CIRP Journal of Manufacturing Science and Technology最新文献_第2页

Temperature field characteristics in rotary longitudinal-torsional ultrasonic machining of unidirectional carbon fiber reinforced polymer (CFRP) 单向碳纤维增强聚合物（CFRP）旋转纵扭超声加工温度场特征

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2026-01-07 DOI: 10.1016/j.cirpj.2025.12.019

Ziqiang Zhang , Feng Jiao , Yuanxiao Li

Enhancing the drilling quality of carbon fiber reinforced polymer (CFRP) holds significant importance for advancing its application in aerospace and other fields. The temperature during CFRP core drilling critically impacts hole quality, and incorporating ultrasonic vibration during machining can effectively reduce this temperature. Predicting workpiece temperature is vital for selecting process parameters and enhancing hole quality of CFRP core drilling. However, current research on rotary ultrasonic machining (RUM) of CFRP predominantly focuses on experimental investigations, which relatively few reports on the temperature prediction. Utilizing the benefits of longitudinal-torsional ultrasonic vibration to reduce temperature, this paper establishes a temperature prediction model for rotary longitudinal-torsional ultrasonic machining (RLTUM) of unidirectional CFRP and analyzes the temperature field characteristics. Initially, the heat source properties in the machining process are analyzed, followed by an examination of heat transfer characteristics using the heat source method. Furthermore, the surface morphology of CFRP hole wall under different machining conditions was compared. Experimental verification confirms the model’s accuracy, demonstrating its capability to predict temperature evolution and variation trends with process parameters. The peak temperature prediction errors perpendicular and parallel to the fiber direction are 7.09–12.63 % and 5.54–14.36 %, respectively. Implementing longitudinal-torsional ultrasonic vibration reduces temperature during the core drilling process. As the fiber orientation angle increases, the corresponding peak temperature decreases, and the peak temperatures for different fiber orientation angles are symmetrical. This model serves as a valuable reference for selecting process parameters to improve CFRP drilling quality.

提高碳纤维增强聚合物（CFRP）的钻孔质量对推进其在航空航天等领域的应用具有重要意义。CFRP钻芯过程中的温度对孔质量影响很大，在加工过程中加入超声振动可以有效降低该温度。预测工件温度对CFRP钻芯工艺参数的选择和提高孔质量具有重要意义。然而，目前对CFRP旋转超声加工（RUM）的研究主要集中在实验研究上，而对温度预测的研究相对较少。利用超声纵扭振动降低温度的优势，建立了单向碳纤维复合材料旋转纵扭超声加工（RLTUM）的温度预测模型，并分析了温度场特征。首先，分析了加工过程中的热源特性，然后使用热源法检查了传热特性。并对不同加工条件下CFRP孔壁的表面形貌进行了比较。实验验证了该模型的准确性，证明了该模型能够预测温度随工艺参数的变化趋势。垂直和平行于光纤方向的峰值温度预测误差分别为7.09 ~ 12.63 %和5.54 ~ 14.36 %。在钻取岩心的过程中，实施纵向-扭转超声振动可以降低温度。随着纤维取向角的增大，相应的峰值温度降低，且不同取向角的峰值温度是对称的。该模型为提高CFRP钻孔质量选择工艺参数提供了有价值的参考。

