Journal of Manufacturing Processes最新文献_第7页

A multi-spectral channel attention mechanism for prediction of welding state during pulsed GTAW

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-31 DOI: 10.1016/j.jmapro.2025.01.023

Yuqing Xu, Qiang Liu, Jingyuan Xu, Runquan Xiao, Shanben Chen

Accurate prediction of welding state is essential for ensuring the quality of aluminum alloy pulsed gas tungsten arc welding (GTAW). While multimodal fusion approaches have advanced welding state prediction, complex environmental noise often introduces interference, reducing prediction accuracy. To address this, we propose a novel multimodal fusion network based on multispectral channel attention mechanism (MFCA-Net). First, our model employs a parallel feature mapping strategy to capture both local and global dependencies within each modality, enhancing receptive field interaction and improving global modeling capabilities. Second, a multi-spectral channel attention mechanism emphasizes informative features across channels, refining the fusion of local high-frequency and global low-frequency features within each mode and reducing redundancy. Finally, these multimodal features are fused to accurately predict welding state. Experimental results demonstrate that MFCA-Net accurately identifies five typical welding states—lack of penetration, normal penetration, over penetration, misalignment, and burn through—with an accuracy of 98.8 %, and 96.1 % on public datasets. Compared with state-of-the-art methods, MFCA-Net significantly enhances prediction performance, showing strong potential for real-world welding applications.

{"title":"A multi-spectral channel attention mechanism for prediction of welding state during pulsed GTAW","authors":"Yuqing Xu, Qiang Liu, Jingyuan Xu, Runquan Xiao, Shanben Chen","doi":"10.1016/j.jmapro.2025.01.023","DOIUrl":"10.1016/j.jmapro.2025.01.023","url":null,"abstract":"<div><div>Accurate prediction of welding state is essential for ensuring the quality of aluminum alloy pulsed gas tungsten arc welding (GTAW). While multimodal fusion approaches have advanced welding state prediction, complex environmental noise often introduces interference, reducing prediction accuracy. To address this, we propose a novel multimodal fusion network based on multispectral channel attention mechanism (MFCA-Net). First, our model employs a parallel feature mapping strategy to capture both local and global dependencies within each modality, enhancing receptive field interaction and improving global modeling capabilities. Second, a multi-spectral channel attention mechanism emphasizes informative features across channels, refining the fusion of local high-frequency and global low-frequency features within each mode and reducing redundancy. Finally, these multimodal features are fused to accurately predict welding state. Experimental results demonstrate that MFCA-Net accurately identifies five typical welding states—lack of penetration, normal penetration, over penetration, misalignment, and burn through—with an accuracy of 98.8 %, and 96.1 % on public datasets. Compared with state-of-the-art methods, MFCA-Net significantly enhances prediction performance, showing strong potential for real-world welding applications.</div></div>","PeriodicalId":16148,"journal":{"name":"Journal of Manufacturing Processes","volume":"134 ","pages":"Pages 1021-1033"},"PeriodicalIF":6.1,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Identification of position-related geometric error terms from profile error in four-axis ultra-precision machine tool based on Informer model

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-31 DOI: 10.1016/j.jmapro.2025.01.021

