Michael Biehler, Reinaldo Mock, Shriyanshu Kode, Maham Mehmood, Palin Bhardwaj, Jianjun Shi
Abstract Additive manufacturing (AM) has revolutionized the way we design, prototype, and produce complex parts with unprecedented geometries. However, the lack of understanding of the functional properties of 3D printed parts has hindered their adoption in critical applications where reliability and durability are paramount. This paper proposes a novel approach to the functional qualification of 3D-printed parts via physical and digital twins. Physical twins are parts that are printed under the same process conditions as the functional parts and undergo a wide range of (destructive) tests to determine their mechanical, thermal, and chemical properties. Digital twins are virtual replicas of the physical twins that are generated using finite element analysis (FEA) simulations based on the 3D shape of the part of interest. We propose a novel approach to transfer learning, specifically designed for the fusion of diverse, unstructured 3D shape data and process inputs from multiple sources. The proposed approach has demonstrated remarkable results in predicting the functional properties of 3D-printed lattice structures. From an engineering standpoint, this paper introduces a comprehensive and innovative methodology for the functional qualification of 3D-printed parts. By combining the strengths of physical and digital twins with transfer learning, our approach opens up possibilities for the widespread adoption of 3D printing in safety-critical applications. Methodologically, this work presents a significant advancement in transfer learning techniques, specifically addressing the challenges of multi-source (e.g., digital and physical twins) and multi-input (e.g., 3D shapes and process variables) transfer learning.
{"title":"AUDIT: Function<u>a</u>l Q<u>u</u>alification in A<u>d</u>ditive Manufacturing via Physical and Dig<u>i</u>tal <u>T</u>wins","authors":"Michael Biehler, Reinaldo Mock, Shriyanshu Kode, Maham Mehmood, Palin Bhardwaj, Jianjun Shi","doi":"10.1115/1.4063655","DOIUrl":"https://doi.org/10.1115/1.4063655","url":null,"abstract":"Abstract Additive manufacturing (AM) has revolutionized the way we design, prototype, and produce complex parts with unprecedented geometries. However, the lack of understanding of the functional properties of 3D printed parts has hindered their adoption in critical applications where reliability and durability are paramount. This paper proposes a novel approach to the functional qualification of 3D-printed parts via physical and digital twins. Physical twins are parts that are printed under the same process conditions as the functional parts and undergo a wide range of (destructive) tests to determine their mechanical, thermal, and chemical properties. Digital twins are virtual replicas of the physical twins that are generated using finite element analysis (FEA) simulations based on the 3D shape of the part of interest. We propose a novel approach to transfer learning, specifically designed for the fusion of diverse, unstructured 3D shape data and process inputs from multiple sources. The proposed approach has demonstrated remarkable results in predicting the functional properties of 3D-printed lattice structures. From an engineering standpoint, this paper introduces a comprehensive and innovative methodology for the functional qualification of 3D-printed parts. By combining the strengths of physical and digital twins with transfer learning, our approach opens up possibilities for the widespread adoption of 3D printing in safety-critical applications. Methodologically, this work presents a significant advancement in transfer learning techniques, specifically addressing the challenges of multi-source (e.g., digital and physical twins) and multi-input (e.g., 3D shapes and process variables) transfer learning.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135591937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Residual stresses have been characterized in four Wire Arc Additive Manufacturing specimens with neutron diffraction technique. Firstly, two methods are investigated for obtaining the reference diffracted angle θ0 that is required for the computation of micro-strains and, thus, the stresses. θ0 was obtained using two approaches. The first one required a strain-free specimen in order to get directly the reference diffracted angles θ0 in three directions. The second one is based on the plane stress assumption to get θ0 indirectly by imposing that the normal stress was equal to zero. Both methods led to similar residual stress profiles for the 1-layer specimen what validated this approach for all specimens that did not have a strain-free specimen available. The second part of this work focused on the effect of addition of a new layer on residual stresses. The measurements showed that the longitudinal stress was tensile in the Heat Affected Zone (HAZ) and Fusion Zone (FZ) with a maximum value located at the parent material - layers interface where the thermal loadings were applied. A decrease of this maximum value from 257 MPa to 199 MPa appeared after deposition of a new layer which is due to some stress relaxation effect. Inside the parent material, a large zone presents compressive longitudinal stress up to -170 MPa. The bottom part of the parent material is under tensile stress likely due to its upward bending following the thermal contraction of the deposited layers during cooling to ambient temperature.
