Advances in Manufacturing最新文献

{"title":"Exoskeleton active assistance strategy for human muscle activation reduction during linear and circular walking","authors":"Wen-Tao Sheng,&nbsp;Ke-Yao Liang,&nbsp;Hai-Bin Tang","doi":"10.1007/s40436-024-00504-1","DOIUrl":"10.1007/s40436-024-00504-1","url":null,"abstract":"<div><p>The exoskeleton is employed to assist humans in various domains including military missions, rehabilitation, industrial operation, and activities of daily living (ADLs).Walking is a fundamental ADL, and exoskeletons are capable of reducing the activation and metabolism of lower extremity muscles through active assistance during walking. To improve the performance of active assistance strategy, this article proposes a framework using an active hip exoskeleton. Subsequently, it correlates to an already established Bayesian-based human gait recognition algorithm, with a particular focus on linear and circular walking within industrial and ADL contexts. In theorizing this strategy for exoskeletons, this study further reveals, in part, the activation characteristics of human hip muscles for the instruction and regulation of active assistance duration and onset timing. This proposed active assistance strategy provides new insights for enhancing the performance of assistive robots and facilitating human robot interaction within the context of ADLs.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"484 - 496"},"PeriodicalIF":4.2,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141188765","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":"Deep learning methods for roping defect analysis in aluminum alloy sheets: prediction and grading","authors":"Yuan-Zhe Hu,&nbsp;Ru-Xue Liu,&nbsp;Jia-Peng He,&nbsp;Guo-Wei Zhou,&nbsp;Da-Yong Li","doi":"10.1007/s40436-024-00499-9","DOIUrl":"10.1007/s40436-024-00499-9","url":null,"abstract":"<div><p>Roping is a severe band-like surface defect that occurs in deformed aluminum alloy sheets. Accurate roping prediction and rating are essential for industrial applications. Recently, the authors introduced an artificial neural network (ANN) model to efficiently forecast roping behavior across the thickness of large regions with texture gradients. In this study, the previously proposed ANN model for roping prediction is briefly reviewed, and a few-shot learning (FSL)-based method is developed for roping grading with limited samples. To consider the directionality of the roping patterns, the roping dataset constructed from experimental observations is transformed into the frequency domain for more compact characterization. A transfer-based FSL method is further presented for grade roping with manifold mixup regularization and the Sinkhorn mapping algorithm. A new component-focused representation is also implemented for data-processing, exploiting the close correlation between roping and power distribution in the frequency domain. The ultimate FSL method achieved an optimal accuracy of 95.65% in roping classification with only five training samples per class, outperforming four typical FSL methods. This FSL approach can be applied to grade the roping morphologies predicted by the ANN model. Consequently, the combination of prediction and grading using deep learning provides a new paradigm for roping analysis and control.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"576 - 590"},"PeriodicalIF":4.2,"publicationDate":"2024-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141100324","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 multi-objective optimization based on machine learning for dimension precision of wax pattern in turbine blade manufacturing","authors":"Jing Dai,&nbsp;Song-Zhe Xu,&nbsp;Chao-Yue Chen,&nbsp;Tao Hu,&nbsp;San-San Shuai,&nbsp;Wei-Dong Xuan,&nbsp;Jiang Wang,&nbsp;Zhong-Ming Ren","doi":"10.1007/s40436-024-00492-2","DOIUrl":"10.1007/s40436-024-00492-2","url":null,"abstract":"<div><p>Wax pattern fabrication in the investment casting of hollow turbine blades directly determines the dimension accuracy of subsequent casting, and therefore significantly affects the quality of final product. In this work, we develop a machine learning-based multi-objective optimization framework for improving dimension accuracy of wax pattern by optimizing its process parameters. We consider two optimization objectives on the dimension of wax pattern, i.e., the surface warpage and core offset. An active learning of Bayesian optimization is employed in data sampling to determine process parameters, and a validated numerical model of injection molding is used to compute objective results of dimension under varied process parameters. The collected dataset is then leveraged to train different machine learning models, and it turns out that the Gaussian process regression model performs best in prediction accuracy, which is then used as the surrogate model in the optimization framework. A genetic