Yang Cao, Xuesen Zhao, Shuli Qu, Tianji Xing, Wenjun Zong, Tao Sun

As modern manufacturing progresses, demands for product quality and precision continuously increase. Ultra-precision machine tools, serving as carriers for high-accuracy workpieces, are widely utilized. The stringent quality control at each stage in these machines, making component accuracy a critical factor influencing workpiece profile precision. Measuring and compensating for geometric errors at specific machining positions constitutes an effective method for enhancing the precision of ultra-precision machine tools. This study aims to employ a data-driven intelligent algorithm to identify the position-related geometric error terms from turned surface profile error, aiming to acquire geometric error data for the ultra-precision machine tool. Initially, an error model between workpiece and tool is established to analyze the effects of position-related geometric error terms, followed by a sensitivity analysis of spatial sub-errors within the total error vector across the X-Y-Z directions. The results indicate that there are no coupling relationships between sensitivity coefficients, enabling the separation of spatial sub-errors and the establishment of corresponding sub-models for position-related geometric error terms, thus generating the theoretical dataset required for model training. Then, using the least square method to fit the turned tool marks and the circle lines, the profile error of the turned surface is obtained for model actual prediction. Subsequently, an identification model for turned surface profile error and position-related geometric error is developed based on the Informer deep learning framework. This model predicts error using a data-driven approach informed by the theoretical sub-models. Finally, experimental data from ultra-precision turned surface profile error are utilized for decoupling and tracing, leading to the predictions of position-related geometric error terms. Validation results demonstrate that the proposed model effectively decouples profile errors and successfully traces the position-related geometric error terms of the ultra-precision machine tool.

{"title":"Identification of position-related geometric error terms from profile error in four-axis ultra-precision machine tool based on Informer model","authors":"Yang Cao, Xuesen Zhao, Shuli Qu, Tianji Xing, Wenjun Zong, Tao Sun","doi":"10.1016/j.jmapro.2025.01.021","DOIUrl":"10.1016/j.jmapro.2025.01.021","url":null,"abstract":"<div><div>As modern manufacturing progresses, demands for product quality and precision continuously increase. Ultra-precision machine tools, serving as carriers for high-accuracy workpieces, are widely utilized. The stringent quality control at each stage in these machines, making component accuracy a critical factor influencing workpiece profile precision. Measuring and compensating for geometric errors at specific machining positions constitutes an effective method for enhancing the precision of ultra-precision machine tools. This study aims to employ a data-driven intelligent algorithm to identify the position-related geometric error terms from turned surface profile error, aiming to acquire geometric error data for the ultra-precision machine tool. Initially, an error model between workpiece and tool is established to analyze the effects of position-related geometric error terms, followed by a sensitivity analysis of spatial sub-errors within the total error vector across the X-Y-Z directions. The results indicate that there are no coupling relationships between sensitivity coefficients, enabling the separation of spatial sub-errors and the establishment of corresponding sub-models for position-related geometric error terms, thus generating the theoretical dataset required for model training. Then, using the least square method to fit the turned tool marks and the circle lines, the profile error of the turned surface is obtained for model actual prediction. Subsequently, an identification model for turned surface profile error and position-related geometric error is developed based on the Informer deep learning framework. This model predicts error using a data-driven approach informed by the theoretical sub-models. Finally, experimental data from ultra-precision turned surface profile error are utilized for decoupling and tracing, leading to the predictions of position-related geometric error terms. Validation results demonstrate that the proposed model effectively decouples profile errors and successfully traces the position-related geometric error terms of the ultra-precision machine tool.</div></div>","PeriodicalId":16148,"journal":{"name":"Journal of Manufacturing Processes","volume":"134 ","pages":"Pages 943-969"},"PeriodicalIF":6.1,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimization of novel coil structure parameters for controlling Al/Fe magnetic pulse welding process

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-31 DOI: 10.1016/j.jmapro.2024.12.044

