Advances in Manufacturing最新文献

{"title":"Cutting performance and effectiveness evaluation on organic monolayer embrittlement in ductile metal precision machining","authors":"Chao-Jun Zhang,&nbsp;Song-Qing Li,&nbsp;Pei-Xuan Zhong,&nbsp;Fei-Fan Zhang,&nbsp;Wen-Jun Deng","doi":"10.1007/s40436-024-00513-0","DOIUrl":"10.1007/s40436-024-00513-0","url":null,"abstract":"<div><p>In the traditional machining field, the addition of cutting fluid can appropriately reduce cutting forces, dissipate cutting heat, and facilitate the machining process. However, the use of cutting fluids has environmental implications. Recently, a phenomenon known as organic monolayer embrittlement (OME) has been proposed, which could address this issue. OME can reduce cutting forces, enhance surface quality, and improve machining performance without the need for cutting fluids, particularly noticeable in ductile metals like pure copper. This study conducted micro-cutting experiments on pure copper to investigate the microstructural features, cutting performance, chip flow patterns, and the effectiveness of OME. The results indicate that OME alters chip flow patterns from sinuous flow to segmented quasi-periodic micro-fracture flow, resulting in a 42% and 63% reduction in cutting forces for copper materials with different initial hardness. This phenomenon significantly improves surface quality, diminishes surface defects caused by adhesion, and effectively reduces work hardening layers. The study also demonstrates that OME is a physical phenomenon closely related to the adsorption properties of organic catalytic agents and van der Waals interactions. Materials with higher initial hardness exhibit less pronounced OME due to a sufficiently high grain boundary density, impeding dislocation movement during shear deformation and causing a local stress increase at the free surface of the chip. This leads to a change in chip flow patterns, improving machining performance, analogous to the adsorption effect of organic catalytic agents.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"13 2","pages":"395 - 412"},"PeriodicalIF":4.2,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141570929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Structural design and simulation of PDMS/SiC functionally graded substrates for applications in flexible hybrid electronics","authors":"Jian-Jun Yang,&nbsp;Yin-Bao Song,&nbsp;Zheng-Hao Li,&nbsp;Luo-Wei Wang,&nbsp;Shuai Shang,&nbsp;Hong-Ke Li,&nbsp;Hou-Chao Zhang,&nbsp;Rui Wang,&nbsp;Hong-Bo Lan,&nbsp;Xiao-Yang Zhu","doi":"10.1007/s40436-024-00510-3","DOIUrl":"10.1007/s40436-024-00510-3","url":null,"abstract":"<div><p>Flexible hybrid electronics possess significant potential for applications in biomedical and wearable devices due to their advantageous properties of good ductility, low mass, and portability. However, they often exhibit a substantial disparity in elastic modulus between the flexible substrate and rigid components. This discrepancy can result in damage to the rigid components themselves and detachment from the substrate when subjected to tensile, bending, or other loads. Consequently, it diminishes the lifespan of flexible hybrid electronics and restricts their broader-scale application. Therefore, this paper proposes a polydimethylsiloxane (PDMS)/SiC functionally graded flexible substrate based on variable stiffness properties. Initially, ABAQUS simulation is employed to analyze how variations in stiffness impact the stress-strain behavior of PDMS/SiC functionally graded flexible substrates. Subsequently, we propose a multi-material 3D printing process for fabricating PDMS/SiC functionally graded flexible substrates and develop an advanced multi-material 3D printing equipment to facilitate this process. Tensile specimens with the functional gradient of PDMS/SiC are successfully fabricated and subjected to mechanical testing. The results from the tensile tests demonstrate a significant enhancement in the tensile rate (from 21.6% to 35%) when utilizing the PDMS/SiC functionally graded flexible substrate compared to those employing only PDMS substrate. Furthermore, the application of PDMS/SiC functional gradient flexible substrate exhibits remarkable bending and tensile properties in stretchable electronics and skin electronics domains. The integrated fabrication approach of the PDMS/SiC functionally graded flexible substrate structure presents a novel high-performance solution along with its corresponding 3D printing methodology for stretchable flexible electronics, skin electronics, and other related fields.