algorithm is employed to produce a non-dominated Pareto front using the surrogate model in searching, followed by an entropy weight method to select the most optimal solution from the Pareto front. The optimized set of process parameters is then compared to empirical parameters obtained from previous trial-and-error experiments, and it turns out that the maximum and average warpage results of the optimized solution decrease 26.0% and 20.2%, and the maximum and average errors of wall thickness compared to standard part decrease from 0.22 mm and 0.051 7 mm using empirical parameters to 0.10 mm and 0.035 6 mm using optimized parameters, respectively. This framework is demonstrated capable of addressing the challenge of dimension control arising in the wax pattern production, and it can be reliably deployed in varied types of turbine blades to significantly reduce the manufacturing cost of turbine blades.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"428 - 446"},"PeriodicalIF":4.2,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140966118","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":"Research progress of magnetorheological polishing technology: a review","authors":"Ming-Ming Lu,&nbsp;Ya-Kun Yang,&nbsp;Jie-Qiong Lin,&nbsp;Yong-Sheng Du,&nbsp;Xiao-Qin Zhou","doi":"10.1007/s40436-024-00490-4","DOIUrl":"10.1007/s40436-024-00490-4","url":null,"abstract":"<div><p>As an essential link in ultra-precision machining technology, various new surface polishing technologies and processes have always attracted continuous in-depth research and exploration by researchers. As a new research direction of ultra-precision machining technology, magnetorheological polishing technology has become an important part. The polishing materials and magnetorheological fluids involved in the process of magnetorheological polishing are reviewed. The polishing principle, equipment development, theoretical research and process research of magnetorheological polishing technologies, such as the wheel-type, cluster-type, ball-type, disc-type and other types, derived from the magnetorheological polishing process, are reviewed. The above magnetorheological polishing technologies are analyzed and compared from the perspective of processing accuracy, processing efficiency and application range. The curvature adaptive magnetorheological polishing technology with a circulatory system is proposed to achieve high efficiency and high-quality polishing.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 4","pages":"642 - 678"},"PeriodicalIF":4.2,"publicationDate":"2024-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s40436-024-00490-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140967439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accelerating the solving of mechanical equilibrium caused by lattice misfit through deep learning method","authors":"Chen-Xi Guo,&nbsp;Hui-Ying Yang,&nbsp;Rui-Jie Zhang","doi":"10.1007/s40436-024-00494-0","DOIUrl":"10.1007/s40436-024-00494-0","url":null,"abstract":"<div><p>Precipitation is a common phenomenon that occurs during heat treatments. There is internal stress around the precipitate owing to the lattice misfit between the precipitate and matrix. This internal stress has a significant influence not only on the precipitation kinetics but also on the material properties. The misfit stress can be obtained by numerically solving the mechanical equilibrium equations. However, this process is complex and time-consuming. We developed a new approach based on deep learning to accelerate the solution process. The training data were first generated by a phase-field model coupled with elastic mechanical equilibrium equations, which were solved using the finite difference method. The obtained precipitate morphologies and corresponding stress distributions were input data for training the physics-informed (PI) UNet model. The well-trained PI-UNet model can then be applied to predicting stress distributions with the precipitate morphology as the input. Prediction accuracy and efficiency are discussed in this study. The results showed that the PI-UNet model was an appropriate approach for quickly predicting the misfit stress between the precipitate and matrix.