Xi Jiang , Haiping Yu , Haohua Li

Magnetic pulse welding (MPW) for dissimilar sheet metals holds significant industrial potential as an environmentally friendly and efficient method. The process and results of MPW are highly dependent on the discharge parameters of MPW equipment. However, the development of excellent performance equipment is challenging and costly, limiting the widespread industrial application of MPW. A novel coil with the capability of amplifying current is proposed in this study, thereby mitigating the stringent requirements on MPW equipment. Firstly, the theoretical model was established to assess the effect of coil structure parameters on RLC (resistance, inductance, and capacitance) within the MPW discharge system and the magnetic pressure exerted on the sheet metal. Subsequently, numerical simulations were employed to investigate the variation trends of current density, Lorentz force, and collision parameters of the flyer sheet basing on different coil structures during the MPW process. Given that coil with 4 turns, diameter of 200 mm and pitch of 30 mm achieves a 3.1 times current amplification and a collision speed of 383.7 m/s of the flyer sheet at 9.8 kJ, while maintaining certain structural stability, the experiments were conducted. Experimental results confirmed that the small error in numerical simulation results. The metallurgical welding features, including the waveform interface, amorphous layer, and element diffusion, were observed at the 1060-DP450 weld interface achieved at 9.8 kJ. Nanoindentation results indicated that work hardening caused a higher hardness (max: 1.808 GPa) near the interface. Mechanical testing of joints welded at different energy levels (6.05–9.8 kJ) revealed that when the discharge energy exceeded 8.45 kJ, the fracture location of the joint occurs in the 1060 rather than the welding area, which is lower than the energy requirement for welding sheets of similar strength levels using traditional coils. Therefore, the novel coil structure proposed in this study reduces the difficulty of the MPW process while ensuring excellent joint performance, which is beneficial for the further industrial application of MPW technology.

{"title":"Optimization of novel coil structure parameters for controlling Al/Fe magnetic pulse welding process","authors":"Xi Jiang , Haiping Yu , Haohua Li","doi":"10.1016/j.jmapro.2024.12.044","DOIUrl":"10.1016/j.jmapro.2024.12.044","url":null,"abstract":"<div><div>Magnetic pulse welding (MPW) for dissimilar sheet metals holds significant industrial potential as an environmentally friendly and efficient method. The process and results of MPW are highly dependent on the discharge parameters of MPW equipment. However, the development of excellent performance equipment is challenging and costly, limiting the widespread industrial application of MPW. A novel coil with the capability of amplifying current is proposed in this study, thereby mitigating the stringent requirements on MPW equipment. Firstly, the theoretical model was established to assess the effect of coil structure parameters on RLC (resistance, inductance, and capacitance) within the MPW discharge system and the magnetic pressure exerted on the sheet metal. Subsequently, numerical simulations were employed to investigate the variation trends of current density, Lorentz force, and collision parameters of the flyer sheet basing on different coil structures during the MPW process. Given that coil with 4 turns, diameter of 200 mm and pitch of 30 mm achieves a 3.1 times current amplification and a collision speed of 383.7 m/s of the flyer sheet at 9.8 kJ, while maintaining certain structural stability, the experiments were conducted. Experimental results confirmed that the small error in numerical simulation results. The metallurgical welding features, including the waveform interface, amorphous layer, and element diffusion, were observed at the 1060-DP450 weld interface achieved at 9.8 kJ. Nanoindentation results indicated that work hardening caused a higher hardness (max: 1.808 GPa) near the interface. Mechanical testing of joints welded at different energy levels (6.05–9.8 kJ) revealed that when the discharge energy exceeded 8.45 kJ, the fracture location of the joint occurs in the 1060 rather than the welding area, which is lower than the energy requirement for welding sheets of similar strength levels using traditional coils. Therefore, the novel coil structure proposed in this study reduces the difficulty of the MPW process while ensuring excellent joint performance, which is beneficial for the further industrial application of MPW technology.</div></div>","PeriodicalId":16148,"journal":{"name":"Journal of Manufacturing Processes","volume":"134 ","pages":"Pages 117-134"},"PeriodicalIF":6.1,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of alkoxide film on chip morphology under electrostatic catalysis in cutting 1060 aluminum alloy

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-31 DOI: 10.1016/j.jmapro.2024.12.066

Wenbin Wang, Ying Wang, Yu Xia, Xinshao Cheng, Fucai Liu, Ruochong Zhang, Xiaodong Hu, Xuefeng Xu

To address the challenges of large plastic deformation, tool adhesion, and built-up edge formation during aluminum alloy cutting, a novel approach using charged alcohol-containing cutting fluid in the machining of aluminum alloy is proposed. On the basis of investigating the mechanism of charging on the formation of chemical reaction films by 1,2-propanediol on the surface of 1060 aluminum alloy, orthogonal cutting experiments were carried out. It was found that charging enhances the chemical activity of alcohol-containing cutting fluids on the surface of aluminum alloys, leading to increased surface hardness and facilitating the plastic-brittle transition on the surface of the material. Under the conditions of static electricity and 1,2-propanediol-containing cutting fluid, the serrated degree of aluminum alloy chips increased, while the chip thickness ratio and cutting force decreased. Additionally, the maximum height of the chip free surface profile increased. The results of this research will offer a fresh concept and approach for achieving high-efficiency and environmentally friendly cutting of aluminum alloys.