{"title":"Effect of layer addition on residual stresses of wire arc additive manufactured stainless steel specimens","authors":"Sebastien Rouquette, Camille Cambon, Issam Bendaoud, Sandra Cabeza, Fabien Soulié","doi":"10.1115/1.4063446","DOIUrl":"https://doi.org/10.1115/1.4063446","url":null,"abstract":"Abstract Residual stresses have been characterized in four Wire Arc Additive Manufacturing specimens with neutron diffraction technique. Firstly, two methods are investigated for obtaining the reference diffracted angle θ0 that is required for the computation of micro-strains and, thus, the stresses. θ0 was obtained using two approaches. The first one required a strain-free specimen in order to get directly the reference diffracted angles θ0 in three directions. The second one is based on the plane stress assumption to get θ0 indirectly by imposing that the normal stress was equal to zero. Both methods led to similar residual stress profiles for the 1-layer specimen what validated this approach for all specimens that did not have a strain-free specimen available. The second part of this work focused on the effect of addition of a new layer on residual stresses. The measurements showed that the longitudinal stress was tensile in the Heat Affected Zone (HAZ) and Fusion Zone (FZ) with a maximum value located at the parent material - layers interface where the thermal loadings were applied. A decrease of this maximum value from 257 MPa to 199 MPa appeared after deposition of a new layer which is due to some stress relaxation effect. Inside the parent material, a large zone presents compressive longitudinal stress up to -170 MPa. The bottom part of the parent material is under tensile stress likely due to its upward bending following the thermal contraction of the deposited layers during cooling to ambient temperature.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","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":"135436438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Connor Quigley, Rokeya Sarah, Warren Hurd, Scott Clark, M. Habib
The field of 3D bio-printing is rapidly expanding as researchers strive to create functional tissues for medical and pharmaceutical purposes. The ability to print multiple materials, each containing various living cells, brings us closer to achieving tissue regeneration. In a previous study, we designed a Y-shaped nozzle connector system that allowed for continuous deposition of multiple materials. This system was made of plastic and had a fixed switching angle, rendering it suitable for a single use. In this paper, we present the updated version of our nozzle system, which includes a range of angles (30°, 45°, 60°, and 90° degrees) between the two materials. We used stainless steel as the fabrication material and recorded the overall material switching time, comparing the effects of the various angles. Our previously developed hybrid hydrogel, which comprised 4% Alginate and 4% Carboxymethyl Cellulose (CMC), was used as a test material to flow through the nozzle system. The in-house fabricated nozzle connectors are reusable, sterile, and easy to clean, ensuring a smooth material transition and flow.
{"title":"Design and Fabrication of In-house Nozzle System to Extrude Multi-Hydrogels for 3D Bioprinting Process","authors":"Connor Quigley, Rokeya Sarah, Warren Hurd, Scott Clark, M. Habib","doi":"10.1115/1.4063357","DOIUrl":"https://doi.org/10.1115/1.4063357","url":null,"abstract":"\u0000 The field of 3D bio-printing is rapidly expanding as researchers strive to create functional tissues for medical and pharmaceutical purposes. The ability to print multiple materials, each containing various living cells, brings us closer to achieving tissue regeneration. In a previous study, we designed a Y-shaped nozzle connector system that allowed for continuous deposition of multiple materials. This system was made of plastic and had a fixed switching angle, rendering it suitable for a single use. In this paper, we present the updated version of our nozzle system, which includes a range of angles (30°, 45°, 60°, and 90° degrees) between the two materials. We used stainless steel as the fabrication material and recorded the overall material switching time, comparing the effects of the various angles. Our previously developed hybrid hydrogel, which comprised 4% Alginate and 4% Carboxymethyl Cellulose (CMC), was used as a test material to flow through the nozzle system. The in-house fabricated nozzle connectors are reusable, sterile, and easy to clean, ensuring a smooth material transition and flow.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43434451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Saravana Sundar A, Krishna Kishore Mugada, Adepu Kumar
