mechanical characteristics in 17-4 PH stainless steel parts.","PeriodicalId":37821,"journal":{"name":"Journal of Machine Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41791815","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：