Zipeng Guo, Ruizhe Yang, Jun Liu, Jason Armstrong, Ruogang Zhao, chi zhou
Abstract This work presents a fast additive manufacturing (AM) protocol for fabricating multi-network hydrogels. A gas-permeable PDMS (polydimethylsiloxane) film creates a polymerization-inhibition zone, enabling continuous stereolithography (SLA) 3D printing of hydrogels. The fabricated multi-bonding network integrates rigid covalent bonding and tough ionic bonding, allowing effective tuning of elastic modulus and strength for various loading conditions. The 3D-printed triply periodic minimal structures (TPMS) hydrogels exhibit high compressibility with up to 80% recoverable strain. Additionally, dried TPMS hydrogels display novel energy/impact absorption properties. By comparing uniform and gradient TPMS hydrogels, we analyze their energy/impact absorption capability of the 3D-printed specimens. We use finite element analysis (FEA) simulation studies to reveal the anisotropy and quasi-isotropy behavior of the TPMS structures, providing insights for designing and controlling TPMS structures for energy absorption. Our findings suggest that gradient TPMS hydrogels are preferable energy absorbers with potential applications in impact resistance and absorption.
{"title":"CONTINUOUS STEREOLITHOGRAPHY 3D PRINTING OF MULTI-NETWORK HYDROGELS IN TRIPLY PERIODIC MINIMAL STRUCTURES (TPMS) WITH TUNABLE MECHANICAL STRENGTH FOR ENERGY ABSORPTION","authors":"Zipeng Guo, Ruizhe Yang, Jun Liu, Jason Armstrong, Ruogang Zhao, chi zhou","doi":"10.1115/1.4063905","DOIUrl":"https://doi.org/10.1115/1.4063905","url":null,"abstract":"Abstract This work presents a fast additive manufacturing (AM) protocol for fabricating multi-network hydrogels. A gas-permeable PDMS (polydimethylsiloxane) film creates a polymerization-inhibition zone, enabling continuous stereolithography (SLA) 3D printing of hydrogels. The fabricated multi-bonding network integrates rigid covalent bonding and tough ionic bonding, allowing effective tuning of elastic modulus and strength for various loading conditions. The 3D-printed triply periodic minimal structures (TPMS) hydrogels exhibit high compressibility with up to 80% recoverable strain. Additionally, dried TPMS hydrogels display novel energy/impact absorption properties. By comparing uniform and gradient TPMS hydrogels, we analyze their energy/impact absorption capability of the 3D-printed specimens. We use finite element analysis (FEA) simulation studies to reveal the anisotropy and quasi-isotropy behavior of the TPMS structures, providing insights for designing and controlling TPMS structures for energy absorption. Our findings suggest that gradient TPMS hydrogels are preferable energy absorbers with potential applications in impact resistance and absorption.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134993479","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 Product disassembly plays a crucial role in the recycling, remanufacturing, and reuse of end-of-use (EoU) products. However, the current manual disassembly process is inefficient due to the complexity and variation of EoU products. While fully automating disassembly is not economically viable given the intricate nature of the task, there is potential in using human-robot collaboration (HRC) to enhance disassembly operations. HRC combines the flexibility and problem-solving abilities of humans with the precise repetition and handling of unsafe tasks by robots. Nevertheless, numerous challenges persist in technology, human workers, and remanufacturing work, that require comprehensive multidisciplinary research to bridge critical gaps. These challenges have motivated the authors to provide a detailed discussion on the opportunities and obstacles associated with introducing HRC to disassembly. In this regard, the authors have conducted a thorough review of the recent progress in HRC disassembly and present the insights gained from this analysis from three distinct perspectives: technology, workers, and work.