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"13 2","pages":"413 - 429"},"PeriodicalIF":4.2,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141570930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Separation of fringe patterns in fast deflectometric measurement of transparent optical elements based on neural network-assisted fast iterative filtering method","authors":"Ting Chen,&nbsp;Pei-De Yang,&nbsp;Xiang-Chao Zhang,&nbsp;Wei Lang,&nbsp;Yu-Nuo Chen,&nbsp;Min Xu","doi":"10.1007/s40436-024-00509-w","DOIUrl":"10.1007/s40436-024-00509-w","url":null,"abstract":"<div><p>Transparent optical elements play a significant role in optical imaging and sensing, and the form qualities of these elements are critical to the functionalities of opto-electrical equipment. Therefore, rapid measurement of advanced transparent optical devices is urgently needed. Deflectometry, as a commonly used measurement method, has broad applications in form measurement. However, there are some challenges in the reflective deflectometric measurement of transparent elements, such as fringe superposition, low reflectivity, and non-uniform backgrounds, which severely affect the measurement accuracy. To address these issues, a single-frame fringe separation method is proposed for the deflectometric measurement of transparent elements. A fast iterative filtering method is utilized for coarse fringe separation and a convolutional neural network is adopted to solve the information leakage and incomplete fringe separation. The construction of the neural network involves improving and refining the filtering method to achieve precise separation of fringes. The proposed method achieves fringe separation and forms reconstruction of the upper and lower surfaces. Through simulations and experiments, the effectiveness and robustness of the proposed method are demonstrated, and the measurement accuracy can achieve 65 nm root-of-mean-squared-error (RMSE).</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"13 3","pages":"493 - 510"},"PeriodicalIF":3.8,"publicationDate":"2024-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141546757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A data-driven approach for predicting the fatigue life and failure mode of self-piercing rivet joints","authors":"Jian Wang,&nbsp;Qiu-Ren Chen,&nbsp;Li Huang,&nbsp;Chen-Di Wei,&nbsp;Chao Tong,&nbsp;Xian-Hui Wang,&nbsp;Qing Liu","doi":"10.1007/s40436-024-00498-w","DOIUrl":"10.1007/s40436-024-00498-w","url":null,"abstract":"<div><p>In lightweight automotive vehicles, the application of self-piercing rivet (SPR) joints is becoming increasingly widespread. Considering the importance of automotive service performance, the fatigue performance of SPR joints has received considerable attention. Therefore, this study proposes a data-driven approach to predict the fatigue life and failure modes of SPR joints. The dataset comprises three specimen types: cross-tensile, cross-peel, and tensile-shear. To ensure data consistency, a finite element analysis was employed to convert the external loads of the different specimens. Feature selection was implemented using various machine-learning algorithms to determine the model input. The Gaussian process regression algorithm was used to predict fatigue life, and its performance was compared with different kernel functions commonly used in the field. The results revealed that the Matern kernel exhibited an exceptional predictive capability for fatigue life. Among the data points, 95.9% fell within the 3-fold error band, and the remaining 4.1% exceeded the 3-fold error band owing to inherent dispersion in the fatigue data. To predict the failure location, various tree and artificial neural network (ANN) models were compared. The findings indicated that the ANN models slightly outperformed the tree models. The ANN model accurately predicts the failure of joints with varying dimensions and materials. However, minor deviations were observed for the joints with the same sheet. Overall, this data-driven approach provided a reliable predictive model for estimating the fatigue life and failure location of SPR joints.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"538 - 555"},"PeriodicalIF":4.2,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A machine learning-based calibration method for strength simulation of self-piercing riveted joints","authors":"Yu-Xiang Ji,&nbsp;Li Huang,&nbsp;Qiu-Ren Chen,&nbsp;Charles K. S. Moy,&nbsp;Jing-Yi Zhang,&nbsp;Xiao-Ya Hu,&nbsp;Jian Wang,&nbsp;Guo-Bi Tan,&nbsp;Qing Liu","doi":"10.1007/s40436-024-00502-3","DOIUrl":"10.1007/s40436-024-00502-3","url":null,"abstract":"<div><p>This paper presents a new machine learning-based calibration framework for strength simulation models of self-piercing riveted (SPR) joints. Strength simulations were conducted through the integrated modeling of SPR joints from process to performance, while physical quasi-static tensile tests were performed on combinations of DP600 high-strength steel and 5754 aluminum alloy sheets under lap-shear loading conditions. A sensitivity study of the critical simulation parameters (e.g., friction coefficient and scaling factor) was conducted using the controlled variables method and Sobol sensitivity analysis for feature selection. Subsequently, machine-learning-based surrogate models were used to train and accurately represent the mapping between the detailed joint profile and its load-displacement curve. Calibration of the simulation model is defined as a dual-objective optimization task to minimize errors in key load displacement features between simulations and experiments. A multi-objective genetic algorithm (MOGA) was chosen for optimization. The three combinations of SPR joints illustrated the effectiveness of the proposed framework, and good agreement was achieved between the calibrated models and experiments.