{"title":"Effect of alkoxide film on chip morphology under electrostatic catalysis in cutting 1060 aluminum alloy","authors":"Wenbin Wang, Ying Wang, Yu Xia, Xinshao Cheng, Fucai Liu, Ruochong Zhang, Xiaodong Hu, Xuefeng Xu","doi":"10.1016/j.jmapro.2024.12.066","DOIUrl":"10.1016/j.jmapro.2024.12.066","url":null,"abstract":"<div><div>To address the challenges of large plastic deformation, tool adhesion, and built-up edge formation during aluminum alloy cutting, a novel approach using charged alcohol-containing cutting fluid in the machining of aluminum alloy is proposed. On the basis of investigating the mechanism of charging on the formation of chemical reaction films by 1,2-propanediol on the surface of 1060 aluminum alloy, orthogonal cutting experiments were carried out. It was found that charging enhances the chemical activity of alcohol-containing cutting fluids on the surface of aluminum alloys, leading to increased surface hardness and facilitating the plastic-brittle transition on the surface of the material. Under the conditions of static electricity and 1,2-propanediol-containing cutting fluid, the serrated degree of aluminum alloy chips increased, while the chip thickness ratio and cutting force decreased. Additionally, the maximum height of the chip free surface profile increased. The results of this research will offer a fresh concept and approach for achieving high-efficiency and environmentally friendly cutting of aluminum alloys.</div></div>","PeriodicalId":16148,"journal":{"name":"Journal of Manufacturing Processes","volume":"134 ","pages":"Pages 360-371"},"PeriodicalIF":6.1,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A laser direct-writing magnetic integration process: Low-temperature packaging of magnetic films on on-chip inductive components

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-31 DOI: 10.1016/j.jmapro.2025.01.014

Leiyang Wang , Yunfan Li , Bang Wu , Lan Liu , Shifeng Li , Kang Liang , Yu Zhou , Feng Liu , Sheng Liu

The integration of functional magnetic films into chips can effectively solve the problem of large area and low performance of radio frequency (RF) on-chip inductive components. However, the lack of low-temperature integration processes compatible with standard semiconductor processes for magnetic films hinders the practical application of on-chip inductive components with magnetic films. In this study, to improve the performance of on-chip inductive components, a laser direct-writing process is proposed for the first time for low-temperature packaging of magnetic films on on-chip inductive components. In this process, an oriented laser is used to heat and solidify a magnetic slurry film composed of thermosetting resin and magnetic nanoparticles, which is coated on on-chip inductive component, thus realizing the low-temperature integration of magnetic film on on-chip component. Furthermore, the laser direct-writing process is applied to integrate ferroferric oxide (Fe₃O₄) magnetic film onto a meander on-chip inductor. Compared to the same type of air-core meander inductor, the inductance (L) and quality factor (Q) of the meander inductor with Fe₃O₄ magnetic film are increased by 20.2 % and 7 % at 1 GHz, respectively. The results indicate that the laser direct-writing magnetic integration process is simple, low-temperature, efficient, and fully compatible with standard semiconductor process, and has great application prospects in magnetic material integration of on-chip inductive components.