{"title":"A Review of Prospects and Opportunities in Disassembly with Human-Robot Collaboration","authors":"Meng-Lun Lee, Xiao Liang, Boyi Hu, Gulcan Onel, Sara Behdad, Minghui Zheng","doi":"10.1115/1.4063992","DOIUrl":"https://doi.org/10.1115/1.4063992","url":null,"abstract":"Abstract Product disassembly plays a crucial role in the recycling, remanufacturing, and reuse of end-of-use (EoU) products. However, the current manual disassembly process is inefficient due to the complexity and variation of EoU products. While fully automating disassembly is not economically viable given the intricate nature of the task, there is potential in using human-robot collaboration (HRC) to enhance disassembly operations. HRC combines the flexibility and problem-solving abilities of humans with the precise repetition and handling of unsafe tasks by robots. Nevertheless, numerous challenges persist in technology, human workers, and remanufacturing work, that require comprehensive multidisciplinary research to bridge critical gaps. These challenges have motivated the authors to provide a detailed discussion on the opportunities and obstacles associated with introducing HRC to disassembly. In this regard, the authors have conducted a thorough review of the recent progress in HRC disassembly and present the insights gained from this analysis from three distinct perspectives: technology, workers, and work.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135390058","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}
Natural fiber reinforced plastic (NFRP) composites are ecofriendly and biodegradable materials that offer tremendous ecological advantages while preserving unique structures and properties. Studies on using these natural fibers as alternatives to conventional synthetic fibers in fiber-reinforced materials have opened up possibilities for industrial applications, especially sustainable manufacturing. However, critical issues reside in the machinability of such materials because of their multi-scale structure and the randomness of the reinforcing elements distributed within the matrix basis. This paper reports a comprehensive investigation of the effect of microstructure heterogeneity on the resultant behaviors of cutting forces for NFRP machining. A convolutional neural network (CNN) links the microstructural reinforcing fibers and their impacts on changing the cutting forces (with an estimation accuracy of over 90%). Next, a model-agnostic explainable machine learning approach is implemented to decipher this CNN black-box model by discovering the underlying mechanisms of relating the reinforcing elements/fibers' microstructures. The presented XML approach extracts physical descriptors from the in-process monitoring microscopic images and finds the causality of the fibrous structures' heterogeneity to the resultant machining forces. The results suggest that, for the heterogeneous fibers, the tightly and evenly bounded fiber elements (i.e., with lower aspect ratio, lower eccentricity, and higher compactness ) strengthen the material and increase the cutting forces. Therefore, the presented explainable machine learning framework opens an opportunity to discover the causality of material microstructures on the resultant process dynamics and accurately predict the cutting behaviors during material removal processes.
{"title":"The Effect of Microstructure on the Machinability of Natural Fiber Reinforced Plastic Composites: A Novel Explainable Machine Learning (XML) Approach","authors":"Qiyang Ma, Yuhao Zhong, Zimo Wang, Satish Bukkapatnam","doi":"10.1115/1.4064039","DOIUrl":"https://doi.org/10.1115/1.4064039","url":null,"abstract":"Natural fiber reinforced plastic (NFRP) composites are ecofriendly and biodegradable materials that offer tremendous ecological advantages while preserving unique structures and properties. Studies on using these natural fibers as alternatives to conventional synthetic fibers in fiber-reinforced materials have opened up possibilities for industrial applications, especially sustainable manufacturing. However, critical issues reside in the machinability of such materials because of their multi-scale structure and the randomness of the reinforcing elements distributed within the matrix basis. This paper reports a comprehensive investigation of the effect of microstructure heterogeneity on the resultant behaviors of cutting forces for NFRP machining. A convolutional neural network (CNN) links the microstructural reinforcing fibers and their impacts on changing the cutting forces (with an estimation accuracy of over 90%). Next, a model-agnostic explainable machine learning approach is implemented to decipher this CNN black-box model by discovering the underlying mechanisms of relating the reinforcing elements/fibers' microstructures. The presented XML approach extracts physical descriptors from the in-process monitoring microscopic images and finds the causality of the fibrous structures' heterogeneity to the resultant machining forces. The results suggest that, for the heterogeneous fibers, the tightly and evenly bounded fiber elements (i.e., with lower aspect ratio, lower eccentricity, and higher compactness ) strengthen the material and increase the cutting forces. Therefore, the presented explainable machine learning framework opens an opportunity to discover the causality of material microstructures on the resultant process dynamics and accurately predict the cutting behaviors during material removal processes.