The present study explores the application of static shoulder friction stir welding (SSFSW) to address the challenges of poor mechanical properties in conventional Al-Ti dissimilar friction stir joints, which arise due to significant material mixing and the formation of thick intermetallic layers. The results show that SSFSW inhibited material mixing and the mutual diffusion of Al and Ti were suppressed due to lower heat input. Mutual interdiffusion of Al and Ti was directed by an exothermic chemical reaction, forming an Al5Ti2 – Al3Ti sequence due to sluggish diffusion of Al in Ti at a temperature of 512°C achieved in this study. The microstructure at stir zone (SZ) comprised equiaxed grains with Ti particles acting as dispersoids for nucleation, whereas the presence of large Ti blocks at SZ of Conventional FSW (CFSW) resisted plastic deformation, resulting in non-homogeneous concentration of dislocations near its interface. A significant decrease in grain size at all the critical zones of weldment was due to rearrangement of dislocations through slip-and-climb mechanism, as evidenced by the occurrence of dynamic recrystallization. Emergence of γ-fiber and basal fiber texture increased the tensile strength of SSFSW to 289 MPa, which is about 11.2% higher than CFSW, with joint efficiency of about 88%. The study also analysed the contribution of various strengthening mechanisms to the yield strength improvement of SSFSW weldments in detail of SSFSW weldments in detail, and the results showed that grain boundary strengthening contributed the most to strength improvement in SSFSW.
{"title":"Enhancing Microstructural, Textural, and Mechanical Properties of Al-Ti Dissimilar Joints via Static Shoulder Friction Stir Welding","authors":"Saravana Sundar A, Krishna Kishore Mugada, Adepu Kumar","doi":"10.1115/1.4063358","DOIUrl":"https://doi.org/10.1115/1.4063358","url":null,"abstract":"\u0000 The present study explores the application of static shoulder friction stir welding (SSFSW) to address the challenges of poor mechanical properties in conventional Al-Ti dissimilar friction stir joints, which arise due to significant material mixing and the formation of thick intermetallic layers. The results show that SSFSW inhibited material mixing and the mutual diffusion of Al and Ti were suppressed due to lower heat input. Mutual interdiffusion of Al and Ti was directed by an exothermic chemical reaction, forming an Al5Ti2 – Al3Ti sequence due to sluggish diffusion of Al in Ti at a temperature of 512°C achieved in this study. The microstructure at stir zone (SZ) comprised equiaxed grains with Ti particles acting as dispersoids for nucleation, whereas the presence of large Ti blocks at SZ of Conventional FSW (CFSW) resisted plastic deformation, resulting in non-homogeneous concentration of dislocations near its interface. A significant decrease in grain size at all the critical zones of weldment was due to rearrangement of dislocations through slip-and-climb mechanism, as evidenced by the occurrence of dynamic recrystallization. Emergence of γ-fiber and basal fiber texture increased the tensile strength of SSFSW to 289 MPa, which is about 11.2% higher than CFSW, with joint efficiency of about 88%. The study also analysed the contribution of various strengthening mechanisms to the yield strength improvement of SSFSW weldments in detail of SSFSW weldments in detail, and the results showed that grain boundary strengthening contributed the most to strength improvement in SSFSW.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42067640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pengjie Gao, Junliang Wang, Min Xia, Zijin Qin, Jie Zhang
As an important application of human-robot collaboration, intelligent detection of surface defects is crucial for production quality control, which also helps in relieving the workload of technical staff in human-centric smart manufacturing. To accurately detect defects with limited samples in industrial practice, a dual-metric neural network with attention guided is proposed. First, an attention-guided recognition network with channel attention and position attention module is designed to efficiently learn representative defect features with limited samples. Second, aiming to detect defects with confusing surface images, a dual-metric function is presented to learn the classification boundary by controlling the distance of samples in feature space from intra-class and inter-class. The experiment results on the fabric defect dataset demonstrate that the proposed approach outperforms state-of-the-art methods in accuracy, recall, precision, F1-score, and few-shot accuracy. Further comparative experiments reveal that the dual-metric function is superior in improving the few-shot detection accuracy for the defect patterns of fabric.