{"title":"Temperature field characteristics in rotary longitudinal-torsional ultrasonic machining of unidirectional carbon fiber reinforced polymer (CFRP)","authors":"Ziqiang Zhang , Feng Jiao , Yuanxiao Li","doi":"10.1016/j.cirpj.2025.12.019","DOIUrl":"10.1016/j.cirpj.2025.12.019","url":null,"abstract":"<div><div>Enhancing the drilling quality of carbon fiber reinforced polymer (CFRP) holds significant importance for advancing its application in aerospace and other fields. The temperature during CFRP core drilling critically impacts hole quality, and incorporating ultrasonic vibration during machining can effectively reduce this temperature. Predicting workpiece temperature is vital for selecting process parameters and enhancing hole quality of CFRP core drilling. However, current research on rotary ultrasonic machining (RUM) of CFRP predominantly focuses on experimental investigations, which relatively few reports on the temperature prediction. Utilizing the benefits of longitudinal-torsional ultrasonic vibration to reduce temperature, this paper establishes a temperature prediction model for rotary longitudinal-torsional ultrasonic machining (RLTUM) of unidirectional CFRP and analyzes the temperature field characteristics. Initially, the heat source properties in the machining process are analyzed, followed by an examination of heat transfer characteristics using the heat source method. Furthermore, the surface morphology of CFRP hole wall under different machining conditions was compared. Experimental verification confirms the model’s accuracy, demonstrating its capability to predict temperature evolution and variation trends with process parameters. The peak temperature prediction errors perpendicular and parallel to the fiber direction are 7.09–12.63 % and 5.54–14.36 %, respectively. Implementing longitudinal-torsional ultrasonic vibration reduces temperature during the core drilling process. As the fiber orientation angle increases, the corresponding peak temperature decreases, and the peak temperatures for different fiber orientation angles are symmetrical. This model serves as a valuable reference for selecting process parameters to improve CFRP drilling quality.</div></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":"65 ","pages":"Pages 145-162"},"PeriodicalIF":5.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927230","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}

引用次数: 0

Finite element modeling of indexable insert drilling processes in stainless steel 不锈钢可转位刀片钻孔过程的有限元建模

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2026-01-05 DOI: 10.1016/j.cirpj.2025.12.018

Mikel Etxebeste , Gorka Ortiz-de-Zarate , Homar Lopez-Hawa , Pedro J. Arrazola

Indexable insert drills play a crucial role in high-performance drilling, particularly for large-diameter holes and difficult-to-machine materials. Although FEM is a powerful tool for analyzing and optimizing drilling processes, limited research has focused on indexable insert drills, and the efficient simulation of large-diameter drills with complex cutting geometries remains a significant challenge. This study presents an optimized and computationally efficient FEM model for indexable insert drills, developed in AdvantEdge™ 3D, capable of predicting thermomechanical loads (thrust force, torque, stress, temperature) and chip morphology during drilling and redrilling of AISI 316 L stainless steel. The key innovation lies in a computational approach that significantly reduces simulation time while maintaining high predictive accuracy. The model incorporates a novel tool–workpiece configuration with a slotted workpiece that enables the drill to reach nominal feed rate immediately upon engagement, accelerating convergence toward thermomechanical steady-state. Model optimization was achieved through a systematic evaluation of the most influential input parameters, surpassing the capabilities of previous FEM approaches and providing new validated insight into drilling process modeling. A comprehensive sensitivity analysis of Johnson–Cook flow stress parameters, friction coefficients, and mesh size was performed to optimize both accuracy and computational efficiency. The model was experimentally validated through complete-drill tests (both inserts mounted) and novel single-insert tests (one insert mounted) across a wide range of cutting conditions, including redrilling with varying pilot hole diameters. The optimized model accurately predicts torque, thrust forces, and chip morphology (average error: 16 %), while providing detailed stress and temperature distributions. Thrust force underprediction remains the primary limitation, identified as originating from the central insert, where Build-Up Edge (BUE) formation was observed at low cutting speeds near the drill tip.