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"465 - 483"},"PeriodicalIF":4.2,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Numerical/experimental investigation of the effect of the laser treatment on the thickness distribution of a magnesium superplastically formed part","authors":"Angela Cusanno,&nbsp;Pasquale Guglielmi,&nbsp;Donato Sorgente,&nbsp;Gianfranco Palumbo","doi":"10.1007/s40436-024-00497-x","DOIUrl":"10.1007/s40436-024-00497-x","url":null,"abstract":"<div><p>The growing need for high-performance components in terms of shape and mechanical properties encourages the adoption of integrated technological solutions. In the present work, a novel methodology for affecting the superplastic behaviour and, in turn, the thickness distribution of magnesium alloy components is proposed. Through heat treatments using a CO₂ laser, the grain size was locally changed, thus modifying the superplastic behaviour in a predefined area of the blank. Both the grain coarsening produced by the laser heat treatment and the superplastic forming of the heat treated blank were simulated using a finite element model, which allowed to set the related process parameters for the manufacturing of the investigated case study (a truncated cone). The thermal finite element model of the laser heat treatment, calibrated using the experimental temperature evolutions acquired in specific areas during the heat treatment, was used to evaluate the influence of process parameters on the grain size evolution. The laser heat treatment was able to significantly promote the grain growth, increasing the mean grain size from about 8 µm to twice (about 17 µm). The resulting grain size distributions were implemented in the mechanical finite element model of the superplastic forming process and the combination of laser parameters which allowed to obtain the most uniform thickness distribution on the final component was finally experimentally reproduced and measured for validation purposes. Even in the case of the laboratory scale application, characterised by quite small dimensions, the proposed approach revealed to be effective, to improving the thinning factor (<i>t</i>_MIN/<i>t</i>_AVG) of the formed part from 0.85 to 0.89, and providing an increase in the thickness uniformity of about 4.7%.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"13 2","pages":"284 - 302"},"PeriodicalIF":4.2,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141506046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CMAGAN: classifier-aided minority augmentation generative adversarial networks for industrial imbalanced data and its application to fault prediction","authors":"Wen-Jie Wang,&nbsp;Zhao Liu,&nbsp;Ping Zhu","doi":"10.1007/s40436-024-00496-y","DOIUrl":"10.1007/s40436-024-00496-y","url":null,"abstract":"<div><p>Class imbalance is a common characteristic of industrial data that adversely affects industrial data mining because it leads to the biased training of machine learning models. To address this issue, the augmentation of samples in minority classes based on generative adversarial networks (GANs) has been demonstrated as an effective approach. This study proposes a novel GAN-based minority class augmentation approach named classifier-aided minority augmentation generative adversarial network (CMAGAN). In the CMAGAN framework, an outlier elimination strategy is first applied to each class to minimize the negative impacts of outliers. Subsequently, a newly designed boundary-strengthening learning GAN (BSLGAN) is employed to generate additional samples for minority classes. By incorporating a supplementary classifier and innovative training mechanisms, the BSLGAN focuses on learning the distribution of samples near classification boundaries. Consequently, it can fully capture the characteristics of the target class and generate highly realistic samples with clear boundaries. Finally, the new samples are filtered based on the Mahalanobis distance to ensure that they are within the desired distribution. To evaluate the effectiveness of the proposed approach, CMAGAN was used to solve the class imbalance problem in eight real-world fault-prediction applications. The performance of CMAGAN was compared with that of seven other algorithms, including state-of-the-art GAN-based methods, and the results indicated that CMAGAN could provide higher-quality augmented results.