{"title":"A laser direct-writing magnetic integration process: Low-temperature packaging of magnetic films on on-chip inductive components","authors":"Leiyang Wang , Yunfan Li , Bang Wu , Lan Liu , Shifeng Li , Kang Liang , Yu Zhou , Feng Liu , Sheng Liu","doi":"10.1016/j.jmapro.2025.01.014","DOIUrl":"10.1016/j.jmapro.2025.01.014","url":null,"abstract":"<div><div>The integration of functional magnetic films into chips can effectively solve the problem of large area and low performance of radio frequency (RF) on-chip inductive components. However, the lack of low-temperature integration processes compatible with standard semiconductor processes for magnetic films hinders the practical application of on-chip inductive components with magnetic films. In this study, to improve the performance of on-chip inductive components, a laser direct-writing process is proposed for the first time for low-temperature packaging of magnetic films on on-chip inductive components. In this process, an oriented laser is used to heat and solidify a magnetic slurry film composed of thermosetting resin and magnetic nanoparticles, which is coated on on-chip inductive component, thus realizing the low-temperature integration of magnetic film on on-chip component. Furthermore, the laser direct-writing process is applied to integrate ferroferric oxide (Fe<sub>3</sub>O<sub>4</sub>) magnetic film onto a meander on-chip inductor. Compared to the same type of air-core meander inductor, the inductance (<em>L</em>) and quality factor (<em>Q</em>) of the meander inductor with Fe<sub>3</sub>O<sub>4</sub> magnetic film are increased by 20.2 % and 7 % at 1 GHz, respectively. The results indicate that the laser direct-writing magnetic integration process is simple, low-temperature, efficient, and fully compatible with standard semiconductor process, and has great application prospects in magnetic material integration of on-chip inductive components.</div></div>","PeriodicalId":16148,"journal":{"name":"Journal of Manufacturing Processes","volume":"134 ","pages":"Pages 904-914"},"PeriodicalIF":6.1,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143131774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Critical velocity and deposition efficiency in cold spray: A reduced-order model and experimental validation

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-31 DOI: 10.1016/j.jmapro.2024.12.077

Che Zhang , Tesfaye Molla , Christian Brandl , Jarrod Watts , Rick McCully , Caixian Tang , Graham Schaffer

Deposition efficiency (DE) in cold spray additive manufacturing (CSAM) is a key indicator for evaluating process efficiency. Here we develop a reduced-order model to predict DE of metals during CSAM by simultaneously calculating the critical velocity and impact velocity using the gas temperature, gas pressure, and particle size as inputs. The impact velocity must exceed the critical velocity to achieve particle adhesion. Since both the critical and impact velocities vary with particle size, DE can be derived from the intersection of these curves. An equation for calculating critical velocity is proposed based on the hydrodynamic spall mechanism with the support of experimental data. The impact velocity is determined using a parametric expression that accounts for the bow shock effect. The model is first calibrated for aluminum to create process design maps. Ten validation experiments are then conducted using two different cold spray systems. The experimental DE values show close agreement with the predicted results. The model can be used to rapidly identify optimal process parameters for achieving high DE of metals, contributing to improved process efficiency and product quality during CSAM.

{"title":"Critical velocity and deposition efficiency in cold spray: A reduced-order model and experimental validation","authors":"Che Zhang , Tesfaye Molla , Christian Brandl , Jarrod Watts , Rick McCully , Caixian Tang , Graham Schaffer","doi":"10.1016/j.jmapro.2024.12.077","DOIUrl":"10.1016/j.jmapro.2024.12.077","url":null,"abstract":"<div><div>Deposition efficiency (DE) in cold spray additive manufacturing (CSAM) is a key indicator for evaluating process efficiency. Here we develop a reduced-order model to predict DE of metals during CSAM by simultaneously calculating the critical velocity and impact velocity using the gas temperature, gas pressure, and particle size as inputs. The impact velocity must exceed the critical velocity to achieve particle adhesion. Since both the critical and impact velocities vary with particle size, DE can be derived from the intersection of these curves. An equation for calculating critical velocity is proposed based on the hydrodynamic spall mechanism with the support of experimental data. The impact velocity is determined using a parametric expression that accounts for the bow shock effect. The model is first calibrated for aluminum to create process design maps. Ten validation experiments are then conducted using two different cold spray systems. The experimental DE values show close agreement with the predicted results. The model can be used to rapidly identify optimal process parameters for achieving high DE of metals, contributing to improved process efficiency and product quality during CSAM.</div></div>","PeriodicalId":16148,"journal":{"name":"Journal of Manufacturing Processes","volume":"134 ","pages":"Pages 547-557"},"PeriodicalIF":6.1,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143131894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bayesian optimization of tailgate rib structures enhancing structural stiffness under manufacturing constraints of injection molding