可转位镶钻在高性能钻孔中发挥着至关重要的作用，特别是对于大直径孔和难以加工的材料。虽然有限元分析是分析和优化钻孔工艺的有力工具，但有限的研究集中在可转位镶齿钻头上，并且具有复杂切削几何形状的大直径钻头的有效模拟仍然是一个重大挑战。本研究提出了一个优化的、计算效率高的可转位嵌套钻头有限元模型，该模型是在AdvantEdge™3D中开发的，能够预测AISI 316 L不锈钢在钻削和再钻削过程中的热机械载荷（推力、扭矩、应力、温度）和切屑形态。关键的创新在于一种计算方法，可以在保持高预测精度的同时显着减少模拟时间。该模型结合了一种新颖的工具-工件配置，具有开槽工件，使钻头在啮合后立即达到标称进给速率，加速了向热机械稳态的收敛。通过对最具影响力的输入参数进行系统评估，实现了模型优化，超越了之前FEM方法的能力，并为钻井过程建模提供了新的验证见解。对Johnson-Cook流动应力参数、摩擦系数和网格尺寸进行了综合敏感性分析，以优化精度和计算效率。该模型通过全钻测试（安装了两个钻头）和新型单钻头测试（安装了一个钻头）在各种切削条件下进行了实验验证，包括在不同的导孔直径下进行重钻。优化后的模型准确地预测了扭矩、推力和芯片形态（平均误差：16 %），同时提供了详细的应力和温度分布。推力预测不足仍然是主要的限制因素，主要原因是中心镶齿，在钻头尖端附近低切削速度下观察到积聚边缘（BUE）地层。

{"title":"Finite element modeling of indexable insert drilling processes in stainless steel","authors":"Mikel Etxebeste , Gorka Ortiz-de-Zarate , Homar Lopez-Hawa , Pedro J. Arrazola","doi":"10.1016/j.cirpj.2025.12.018","DOIUrl":"10.1016/j.cirpj.2025.12.018","url":null,"abstract":"<div><div>Indexable insert drills play a crucial role in high-performance drilling, particularly for large-diameter holes and difficult-to-machine materials. Although FEM is a powerful tool for analyzing and optimizing drilling processes, limited research has focused on indexable insert drills, and the efficient simulation of large-diameter drills with complex cutting geometries remains a significant challenge. This study presents an optimized and computationally efficient FEM model for indexable insert drills, developed in AdvantEdge™ 3D, capable of predicting thermomechanical loads (thrust force, torque, stress, temperature) and chip morphology during drilling and redrilling of AISI 316 L stainless steel. The key innovation lies in a computational approach that significantly reduces simulation time while maintaining high predictive accuracy. The model incorporates a novel tool–workpiece configuration with a slotted workpiece that enables the drill to reach nominal feed rate immediately upon engagement, accelerating convergence toward thermomechanical steady-state. Model optimization was achieved through a systematic evaluation of the most influential input parameters, surpassing the capabilities of previous FEM approaches and providing new validated insight into drilling process modeling. A comprehensive sensitivity analysis of Johnson–Cook flow stress parameters, friction coefficients, and mesh size was performed to optimize both accuracy and computational efficiency. The model was experimentally validated through complete-drill tests (both inserts mounted) and novel single-insert tests (one insert mounted) across a wide range of cutting conditions, including redrilling with varying pilot hole diameters. The optimized model accurately predicts torque, thrust forces, and chip morphology (average error: 16 %), while providing detailed stress and temperature distributions. Thrust force underprediction remains the primary limitation, identified as originating from the central insert, where Build-Up Edge (BUE) formation was observed at low cutting speeds near the drill tip.</div></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":"65 ","pages":"Pages 130-144"},"PeriodicalIF":5.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927229","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}

引用次数: 0

Friction stir lap welding of AA 2139 and AA 7075: Processing and sustainability analysis aa2139和aa7075搅拌摩擦搭接焊：工艺及可持续性分析

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2025-12-24 DOI: 10.1016/j.cirpj.2025.12.015

Vitantonio Esperto , Ersilia Cozzolino , Antonello Astarita , Pierpaolo Carlone , Felice Rubino