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"512 - 521"},"PeriodicalIF":4.2,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140568400","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":"Fabrication of micro holes using low power fiber laser: surface morphology, modeling and soft-computing based optimization","authors":"Tuhin Kar,&nbsp;Swarup S. Deshmukh,&nbsp;Arjyajyoti Goswami","doi":"10.1007/s40436-024-00484-2","DOIUrl":"10.1007/s40436-024-00484-2","url":null,"abstract":"<div><p>Fiber laser micromachining is found extensive applications at industrial level because it is cheap and simple to use. Due to its high strength and low conductivity titanium is difficult to machine with conventional methods. In this investigation, micro holes were fabricated using a 30 W fiber laser on 2 mm thick <i>α</i>-titanium (Grade 2) and the process parameters were optimized through response surface methodology (RSM) and teaching learning-based optimization (TLBO) approach. Experimental runs were designed as per rotatable central composite design (RCCD). Material removal rate (MRR), hole circularity (HC), deviation in diameter (DEV) and heat affected zone (HAZ) were selected as output. A third-order polynomial prediction model was established using RSM. Analysis of variance (ANOVA) suggested that the developed model was 93.5% accurate. The impact of input factors on responses were studied by 3D surface plots. RSM desirability indicates that optimum micro drilling conditions are scan speed 275.43 mm/s, frequency 24.61 kHz, power 36.23% and number of passes 49.75. TLBO indicates that optimum micro drilling conditions are scan speed 100 mm/s, frequency 20 kHz, power 20% and number of passes 50. Comparison between RSM and TLBO suggested that TLBO provided better optimization results. Surface morphology of the fabricated micro holes were analyzed with scanning electron microscopy (SEM).</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 4","pages":"810 - 831"},"PeriodicalIF":4.2,"publicationDate":"2024-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140568314","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":"Understanding microstructure-property relationships of HPDC Al-Si alloy based on machine learning and crystal plasticity simulation","authors":"Qiang-Qiang Zhai,&nbsp;Zhao Liu,&nbsp;Ping Zhu","doi":"10.1007/s40436-024-00488-y","DOIUrl":"10.1007/s40436-024-00488-y","url":null,"abstract":"<div><p>Al-Si alloys manufactured via high-pressure die casting (HPDC) are suitable for a wide range of applications. However, the heterogeneous microstructure and unpredictable pore distribution of Al-Si high-pressure die castings result in significant variations in the mechanical properties, thus leading to a complicated microstructure-property relationship that is difficult to capture. Hence, a computational framework incorporating machine learning and crystal plasticity method is proposed. This framework aims to provide a systematic and comprehensive understanding of this relationship and enable the rapid prediction of macroscopic mechanical properties based on the microstructure. Firstly, we select eight variables that can effectively characterize the microstructural features and then obtain their statistical information. Subsequently, based on 160 samples obtained via the Latin hypercube sampling method, representative volume elements are constructed, and the crystal plasticity fast Fourier transformation method is executed to obtain the macroscopic mechanical properties. Next, the yield strength, elastic modulus, strength coefficient, and strain-hardening exponent are used to characterize the stress-strain curve, and Gaussian process regression models and microstructural variables are developed. Finally, sensitivity and univariate analyses based on these machine-learning models are performed to obtain insights into the microstructure-property relationships of the HPDC Al-Si alloy. The results show that the Gaussian process regression models exhibit high accuracy (<i>R</i>² greater than 0.84), thus confirming the viability of the proposed method. The results of sensitivity analysis indicate that the pore size exerts the most significant effect on the mechanical properties. Furthermore, the proposed framework can not only be transferred to other alloys but also be employed for material design.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 3","pages":"497 - 511"},"PeriodicalIF":4.2,"publicationDate":"2024-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140568571","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":"Sensitivity analysis of near solidus forming (NSF) process with digital twin using Taguchi approach","authors":"Muhammad Sajjad,&nbsp;Javier Trinidad,&nbsp;Gorka Plata,&nbsp;Jokin Lozares,&nbsp;Joseba Mendiguren","doi":"10.1007/s40436-024-00482-4","DOIUrl":"10.1007/s40436-024-00482-4","url":null,"abstract":"<div><p>Forging at near solidus material state takes advantage of the high ductility of the material at the semi solid or soft-solid state while keeping most of the mechanical properties of a forged part. The technology is at maturity level ready for its industrial implementation. However, to implement the process for complex cases the development of an appropriate digital twin (DT) is necessary. While developing a material model, a strong experimental and DT is necessary to be able to evaluate the accuracy of the model. Aimed at having a reliable DT under control, for future material model validations, the main objective of this work is to develop a sensitivity analysis of three NSF