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"603 - 618"},"PeriodicalIF":4.2,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving RSW nugget diameter prediction method: unleashing the power of multi-fidelity neural networks and transfer learning","authors":"Zhong-Jie Yue,&nbsp;Qiu-Ren Chen,&nbsp;Zu-Guo Bao,&nbsp;Li Huang,&nbsp;Guo-Bi Tan,&nbsp;Ze-Hong Hou,&nbsp;Mu-Shi Li,&nbsp;Shi-Yao Huang,&nbsp;Hai-Long Zhao,&nbsp;Jing-Yu Kong,&nbsp;Jia Wang,&nbsp;Qing Liu","doi":"10.1007/s40436-024-00503-2","DOIUrl":"10.1007/s40436-024-00503-2","url":null,"abstract":"<div><p>This research presents an innovative approach to accurately predict the nugget diameter in resistance spot welding (RSW) by leveraging machine learning and transfer learning methods. Initially, low-fidelity (LF) data were obtained through finite element numerical simulation and design of experiments (DOEs) to train the LF machine learning model. Subsequently, high-fidelity (HF) data were collected from RSW process experiments and used to fine-tune the LF model by transfer learning techniques. The accuracy and generalization performance of the models were thoroughly validated. The results demonstrated that combining different fidelity datasets and employing transfer learning could significantly improve the prediction accuracy while minimize the costs associated with experimental trials, and provide an effective and valuable method for predicting critical process parameters in RSW.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"409 - 427"},"PeriodicalIF":4.2,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data-driven approach to predict the fatigue properties of ferrous metal materials using the cGAN and machine-learning algorithms","authors":"Si-Geng Li,&nbsp;Qiu-Ren Chen,&nbsp;Li Huang,&nbsp;Min Chen,&nbsp;Chen-Di Wei,&nbsp;Zhong-Jie Yue,&nbsp;Ru-Xue Liu,&nbsp;Chao Tong,&nbsp;Qing Liu","doi":"10.1007/s40436-024-00491-3","DOIUrl":"10.1007/s40436-024-00491-3","url":null,"abstract":"<div><p>The stress-life curve (S–N) and low-cycle strain-life curve (E–N) are the two primary representations used to characterize the fatigue behavior of a material. These material fatigue curves are essential for structural fatigue analysis. However, conducting material fatigue tests is expensive and time-intensive. To address the challenge of data limitations on ferrous metal materials, we propose a novel method that utilizes the Random Forest Algorithm and transfer learning to predict the S–N and E–N curves of ferrous materials. In addition, a data-augmentation framework is introduced using a conditional generative adversarial network (cGAN) to overcome data deficiencies. By incorporating the cGAN-generated data, the accuracy (<i>R</i>²) of the Random Forest Algorithm-trained model is improved by 0.3–0.6. It is proven that the cGAN can significantly enhance the prediction accuracy of the machine-learning model and balance the cost of obtaining fatigue data from the experiment.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"447 - 464"},"PeriodicalIF":4.2,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141254318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Laser welding monitoring techniques based on optical diagnosis and artificial intelligence: a review","authors":"Yi-Wei Huang,&nbsp;Xiang-Dong Gao,&nbsp;Perry P. Gao,&nbsp;Bo Ma,&nbsp;Yan-Xi Zhang","doi":"10.1007/s40436-024-00493-1","DOIUrl":"10.1007/s40436-024-00493-1","url":null,"abstract":"<div><p>Laser welding is an efficient and precise joining method widely used in various industries. Real-time monitoring of the welding process is important for improving the quality of the weld products. This study provides an overview of the optical diagnostics of the laser welding process. The common welding defects and their formation mechanisms are described, starting with an introduction to the principles of laser welding. Optical signal sources are divided into radiated and external active lights, and different monitoring systems are summarized and classified. Also, the applications of artificial intelligence techniques in data processing, weld defect prediction and classification, and adaptive welding control are summarized. Finally, future research and challenges in real-time laser welding monitoring technology based on optical diagnostics are discussed. This study demonstrated that optical diagnostic techniques could acquire substantial information about the laser welding process and help identify welding defects.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"13 2","pages":"337 - 361"},"PeriodicalIF":4.2,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141254142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}