{"title":"Dual-Metric Neural Network with Attention Guidance for Surface Defect Few-Shot Detection in Smart Manufacturing","authors":"Pengjie Gao, Junliang Wang, Min Xia, Zijin Qin, Jie Zhang","doi":"10.1115/1.4063356","DOIUrl":"https://doi.org/10.1115/1.4063356","url":null,"abstract":"\u0000 As an important application of human-robot collaboration, intelligent detection of surface defects is crucial for production quality control, which also helps in relieving the workload of technical staff in human-centric smart manufacturing. To accurately detect defects with limited samples in industrial practice, a dual-metric neural network with attention guided is proposed. First, an attention-guided recognition network with channel attention and position attention module is designed to efficiently learn representative defect features with limited samples. Second, aiming to detect defects with confusing surface images, a dual-metric function is presented to learn the classification boundary by controlling the distance of samples in feature space from intra-class and inter-class. The experiment results on the fabric defect dataset demonstrate that the proposed approach outperforms state-of-the-art methods in accuracy, recall, precision, F1-score, and few-shot accuracy. Further comparative experiments reveal that the dual-metric function is superior in improving the few-shot detection accuracy for the defect patterns of fabric.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46460502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The five-axis ball-end milling dynamics of thin-walled blades is presented. The cutting forces are predicted from the ball end mill–blade geometry engagement maps along the tool path. The Frequency Response Function (FRF) of the thin-walled blade is predicted using Finite Element shell elements, and it is updated along the toolpath as the metal is removed. The predicted cutting forces are applied on both the workpiece and tool FRFs to predict the forced vibrations and chatter stability at each tool location. A simplified method to update the cutter–workpiece engagement (CWE) is used to obtain the three-dimensional stability lobe diagram at each desired point on the blade. The integrated model is used to simulate the 5-axis machining of thin-walled blades in the digital environment. The proposed digital model is experimentally validated by machining a series of thin-walled rectangular plates and a twisted fan blade.
{"title":"Virtual Dynamics Model for 5-axis Machining of Thin-Walled Blades","authors":"B. Karimi, Y. Altintas","doi":"10.1115/1.4063286","DOIUrl":"https://doi.org/10.1115/1.4063286","url":null,"abstract":"\u0000 The five-axis ball-end milling dynamics of thin-walled blades is presented. The cutting forces are predicted from the ball end mill–blade geometry engagement maps along the tool path. The Frequency Response Function (FRF) of the thin-walled blade is predicted using Finite Element shell elements, and it is updated along the toolpath as the metal is removed. The predicted cutting forces are applied on both the workpiece and tool FRFs to predict the forced vibrations and chatter stability at each tool location. A simplified method to update the cutter–workpiece engagement (CWE) is used to obtain the three-dimensional stability lobe diagram at each desired point on the blade. The integrated model is used to simulate the 5-axis machining of thin-walled blades in the digital environment. The proposed digital model is experimentally validated by machining a series of thin-walled rectangular plates and a twisted fan blade.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41382106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The manufacturing industry is currently facing an increasing demand for customized products, leading to a shift from mass production to mass customization. As a result, operators are required to produce multiple product variants with varying complexity levels while maintaining high-quality standards. Further, in line with the human-centered paradigm of Industry 5.0, ensuring the well-being of workers is equally important as production quality. This paper proposes a novel tool, the “Human-Robot Collaboration Quality and Well-Being Assessment Tool” (HRC-QWAT), which combines the analysis of overall defects generated during product variant manufacturing with the evaluation of human well-being in terms of stress response. The HRC-QWAT enables the evaluation and monitoring of human-robot collaboration systems during product variant production from a broader standpoint. A case study of collaborative human-robot assembly is used to demonstrate the applicability of the proposed approach. The results suggest that the HRC-QWAT can evaluate both production quality and human well-being, providing a useful tool for companies to monitor and improve their manufacturing processes. Overall, this paper contributes to developing a human-centric approach to quality monitoring in the context of human-robot collaborative manufacturing.