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-31 DOI: 10.1016/j.jmapro.2024.12.064

Hugon Lee , Jinwook Yeo , Keonpyo Kong , Dujae Myeong , Donghoon Jang , Jongyeob Lee , Hyeokhwan Choi , Namkeun Kim , Seunghwa Ryu

The shift towards environmentally friendly transportation has driven significant attention to lightweight vehicle design, especially to counterbalance the substantial weight of batteries in electric vehicles. Reinforced polymer composites offer a promising alternative to traditional steel due to their lower density. However, to overcome the inherent stiffness limitations of mass-produced short fiber reinforced polymer composites manufactured through compounding and injection molding, the use of internal reinforcing structures, such as ribs, is essential. This study proposes a cost-effective, data-driven approach to parametrize and optimize rib placement within automotive tailgate components. The primary objective is to maximize structural stiffness, evaluated with industry-standard testing methods for tailgate components, while adhering to mass constraints. Rib structures are parametrized with a focus on simplicity to reduce data requirements, accounting for manufacturing constraints inherent to injection molding and maintaining permutation invariance of rib designs. Given the high cost of evaluating variety of rib configurations, Bayesian optimization is applied for efficient data utilization. Gaussian process regression is used as a surrogate model to predict structural stiffness, based on finite element analysis data from various rib configurations. The optimized design is then fabricated as full-scale prototypes through injection molding, and their performance is validated against numerical predictions. This approach exemplifies a practical, data-driven methodology for designing rib structures in complex industrial components, integrating computational design with manufacturing processes.

{"title":"Bayesian optimization of tailgate rib structures enhancing structural stiffness under manufacturing constraints of injection molding","authors":"Hugon Lee , Jinwook Yeo , Keonpyo Kong , Dujae Myeong , Donghoon Jang , Jongyeob Lee , Hyeokhwan Choi , Namkeun Kim , Seunghwa Ryu","doi":"10.1016/j.jmapro.2024.12.064","DOIUrl":"10.1016/j.jmapro.2024.12.064","url":null,"abstract":"<div><div>The shift towards environmentally friendly transportation has driven significant attention to lightweight vehicle design, especially to counterbalance the substantial weight of batteries in electric vehicles. Reinforced polymer composites offer a promising alternative to traditional steel due to their lower density. However, to overcome the inherent stiffness limitations of mass-produced short fiber reinforced polymer composites manufactured through compounding and injection molding, the use of internal reinforcing structures, such as ribs, is essential. This study proposes a cost-effective, data-driven approach to parametrize and optimize rib placement within automotive tailgate components. The primary objective is to maximize structural stiffness, evaluated with industry-standard testing methods for tailgate components, while adhering to mass constraints. Rib structures are parametrized with a focus on simplicity to reduce data requirements, accounting for manufacturing constraints inherent to injection molding and maintaining permutation invariance of rib designs. Given the high cost of evaluating variety of rib configurations, Bayesian optimization is applied for efficient data utilization. Gaussian process regression is used as a surrogate model to predict structural stiffness, based on finite element analysis data from various rib configurations. The optimized design is then fabricated as full-scale prototypes through injection molding, and their performance is validated against numerical predictions. This approach exemplifies a practical, data-driven methodology for designing rib structures in complex industrial components, integrating computational design with manufacturing processes.</div></div>","PeriodicalId":16148,"journal":{"name":"Journal of Manufacturing Processes","volume":"134 ","pages":"Pages 739-748"},"PeriodicalIF":6.1,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143131948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimal positioning of reference holes in forged turbine blades under adaptive point cloud registration based on robotic arm