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135390208","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 Human-robot collaboration, which strives to combine the best skills of humans and robots, has shown board application prospects in meeting safe-effective-flexible requirements in various fields. The ideation of much closer interaction between humans and robots has greatly developed the exploration of digital twin to enhance the collaboration. By offering high-fidelity models and real-time physical-virtual interaction, digital twin enables to achieve an accurate reflection of the physical scenario, including not only human-robot conditions but also environment changes. However, the appearance of unpredictable events may cause an inconsistency between the established schedule and actual execution. To cope with this issue, an environment-adaptive assignment method based on digital twin for human-robot collaboration is formed in this study. The proposed approach is consisted of a factor-event-act mechanism that analyzes the dynamic events and their impacts from both internal and external perspectives of the digital twin, and a GA-based assignment algorithm to response to them. Experiments are carried out in the last part, aiming to show the feasibility of the proposed method.
{"title":"A Digital Twin-based environment-adaptive assignment method for human-robot collaboration","authors":"Xin Ma, Qinglin Qi, Fei Tao","doi":"10.1115/1.4064040","DOIUrl":"https://doi.org/10.1115/1.4064040","url":null,"abstract":"Abstract Human-robot collaboration, which strives to combine the best skills of humans and robots, has shown board application prospects in meeting safe-effective-flexible requirements in various fields. The ideation of much closer interaction between humans and robots has greatly developed the exploration of digital twin to enhance the collaboration. By offering high-fidelity models and real-time physical-virtual interaction, digital twin enables to achieve an accurate reflection of the physical scenario, including not only human-robot conditions but also environment changes. However, the appearance of unpredictable events may cause an inconsistency between the established schedule and actual execution. To cope with this issue, an environment-adaptive assignment method based on digital twin for human-robot collaboration is formed in this study. The proposed approach is consisted of a factor-event-act mechanism that analyzes the dynamic events and their impacts from both internal and external perspectives of the digital twin, and a GA-based assignment algorithm to response to them. Experiments are carried out in the last part, aiming to show the feasibility of the proposed method.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135391010","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}
Paulo Henrique Teixeira França Alves, Gracie Bahr, Abigail Clarke-Sather, Melissa Maurer-Jones
Abstract As rates of textile manufacturing and disposal escalate, the ramifications to health and the environment through water pollution, microplastic contaminant concentrations, and greenhouse gas emissions increases. Discarding over 15.4 million tons of textiles each year, the U.S. recycles less than 15%, sending the remainder to landfills and incinerators. Textile reuse is not sufficient to de-escalate the situation; recycling is necessary. Most textile recycling technologies from past decades are expensive, create low quality outputs, or are not industry scalable. For viability, textile recycling system designs must evolve with the rapid pace of a dynamic textile and fashion industry. For any design to be sustainable, it must also be flexible to adapt with technological, user, societal, and environmental condition advances. To this end flexible and sustainable design principles were compared: overlapping principles were combined and missing principles were added to create twelve overarching sustainable, flexible design principles (DfSFlex). The Fiber Shredder was designed and built with flexibility and sustainability as its goal and evaluated on how well it met DfSFlex principles. An evaluation of the Fiber Shredder's performance found that increased speed and processing time increases the generation of the desired output - fibers and yarns, manifesting the principles of Design for Separation in design and Facilitate Resource Recovery in processing. The development of this technology, with the application of sustainable and flexible design, fiber-to-fiber recycling using mechanical systems appears promising for maintaining value while repurposing textiles.