Friction Stir Welding (FSW) is increasingly adopted by industry to join difficult-to-weld materials thanks to its high energy efficiency and environmental sustainability. However, despite the extensive research, the studies on the sustainability of the process in correlation with the mechanical performance of the joints are still in the early stages. This study combines the analysis of energy consumption and mechanical properties in the FSW of dissimilar aluminum alloys, exploring different combinations of key process parameters. A gate-to-gate Life Cycle Assessment (LCA) was conducted to evaluate the environmental impact of the FSW process. From a sustainability standpoint, the optimal result was achieved using the highest travel speed (TS) of 270 mm/min in combination with a tool rotational speed (TRS) of 2000 rpm. Under these process conditions, reductions of up to 61 % in global warming potential (GWP), 62 % in total energy consumption, and 62 % in specific welding energy (SWE) were observed at the cost of approximately a 13 % reduction in flexural strength. As a result, power/energy, microhardness, microstructure, and flexural tests were incorporated into welding parameter maps to help in identifying minimum energy consumption and GWP points within the process constraints needed for maintaining good welding quality.

搅拌摩擦焊（FSW）由于其高能效和环境可持续性，越来越多地被工业应用于连接难焊材料。然而，尽管研究广泛，但对该过程的可持续性与节点力学性能的关系的研究仍处于早期阶段。本研究结合对不同铝合金搅拌搅拌能耗和力学性能的分析，探索关键工艺参数的不同组合。通过“门到门”生命周期评估（LCA）来评估FSW过程的环境影响。从可持续性的角度来看，当最高行程速度（TS）为270 mm/min，刀具转速（TRS）为2000 rpm时，获得了最佳结果。在这些工艺条件下，全球变暖潜能值（GWP）降低了61% %，总能耗降低了62% %，比焊接能量（SWE）降低了62% %，而弯曲强度降低了约13% %。因此，功率/能量、显微硬度、微观结构和弯曲测试被纳入焊接参数图，以帮助确定在保持良好焊接质量所需的工艺限制内的最小能耗和GWP点。

{"title":"Friction stir lap welding of AA 2139 and AA 7075: Processing and sustainability analysis","authors":"Vitantonio Esperto , Ersilia Cozzolino , Antonello Astarita , Pierpaolo Carlone , Felice Rubino","doi":"10.1016/j.cirpj.2025.12.015","DOIUrl":"10.1016/j.cirpj.2025.12.015","url":null,"abstract":"<div><div>Friction Stir Welding (FSW) is increasingly adopted by industry to join difficult-to-weld materials thanks to its high energy efficiency and environmental sustainability. However, despite the extensive research, the studies on the sustainability of the process in correlation with the mechanical performance of the joints are still in the early stages. This study combines the analysis of energy consumption and mechanical properties in the FSW of dissimilar aluminum alloys, exploring different combinations of key process parameters. A gate-to-gate Life Cycle Assessment (LCA) was conducted to evaluate the environmental impact of the FSW process. From a sustainability standpoint, the optimal result was achieved using the highest travel speed (TS) of 270 mm/min in combination with a tool rotational speed (TRS) of 2000 rpm. Under these process conditions, reductions of up to 61 % in global warming potential (GWP), 62 % in total energy consumption, and 62 % in specific welding energy (SWE) were observed at the cost of approximately a 13 % reduction in flexural strength. As a result, power/energy, microhardness, microstructure, and flexural tests were incorporated into welding parameter maps to help in identifying minimum energy consumption and GWP points within the process constraints needed for maintaining good welding quality.</div></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":"65 ","pages":"Pages 1-17"},"PeriodicalIF":5.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145814406","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}

引用次数: 0

Nozzle clogging during extrusion based additive manufacturing of polymer matrix composites—A numerical simulation insight into the process 聚合物基复合材料挤压增材制造过程中的喷嘴堵塞——对该过程的数值模拟

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2026-01-26 DOI: 10.1016/j.cirpj.2026.01.009