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-31 DOI: 10.1016/j.jmapro.2024.12.067

Xingzhao Wang , Xu Zhang , Shuoyan Wang , Jianguo Zhang , Hongfei Yan , Limin Zhu

The complexity of forged turbine blade machining requirements brings challenges to point cloud registration in automated hole positioning. In this paper, a weighted point cloud registration method based on directional distance function is proposed, which converts various machining requirements into adaptive weight coefficients. In addition, a coarse registration method using the global bounding box information is proposed, which fuses the multi-feature parameters into the objective function, forming a mutual feedback mechanism between the point cloud segmentation and the coarse registration, and realizing the coarse registration under two-way high-quality point clouds. Combining the two methods, a hole positioning scheme of forged turbine blade based on robot arm is developed. In the test of two typical turbine blades, the maximum homogenization improvement of the blade body machining allowance reaches 26.9 %, and the maximum improvement of the qualified rate of the machining allowance reaches 11.6 %. The proportion exceeding the lower limit of the allowable machining allowance is reduced by 19.8 % at most, and the average optimization range of about 10 % is reached when dealing with unqualified blades, which is very close to the allowable machining allowance value. The average error of blade reference hole positioning is 0.420 μm, and the maximum error is 1.652 μm, which is two orders of magnitude lower than the allowable machining accuracy. The proposed method can provide reliable data support for automatic machining of robotic arm.

{"title":"Optimal positioning of reference holes in forged turbine blades under adaptive point cloud registration based on robotic arm","authors":"Xingzhao Wang , Xu Zhang , Shuoyan Wang , Jianguo Zhang , Hongfei Yan , Limin Zhu","doi":"10.1016/j.jmapro.2024.12.067","DOIUrl":"10.1016/j.jmapro.2024.12.067","url":null,"abstract":"<div><div>The complexity of forged turbine blade machining requirements brings challenges to point cloud registration in automated hole positioning. In this paper, a weighted point cloud registration method based on directional distance function is proposed, which converts various machining requirements into adaptive weight coefficients. In addition, a coarse registration method using the global bounding box information is proposed, which fuses the multi-feature parameters into the objective function, forming a mutual feedback mechanism between the point cloud segmentation and the coarse registration, and realizing the coarse registration under two-way high-quality point clouds. Combining the two methods, a hole positioning scheme of forged turbine blade based on robot arm is developed. In the test of two typical turbine blades, the maximum homogenization improvement of the blade body machining allowance reaches 26.9 %, and the maximum improvement of the qualified rate of the machining allowance reaches 11.6 %. The proportion exceeding the lower limit of the allowable machining allowance is reduced by 19.8 % at most, and the average optimization range of about 10 % is reached when dealing with unqualified blades, which is very close to the allowable machining allowance value. The average error of blade reference hole positioning is 0.420 μm, and the maximum error is 1.652 μm, which is two orders of magnitude lower than the allowable machining accuracy. The proposed method can provide reliable data support for automatic machining of robotic arm.</div></div>","PeriodicalId":16148,"journal":{"name":"Journal of Manufacturing Processes","volume":"134 ","pages":"Pages 285-298"},"PeriodicalIF":6.1,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143132197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High-speed and high-fidelity prediction of residual stress field distribution in micro-forging using a physical-translated cGAN

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-31 DOI: 10.1016/j.jmapro.2024.12.060

Bin Shen , Siyu Jin , Chenghan Wang , Jun Wu , Xingwei Xu , Sulin Chen

Micro-forging (MF) is a surface treatment that induces compressive residual stress (RS) near the surface to improve fatigue performance. However, achieving rapid prediction of RS fields remains a challenging task. In this work, a physical-translated condition generative adversarial network (PT-cGAN) was developed to predict RS fields of the MF process. The PT module translated the non-structured inputs of parameters into nominal RS fields with uniform size, which is suitable for cGAN module. Then the cGAN was trained by the nominal RS fields and finite element (FE) results which used as ground truth. The prediction time of PT-cGAN model has decreased from several hours (FE methods) to a few minutes, with an RS field accuracy (SSIM) of 0.96 and an RS curve accuracy (

R^{²}

) of 0.99. Furthermore, it is attractive to be used for real-time monitoring and parameter optimization.