{"title":"Combining Flexible and Sustainable Design Principles for Evaluating Designs: Textile Recycling Application","authors":"Paulo Henrique Teixeira França Alves, Gracie Bahr, Abigail Clarke-Sather, Melissa Maurer-Jones","doi":"10.1115/1.4063993","DOIUrl":"https://doi.org/10.1115/1.4063993","url":null,"abstract":"Abstract As rates of textile manufacturing and disposal escalate, the ramifications to health and the environment through water pollution, microplastic contaminant concentrations, and greenhouse gas emissions increases. Discarding over 15.4 million tons of textiles each year, the U.S. recycles less than 15%, sending the remainder to landfills and incinerators. Textile reuse is not sufficient to de-escalate the situation; recycling is necessary. Most textile recycling technologies from past decades are expensive, create low quality outputs, or are not industry scalable. For viability, textile recycling system designs must evolve with the rapid pace of a dynamic textile and fashion industry. For any design to be sustainable, it must also be flexible to adapt with technological, user, societal, and environmental condition advances. To this end flexible and sustainable design principles were compared: overlapping principles were combined and missing principles were added to create twelve overarching sustainable, flexible design principles (DfSFlex). The Fiber Shredder was designed and built with flexibility and sustainability as its goal and evaluated on how well it met DfSFlex principles. An evaluation of the Fiber Shredder's performance found that increased speed and processing time increases the generation of the desired output - fibers and yarns, manifesting the principles of Design for Separation in design and Facilitate Resource Recovery in processing. The development of this technology, with the application of sustainable and flexible design, fiber-to-fiber recycling using mechanical systems appears promising for maintaining value while repurposing textiles.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584754","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 Magnetorheological shear thickening polishing (MRSTP) is a novel multi-field compound polishing method that combines the shear-thickening effect and the magnetorheological effect. It has great potential as an ultra-precise machining for complex surfaces. However, there is absence of the correlation between the material removal and the rheological properties of the polishing media leads to difficulties for further improvement in polishing efficiency and quality in MRSTP. In this paper, the material removal model for MRSTP was established based on magneto-hydrodynamics, non-Newtonian fluid kinematics and microscopic contact mechanics. It combines the material removal model for single abrasive and statistical model of active abrasives. On comparing the experimental and theoretical results, it showed that the developed material removal model can accurately predict the material removal depth of the workpiece under different processing parameters (rotational speed of rotary table and magnetic field strength). The average prediction error was less than 5.0%. In addition, the analysis of the rheological behavior and fluid dynamic pressure of the polishing media reveals the coupling effect between the magnetic, stress and flow fields. This provides theoretical guidance for the actual processing of MRSTP. Finally, the maximum material removal rate of 3.3 μm/h was obtained on the cylindrical surface of the Ti-6Al-4V workpiece using the MRSTP method. The result shows that the MRSTP method has great potential in the field of ultra-precision machining of difficult-to-machine materials.