Rajat Mishra , Swasti Chakrabarty , Amit Arora

Enhancing properties of composite materials through aligned reinforcements in an extrusion-based additive manufacturing (AM) process, is a critical objective in engineering applications. The extrusion process involves study of complex multiphase flow to determine the directionality of the reinforcement. Advanced numerical techniques are to be deployed to study the interplay of various forces and process parameters in the process. In this study, we use coupled Computational Fluid Dynamics (CFD) and Discrete Element Method (DEM) numerical techniques to investigate the flow of a graphite-reinforced PVA polymer matrix through a nozzle, a process not easily achievable through experimental means. The drag force, pressure gradient force, and virtual mass force are found significant based on a comprehensive analysis of simulation and experimental data. Non-linear regression analysis is performed to quantify the impact of these forces on reinforcement alignment. The orientation angle of reinforcements is chosen as the output parameter, with input parameters comprising nozzle outlet diameter, reinforcement aspect ratio, volume flow rate, polymer viscosity, and reinforcement concentration. Additionally, the nozzle clogging during printing is studied using the developed model. Nozzle rotation is proposed as an effective method to mitigate clogging, further enhancing the efficiency of the reinforcement alignment process. This research advances our understanding of composite material printing and offers practical solution for optimizing the alignment of reinforcements in polymer matrices, paving the way for developing high-performance composite materials with tailored properties using extrusion based AM processes.

在基于挤压的增材制造（AM）工艺中，通过对齐增强来增强复合材料的性能是工程应用中的一个关键目标。挤压过程涉及复杂多相流的研究，以确定强化的方向性。采用先进的数值技术来研究过程中各种力和工艺参数的相互作用。在这项研究中，我们使用耦合计算流体力学（CFD）和离散元方法（DEM）数值技术来研究石墨增强PVA聚合物基体通过喷嘴的流动，这一过程不容易通过实验手段实现。通过对仿真和实验数据的综合分析，发现了阻力、压力梯度力和虚拟质量力的显著性。进行非线性回归分析，以量化这些力对钢筋对齐的影响。输出参数选择增强剂取向角，输入参数为喷嘴出口直径、增强剂长径比、体积流量、聚合物粘度和增强剂浓度。此外，利用所建立的模型对打印过程中的喷嘴堵塞进行了研究。提出了喷嘴旋转是一种有效的缓解堵塞的方法，进一步提高了补强过程的效率。这项研究提高了我们对复合材料打印的理解，并为优化聚合物基体中增强材料的排列提供了实用的解决方案，为使用基于挤压的增材制造工艺开发具有定制性能的高性能复合材料铺平了道路。

{"title":"Nozzle clogging during extrusion based additive manufacturing of polymer matrix composites—A numerical simulation insight into the process","authors":"Rajat Mishra , Swasti Chakrabarty , Amit Arora","doi":"10.1016/j.cirpj.2026.01.009","DOIUrl":"10.1016/j.cirpj.2026.01.009","url":null,"abstract":"<div><div>Enhancing properties of composite materials through aligned reinforcements in an extrusion-based additive manufacturing (AM) process, is a critical objective in engineering applications. The extrusion process involves study of complex multiphase flow to determine the directionality of the reinforcement. Advanced numerical techniques are to be deployed to study the interplay of various forces and process parameters in the process. In this study, we use coupled Computational Fluid Dynamics (CFD) and Discrete Element Method (DEM) numerical techniques to investigate the flow of a graphite-reinforced PVA polymer matrix through a nozzle, a process not easily achievable through experimental means. The drag force, pressure gradient force, and virtual mass force are found significant based on a comprehensive analysis of simulation and experimental data. Non-linear regression analysis is performed to quantify the impact of these forces on reinforcement alignment. The orientation angle of reinforcements is chosen as the output parameter, with input parameters comprising nozzle outlet diameter, reinforcement aspect ratio, volume flow rate, polymer viscosity, and reinforcement concentration. Additionally, the nozzle clogging during printing is studied using the developed model. Nozzle rotation is proposed as an effective method to mitigate clogging, further enhancing the efficiency of the reinforcement alignment process. This research advances our understanding of composite material printing and offers practical solution for optimizing the alignment of reinforcements in polymer matrices, paving the way for developing high-performance composite materials with tailored properties using extrusion based AM processes.</div></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":"65 ","pages":"Pages 273-294"},"PeriodicalIF":5.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078292","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}