引用次数: 0

A denoising and restoration method of weld laser stripe image for robotic multi-layer multi-pass welding based on generative adversarial networks

IF 6.1 1区工程技术 Q1 ENGINEERING, MANUFACTURING

Journal of Manufacturing Processes

Pub Date : 2025-01-17 DOI: 10.1016/j.jmapro.2024.12.001

Hui Xu , Yingjie Guo , Huiyue Dong , Minghua Zhu , Hanling Wu , Yinglin Ke

Obtaining clean, intact, and clear laser stripe images from weld laser stripe images with noise is a key issue in robot welding systems based on laser vision sensors, especially for robotic multi-layer multi-pass welding. However, existing methods typically require image pairs, consisting of images with noise and corresponding images without noise, which are very difficult to obtain. Meanwhile, methods that do not require image pairs suffer from low accuracy. Therefore, a model called DARM (denoising and restoration model) based on CycleGAN is proposed to denoise and restore laser stripe images for robotic multi-layer multi-pass welding in this paper. Firstly, a conditional generator assisted by a weld pass number is established to guide the generator in processing images by introducing a prior information. At the same time, the above generator is streamlined through a lightweight convolution module to reduce the model scale. Then, a double-ended discriminator is constructed to assess the authenticity and class of the processed images, enhancing the processing effect through additional class loss. Finally, experiments show that the RMSE, PSNR, and SSIM of DARM are 1.384, 25.457, and 0.977, respectively, and the average processing time is 9.0 ms, which can achieve accurate real-time denoising and restoration of multi-layer multi-pass weld laser stripe images. The proposed method does not require image pairs for learning, the processing effect is better than that of existing methods, and the model scale is significantly reduced.

{"title":"A denoising and restoration method of weld laser stripe image for robotic multi-layer multi-pass welding based on generative adversarial networks","authors":"Hui Xu , Yingjie Guo , Huiyue Dong , Minghua Zhu , Hanling Wu , Yinglin Ke","doi":"10.1016/j.jmapro.2024.12.001","DOIUrl":"10.1016/j.jmapro.2024.12.001","url":null,"abstract":"<div><div>Obtaining clean, intact, and clear laser stripe images from weld laser stripe images with noise is a key issue in robot welding systems based on laser vision sensors, especially for robotic multi-layer multi-pass welding. However, existing methods typically require image pairs, consisting of images with noise and corresponding images without noise, which are very difficult to obtain. Meanwhile, methods that do not require image pairs suffer from low accuracy. Therefore, a model called DARM (denoising and restoration model) based on CycleGAN is proposed to denoise and restore laser stripe images for robotic multi-layer multi-pass welding in this paper. Firstly, a conditional generator assisted by a weld pass number is established to guide the generator in processing images by introducing a prior information. At the same time, the above generator is streamlined through a lightweight convolution module to reduce the model scale. Then, a double-ended discriminator is constructed to assess the authenticity and class of the processed images, enhancing the processing effect through additional class loss. Finally, experiments show that the <em>RMSE</em>, <em>PSNR</em>, and <em>SSIM</em> of DARM are 1.384, 25.457, and 0.977, respectively, and the average processing time is 9.0 ms, which can achieve accurate real-time denoising and restoration of multi-layer multi-pass weld laser stripe images. The proposed method does not require image pairs for learning, the processing effect is better than that of existing methods, and the model scale is significantly reduced.</div></div>","PeriodicalId":16148,"journal":{"name":"Journal of Manufacturing Processes","volume":"133 ","pages":"Pages 1183-1195"},"PeriodicalIF":6.1,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143138186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0