{"title":"Theoretical and experimental investigation of material removal rate in magnetorheological shear thickening polishing of Ti-6Al-4V alloy","authors":"Yebing Tian, Zhen Ma, Shadab Ahmad, Cheng Qian, Xifeng Ma, Xiangyu Yuan, Zenghua Fan","doi":"10.1115/1.4063984","DOIUrl":"https://doi.org/10.1115/1.4063984","url":null,"abstract":"Abstract Magnetorheological shear thickening polishing (MRSTP) is a novel multi-field compound polishing method that combines the shear-thickening effect and the magnetorheological effect. It has great potential as an ultra-precise machining for complex surfaces. However, there is absence of the correlation between the material removal and the rheological properties of the polishing media leads to difficulties for further improvement in polishing efficiency and quality in MRSTP. In this paper, the material removal model for MRSTP was established based on magneto-hydrodynamics, non-Newtonian fluid kinematics and microscopic contact mechanics. It combines the material removal model for single abrasive and statistical model of active abrasives. On comparing the experimental and theoretical results, it showed that the developed material removal model can accurately predict the material removal depth of the workpiece under different processing parameters (rotational speed of rotary table and magnetic field strength). The average prediction error was less than 5.0%. In addition, the analysis of the rheological behavior and fluid dynamic pressure of the polishing media reveals the coupling effect between the magnetic, stress and flow fields. This provides theoretical guidance for the actual processing of MRSTP. Finally, the maximum material removal rate of 3.3 μm/h was obtained on the cylindrical surface of the Ti-6Al-4V workpiece using the MRSTP method. The result shows that the MRSTP method has great potential in the field of ultra-precision machining of difficult-to-machine materials.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135868277","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 While reactor wall preconditioning was previously shown to influence the yield in chemical vapor deposition (CVD), especially for coatings of carbon nanotubes (CNTs), it was limited to studying accumulating deposits over a number of runs. However, the effects of temperature and duration as the reactor walls are exposed to hot humidity for an extended period of time between growth runs was not previously studied systematically. Here, we combine experimental measurements with a mathematical model to elucidate how thermochemical history of reactor walls impacts growth yield of vertically aligned CNT films. Importantly, we demonstrate one-order-of-magnitude higher CNT yield, by increasing the interim, i.e., the time between runs. We explain the results based on previously unexplored process sensitivity to trace amounts of oxygen-containing species in the reactor. In particular, we model the effect of small amounts of water vapor desorbing from reactor walls during growth. Our results reveal the outgassing dynamics, and show the underlying mechanism of generating growth promoting molecules. By installing a humidity sensor in our custom-designed multizone rapid thermal CVD reactor, we are able to uniquely correlate the amount of moisture within the reactor to real-time measurements of growth kinetics, as well as ex situ characterization of CNT alignment and atomic defects. Our findings enable a scientifically grounded approach toward both boosting growth yield and improving its consistency by reducing run-to-run variations. Accordingly, engineered dynamics recipes can be envisioned to leverage this effect for improving manufacturing process scalability and robustness.
{"title":"Order-of-Magnitude Increase in Carbon Nanotube Yield Based on Modeling Transient Diffusion and Outgassing of Water from Reactor Walls","authors":"Golnaz Tomaraei, Moataz Abdulhafez, Mostafa Bedewy","doi":"10.1115/1.4063965","DOIUrl":"https://doi.org/10.1115/1.4063965","url":null,"abstract":"Abstract While reactor wall preconditioning was previously shown to influence the yield in chemical vapor deposition (CVD), especially for coatings of carbon nanotubes (CNTs), it was limited to studying accumulating deposits over a number of runs. However, the effects of temperature and duration as the reactor walls are exposed to hot humidity for an extended period of time between growth runs was not previously studied systematically. Here, we combine experimental measurements with a mathematical model to elucidate how thermochemical history of reactor walls impacts growth yield of vertically aligned CNT films. Importantly, we demonstrate one-order-of-magnitude higher CNT yield, by increasing the interim, i.e., the time between runs. We explain the results based on previously unexplored process sensitivity to trace amounts of oxygen-containing species in the reactor. In particular, we model the effect of small amounts of water vapor desorbing from reactor walls during growth. Our results reveal the outgassing dynamics, and show the underlying mechanism of generating growth promoting molecules. By installing a humidity sensor in our custom-designed multizone rapid thermal CVD reactor, we are able to uniquely correlate the amount of moisture within the reactor to real-time measurements of growth kinetics, as well as ex situ characterization of CNT alignment and atomic defects. Our findings enable a scientifically grounded approach toward both boosting growth yield and improving its consistency by reducing run-to-run variations. Accordingly, engineered dynamics recipes can be envisioned to leverage this effect for improving manufacturing process scalability and robustness.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135321439","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 Despite the importance of product repairability, current methods for assessing and grading repairability are limited, which hampers the efforts of designers, remanufacturers, original equipment manufacturers (OEMs), and repair shops. To improve the efficiency of assessing product repairability, this study introduces two artificial intelligence (AI) based approaches. The first approach is a supervised learning framework that utilizes object detection on product teardown images to measure repairability. Transfer learning is employed with machine learning architectures such as ConvNeXt, GoogLeNet, ResNet50, and VGG16 to evaluate repairability scores. The second approach is an unsupervised learning framework that combines feature extraction and cluster learning to identify product design features and group devices with similar designs. It utilizes an oriented FAST and rotated BRIEF feature extractor (ORB) along with k-means clustering to extract features from teardown images and categorize products with similar designs. To demonstrate the application of these assessment approaches, smartphones are used as a case study. The results highlight the potential of artificial intelligence in developing an automated system for assessing and rating product repairability.