{"title":"A Novel Diagnostic Tool for Human-Centric Quality Monitoring in Human-Robot Collaboration Manufacturing","authors":"E. Verna, Stefano Puttero, G. Genta, M. Galetto","doi":"10.1115/1.4063284","DOIUrl":"https://doi.org/10.1115/1.4063284","url":null,"abstract":"\u0000 The manufacturing industry is currently facing an increasing demand for customized products, leading to a shift from mass production to mass customization. As a result, operators are required to produce multiple product variants with varying complexity levels while maintaining high-quality standards. Further, in line with the human-centered paradigm of Industry 5.0, ensuring the well-being of workers is equally important as production quality. This paper proposes a novel tool, the “Human-Robot Collaboration Quality and Well-Being Assessment Tool” (HRC-QWAT), which combines the analysis of overall defects generated during product variant manufacturing with the evaluation of human well-being in terms of stress response. The HRC-QWAT enables the evaluation and monitoring of human-robot collaboration systems during product variant production from a broader standpoint. A case study of collaborative human-robot assembly is used to demonstrate the applicability of the proposed approach. The results suggest that the HRC-QWAT can evaluate both production quality and human well-being, providing a useful tool for companies to monitor and improve their manufacturing processes. Overall, this paper contributes to developing a human-centric approach to quality monitoring in the context of human-robot collaborative manufacturing.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49147762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Powder Bed Fusion (PBF) is an additive manufacturing process in which laser heat liquefies blown powder particles on top of a powder bed, and cooling solidifies the melted powder particles. During this process, the laser beam heat interacts with the powder causing thermal emission and affecting the melt pool. This paper aims to predict heat emission in PBF by harnessing the strengths of recurrent neural networks. Long Short-Term Memory (LSTM) networks are developed to learn from sequential data (emission readings), while the learning is guided by process physics including laser power, laser speed, layer number, and scanning patterns. To reduce the computational efforts on model training, the LSTM models are integrated with a new approach for down-sampling the pyrometry raw data and extracting useful statistical features from raw data. The structure and hyperparameters of the LSTM model reflect several iterations of tuning based on the training on the pyrometer readings data. Results reveal useful knowledge on how raw pyrometer data should be processed to work the best with LSTM, how physics features are informative in predicting overheating, and the effectiveness of physics-guided LSTM in emission prediction.
{"title":"PHYSICS-GUIDED LONG SHORT-TERM MEMORY NETWORKS FOR EMISSION PREDICTION IN LASER POWDER BED FUSION","authors":"Rong Lei, Y.B. Guo, W. Guo","doi":"10.1115/1.4063270","DOIUrl":"https://doi.org/10.1115/1.4063270","url":null,"abstract":"\u0000 Powder Bed Fusion (PBF) is an additive manufacturing process in which laser heat liquefies blown powder particles on top of a powder bed, and cooling solidifies the melted powder particles. During this process, the laser beam heat interacts with the powder causing thermal emission and affecting the melt pool. This paper aims to predict heat emission in PBF by harnessing the strengths of recurrent neural networks. Long Short-Term Memory (LSTM) networks are developed to learn from sequential data (emission readings), while the learning is guided by process physics including laser power, laser speed, layer number, and scanning patterns. To reduce the computational efforts on model training, the LSTM models are integrated with a new approach for down-sampling the pyrometry raw data and extracting useful statistical features from raw data. The structure and hyperparameters of the LSTM model reflect several iterations of tuning based on the training on the pyrometer readings data. Results reveal useful knowledge on how raw pyrometer data should be processed to work the best with LSTM, how physics features are informative in predicting overheating, and the effectiveness of physics-guided LSTM in emission prediction.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48212078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the development and gradual maturity of additive manufacturing (AM) over the years, AM has reached a stage where implementation into a conventional production system becomes possible. With AM suitable for small volume of highly customized production, there are various ways of implementing AM in a conventional production line. The aim of this paper is to present a strategic design approach of implementing AM with conventional manufacturing in a complementary manner for parallel processing of production orders of large quantities in a make-to-stock environment. By assuming that a single machine in conventional manufacturing can be operated using AM, splitting of production orders is allowed. Therefore production can be conducted by both conventional and AM processes simultaneously, with the latter being able to produce various make-to-stock parts in a single build. A generic algorithm with a scheduling and rule-based heuristic for part allocation on build plate of AM process is used to solve a multi-objective implementation problem of AM with conventional manufacturing, with cost, scheduling and sustainability being the considered performance measures. By obtaining a knee-point solution using varying numbers of population size and generation number, an experiment involving an industry case study of implementing fused deposition modelling (FDM) process with injection moulding process shows the greatest impact, i.e., increase, in cost. Except for material efficiency, improvements are shown in scheduling and carbon footprint objectives.