industrial cases such as Hook, R spindle and H spindle to develop an adequate DT calibration procedure. Firstly, the benchmark experimentation process parameter noise and experimentation boundary conditions (BCs) parameter uncertainty are identified. Secondly, the three industrial benchmark DTs are constructed, and a Taguchi design of experiments (DoEs) methodology is put in place to develop the sensitivity analysis. Finally, after simulations the results are critically evaluated and the sensitivity of each benchmark to the different inputs (process parameter noise and BC parameter uncertainty) is studied. Lastly, the optimum DT calibration procedure is developed. Overall, the results stated the minimum impact of the material model in terms of dies filling. Nevertheless, even if the material model is the highest impacting factor for the forging forces other inputs, such as heat transfer and friction must be under control first.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"13 2","pages":"322 - 336"},"PeriodicalIF":4.2,"publicationDate":"2024-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s40436-024-00482-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140568329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Single-track geometrical characteristics under different energy input and mass addition in coaxial laser cladding","authors":"Yan-Hua Bian,&nbsp;Chong-Xin Tian,&nbsp;Bo Chen,&nbsp;Bin-Xin Dong,&nbsp;Shao-Xia Li,&nbsp;Zhi-Yong Li,&nbsp;Yang-Rui Nan,&nbsp;Xiu-Li He,&nbsp;Gang Yu","doi":"10.1007/s40436-023-00478-6","DOIUrl":"10.1007/s40436-023-00478-6","url":null,"abstract":"<div><p>To provide a broad processing window with a high deposition rate, a comprehensive analysis of single-track geometrical characteristics over a wide range of laser energies and mass inputs in laser cladding is necessary. The formation of a single cladding track of Inconel 718 on a substrate by coaxial laser cladding, with a wide range of laser power from 1 200 W to 3 900 W and a powder feeding rate from 5 g/min to 35 g/min, was studied from both theoretical and experimental points of view. A quantitative model of powder concentration distribution was developed based on the powder transport morphology obtained by high-speed photography. Linear regression models were established between nine geometrical characteristics and the combined process parameters of laser power and powder feeding rate, written as <i>P</i>^<i>α</i><i>F</i>^<i>β</i>, to quantitatively analyze the geometrical characteristics of the clad. These were confirmed by large correlation coefficients and analysis of residuals. From the findings we deduced that more energy input enhanced the outward direction of Marangoni convection, leading to the melt pool undergoing evolution from shallow dilution and flat dilution to fluctuating dilution. An almost linear relationship was found between the cladding width, <i>W</i>, and the laser power, indicating that laser energy accumulation was a major factor in the evolution of <i>W</i>. The increase ratio of the cladding height, <i>h</i>_c, ranged from 640% to 360% along with an increase in the powder feeding rate, implying that the evolution of <i>h</i>_c, was dominated by the powder feeding rate. The total area of the cross-section, <i>A</i>; the area of the clad, <i>A</i>_c; the area of the molten substrate, <i>A</i>_m; the total height of the cross-section, <i>H</i>; the penetration depth, <i>h</i>_m; the dilution ratio, <i>D</i>; and the wetting angle, <i>θ</i>, were determined by a complex coupling of energy input and mass accumulation, and they are proportional to <i>P</i>^0.5<i>F</i>^0.2, <i>P</i>^0.2<i>F</i>^0.5, <i>P</i>^0.5/<i>F</i>^0.2, <i>P</i>^0.3<i>F</i>, <i>P</i>^0.5/<i>F</i>^0.2, <i>P</i>^0.2/<i>F</i>^0.2, and <i>P</i>^0.2/<i>F</i>^0.2, respectively. This research aims to provide general knowledge on the influence of energy input and mass addition on the geometrical characteristics of the clad and its related influence mechanism. Such information could provide a reference and basis for promoting the practical application of laser cladding technology.</p></div>","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"12 4","pages":"742 - 763"},"PeriodicalIF":4.2,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140568569","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":"RETRACTED ARTICLE: Research on parameter identification of fracture model for titanium alloy under wide stress triaxiality based on machine learning","authors":"Rui Feng,&nbsp;Ming-He Chen,&nbsp;Ning Wang,&nbsp;Lan-Sheng Xie","doi":"10.1007/s40436-024-00487-z","DOIUrl":"10.1007/s40436-024-00487-z","url":null,"abstract":"","PeriodicalId":7342,"journal":{"name":"Advances in Manufacturing","volume":"14 3","pages":"789 - 789"},"PeriodicalIF":3.9,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140310981","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}