{"title":"AUTOMATED EVALUATION AND RATING OF PRODUCT REPAIRABILITY USING ARTIFICIAL INTELLIGENCE-BASED APPROACHES","authors":"Hao-Yu Liao, Behzad Esmaeilian, Sara Behdad","doi":"10.1115/1.4063561","DOIUrl":"https://doi.org/10.1115/1.4063561","url":null,"abstract":"Abstract Despite the importance of product repairability, current methods for assessing and grading repairability are limited, which hampers the efforts of designers, remanufacturers, original equipment manufacturers (OEMs), and repair shops. To improve the efficiency of assessing product repairability, this study introduces two artificial intelligence (AI) based approaches. The first approach is a supervised learning framework that utilizes object detection on product teardown images to measure repairability. Transfer learning is employed with machine learning architectures such as ConvNeXt, GoogLeNet, ResNet50, and VGG16 to evaluate repairability scores. The second approach is an unsupervised learning framework that combines feature extraction and cluster learning to identify product design features and group devices with similar designs. It utilizes an oriented FAST and rotated BRIEF feature extractor (ORB) along with k-means clustering to extract features from teardown images and categorize products with similar designs. To demonstrate the application of these assessment approaches, smartphones are used as a case study. The results highlight the potential of artificial intelligence in developing an automated system for assessing and rating product repairability.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136371683","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}
Zhuoran Li, Dianping Zhang, Ruiming Chen, Songlin Wang, Yu-Jun Xia, Ming Lou, YongBing Li
Abstract Press-hardened steel (PHS) with extremely high strength has wide applications in vehicle body manufacturing as an innovative lightweight material. However, the poor weldability of PHS results in poor weld toughness and a high risk of interfacial fracture, posing challenges to the resistance spot welding (RSW) process. Introducing an external magnetic field in the welding process to perform electromagnetic stirring (EMS), magnetically assisted RSW (MA-RSW) process has been proven an effective method to improve the weld toughness of high-strength steel, but it may increase the risk of expulsion. In this study, a new process called SPMA-RSW is developed to improve the weldability of PHS by combining MA-RSW and the stepped-current pulses (SP) technique, which can enlarge the weld lobe. Nugget appearance, microstructure, microhardness, and mechanical properties were systematically investigated by comparing traditional RSW, MA-RSW, SP-RSW, and SPMA-RSW. The result showed that the SPMA-RSW process would significantly increase the nugget size, inhibit the shrinkage voids, finer the grain, and harden the nugget. This increased the lap-shear strength, energy absorption, and changed the fracture mode from brittle interfacial (IF) mode to ductile plug fracture (PF) mode at the same heat input. Then, a simple model was developed to reveal the mechanism of the effect of EMS on the fracture mode transition and was verified by experiment. This work can help improve the weld quality and thermal efficiency of the RSW process for PHS.