{"title":"Strategic Production Process Design with Additive Manufacturing in a Make-to-stock Environment","authors":"P. C. Chua, S. K. Moon, Y. Ng, Manel Lopez","doi":"10.1115/1.4063285","DOIUrl":"https://doi.org/10.1115/1.4063285","url":null,"abstract":"\u0000 With the development and gradual maturity of additive manufacturing (AM) over the years, AM has reached a stage where implementation into a conventional production system becomes possible. With AM suitable for small volume of highly customized production, there are various ways of implementing AM in a conventional production line. The aim of this paper is to present a strategic design approach of implementing AM with conventional manufacturing in a complementary manner for parallel processing of production orders of large quantities in a make-to-stock environment. By assuming that a single machine in conventional manufacturing can be operated using AM, splitting of production orders is allowed. Therefore production can be conducted by both conventional and AM processes simultaneously, with the latter being able to produce various make-to-stock parts in a single build. A generic algorithm with a scheduling and rule-based heuristic for part allocation on build plate of AM process is used to solve a multi-objective implementation problem of AM with conventional manufacturing, with cost, scheduling and sustainability being the considered performance measures. By obtaining a knee-point solution using varying numbers of population size and generation number, an experiment involving an industry case study of implementing fused deposition modelling (FDM) process with injection moulding process shows the greatest impact, i.e., increase, in cost. Except for material efficiency, improvements are shown in scheduling and carbon footprint objectives.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42288570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The vigorous development of the human cyber-physical system (HCPS) and the next generation of artificial intelligence provide new ideas for smart manufacturing, where manufacturing quality prediction is an important issue in the manufacturing system. However, the small-scale data from humans in emerging HCPS-enabled manufacturing restricts the development of traditional quality prediction methods. To address this question, a data augmentation-based manufacturing quality prediction approach in human cyber-physical systems is proposed in this paper. Specifically, a Data Augmentation-Gradient Boosting Decision Tree (DA-GBDT) model is developed for quality prediction under the HCPS context. In addition, an adaptive selection algorithm of data augmentation rate is designed to balance the trade-off between the training time of the prediction model and the prediction accuracy. Finally, the experimental results of automobile covering products demonstrate that the proposed method can improve the average prediction error of the model compared with the prevailing quality prediction methods. Moreover, the predicted quality information can provide guidance for product optimization decisions in smart manufacturing systems.
{"title":"Data Augmentation-based Manufacturing Quality Prediction Approach in Human Cyber-Physical Systems","authors":"Tianyue Wang, Bingtao Hu, Yixiong Feng, Xiaoxie Gao, Chen Yang, Jianrong Tan","doi":"10.1115/1.4063269","DOIUrl":"https://doi.org/10.1115/1.4063269","url":null,"abstract":"\u0000 The vigorous development of the human cyber-physical system (HCPS) and the next generation of artificial intelligence provide new ideas for smart manufacturing, where manufacturing quality prediction is an important issue in the manufacturing system. However, the small-scale data from humans in emerging HCPS-enabled manufacturing restricts the development of traditional quality prediction methods. To address this question, a data augmentation-based manufacturing quality prediction approach in human cyber-physical systems is proposed in this paper. Specifically, a Data Augmentation-Gradient Boosting Decision Tree (DA-GBDT) model is developed for quality prediction under the HCPS context. In addition, an adaptive selection algorithm of data augmentation rate is designed to balance the trade-off between the training time of the prediction model and the prediction accuracy. Finally, the experimental results of automobile covering products demonstrate that the proposed method can improve the average prediction error of the model compared with the prevailing quality prediction methods. Moreover, the predicted quality information can provide guidance for product optimization decisions in smart manufacturing systems.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48401734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","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：