{"title":"Improving Weldability of Press Hardened Steel through Combining Stepped Current Pulse and Magnetically Assisted Resistance Spot Welding Process","authors":"Zhuoran Li, Dianping Zhang, Ruiming Chen, Songlin Wang, Yu-Jun Xia, Ming Lou, YongBing Li","doi":"10.1115/1.4063904","DOIUrl":"https://doi.org/10.1115/1.4063904","url":null,"abstract":"Abstract Press-hardened steel (PHS) with extremely high strength has wide applications in vehicle body manufacturing as an innovative lightweight material. However, the poor weldability of PHS results in poor weld toughness and a high risk of interfacial fracture, posing challenges to the resistance spot welding (RSW) process. Introducing an external magnetic field in the welding process to perform electromagnetic stirring (EMS), magnetically assisted RSW (MA-RSW) process has been proven an effective method to improve the weld toughness of high-strength steel, but it may increase the risk of expulsion. In this study, a new process called SPMA-RSW is developed to improve the weldability of PHS by combining MA-RSW and the stepped-current pulses (SP) technique, which can enlarge the weld lobe. Nugget appearance, microstructure, microhardness, and mechanical properties were systematically investigated by comparing traditional RSW, MA-RSW, SP-RSW, and SPMA-RSW. The result showed that the SPMA-RSW process would significantly increase the nugget size, inhibit the shrinkage voids, finer the grain, and harden the nugget. This increased the lap-shear strength, energy absorption, and changed the fracture mode from brittle interfacial (IF) mode to ductile plug fracture (PF) mode at the same heat input. Then, a simple model was developed to reveal the mechanism of the effect of EMS on the fracture mode transition and was verified by experiment. This work can help improve the weld quality and thermal efficiency of the RSW process for PHS.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136316724","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}
This Special Issue serves as a bridge between the ASME Journal of Manufacturing Science and Engineering (JMSE) and the global community of manufacturing researchers. Its primary objective is to curate a collection of high-level scientific articles that push the boundaries of knowledge in the realm of Human-Robot Collaboration (HRC) for forward-looking, human-centric smart manufacturing. It encourages researchers to present their innovative methodologies, tools, systems, and practical case studies, fostering advancements that integrate cognitive computing, mixed reality, and advanced data analytics. By emphasizing proactive teamwork and seamless interaction, this initiative aims to narrow the gap between human operators and industrial robots. Contributions are sought in areas such as cognitive HRC systems, safety considerations, adaptive motion planning, human intention prediction, and semantic knowledge representation—key components in achieving efficient and effective collaboration within the manufacturing industry. Beyond its scientific impact, this Special Issue also seeks to unite leading scientific communities worldwide.
{"title":"Special Issue on Human-Robot Collaboration for Futuristic Human-Centric Smart Manufacturing","authors":"Pai Zheng","doi":"10.1115/1.4063447","DOIUrl":"https://doi.org/10.1115/1.4063447","url":null,"abstract":"This Special Issue serves as a bridge between the ASME Journal of Manufacturing Science and Engineering (JMSE) and the global community of manufacturing researchers. Its primary objective is to curate a collection of high-level scientific articles that push the boundaries of knowledge in the realm of Human-Robot Collaboration (HRC) for forward-looking, human-centric smart manufacturing. It encourages researchers to present their innovative methodologies, tools, systems, and practical case studies, fostering advancements that integrate cognitive computing, mixed reality, and advanced data analytics. By emphasizing proactive teamwork and seamless interaction, this initiative aims to narrow the gap between human operators and industrial robots. Contributions are sought in areas such as cognitive HRC systems, safety considerations, adaptive motion planning, human intention prediction, and semantic knowledge representation—key components in achieving efficient and effective collaboration within the manufacturing industry. Beyond its scientific impact, this Special Issue also seeks to unite leading scientific communities worldwide.","PeriodicalId":16299,"journal":{"name":"Journal of Manufacturing Science and Engineering-transactions of The Asme","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135667441","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：