引用次数: 0

Physics-based feature enhancement method and physics constraint Transformer model for multi-step tool wear and RUL prediction 基于物理的特征增强方法和物理约束Transformer模型用于多步刀具磨损和RUL预测

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2026-01-14 DOI: 10.1016/j.cirpj.2026.01.001

Shanglei Jiang , Haoyuan Zhang , Zhengmao Chen , Yuwen Sun , Xuexia Liu

In intelligent manufacturing, tool wear monitoring (TWM) and remaining useful life (RUL) prediction are crucial for improving production quality and efficiency. However, achieving accurate and reliable multi-step (long-term) predictions remains a substantial challenge. This research proposes a feature enhancement method and constructs a Transformer model that embeds hard-soft physics constraints for multi-step wear and RUL prediction. Firstly, the fast adaptive Brownian bridge aggregation algorithm (fABBA) is employed to extract the features from multiscale signals during machining, alleviating the reliance on domain knowledge inherent in traditional feature engineering to some extent. On this basis, a physics-based feature enhancement method is proposed to improve the model’s generalization. Secondly, a Transformer model based on multi-head self-attention and cross-attention mechanisms is constructed for multi-step tool wear and RUL prediction. Meanwhile, a hard-soft physical constraint embedding module is designed to ensure that the model's output has a certain degree of physical interpretability. Finally, the PHM2010 and self-constructed datasets are employed to verify the effectiveness of the proposed method. Shapley Additive Explanations (SHAP) analysis method is used to quantitatively analyze the contribution of features to the model. The wear comparison experiments on the PHM2010 dataset, using C6 as the test set, show that the proposed model achieves RMSE values of 1.680672

\pm

0.137001, 2.220760

\pm

0.145516, 3.430798

\pm

0.485509, and 5.106184

\pm

0.690110 for 12, 24, 36 and 48 step predictions, respectively. Even for the ultra-long wear prediction, the R² remains at 0.981760

\pm

0.005227, which is better than GRU, BiGRU, BiGRU-AT, and TCN models.

在智能制造中，刀具磨损监测（TWM）和剩余使用寿命预测（RUL）对提高生产质量和效率至关重要。然而，实现准确可靠的多步骤（长期）预测仍然是一个重大挑战。本研究提出了一种特征增强方法，并构建了一个嵌入软硬物理约束的Transformer模型，用于多步磨损和RUL预测。首先，采用快速自适应布朗桥聚合算法（fABBA）从加工过程中的多尺度信号中提取特征，在一定程度上减轻了传统特征工程对领域知识的依赖；在此基础上，提出了一种基于物理的特征增强方法来提高模型的泛化能力。其次，构建了基于多头自注意和交叉注意机制的Transformer模型，用于多步刀具磨损和RUL预测。同时设计了软硬物理约束嵌入模块，保证模型输出具有一定的物理可解释性。最后，利用PHM2010和自构建数据集验证了所提方法的有效性。采用Shapley加性解释（SHAP）分析方法定量分析特征对模型的贡献。在PHM2010数据集上，以C6为测试集进行磨损对比实验，结果表明，该模型在12步、24步、36步和48步预测下的RMSE值分别为1.680672±0.137001、2.220760±0.145516、3.430798±0.485509和5.106184±0.690110。即使对于超长磨损预测，R2仍为0.981760±0.005227，优于GRU、BiGRU、BiGRU- at和TCN模型。

{"title":"Physics-based feature enhancement method and physics constraint Transformer model for multi-step tool wear and RUL prediction","authors":"Shanglei Jiang , Haoyuan Zhang , Zhengmao Chen , Yuwen Sun , Xuexia Liu","doi":"10.1016/j.cirpj.2026.01.001","DOIUrl":"10.1016/j.cirpj.2026.01.001","url":null,"abstract":"<div><div>In intelligent manufacturing, tool wear monitoring (TWM) and remaining useful life (RUL) prediction are crucial for improving production quality and efficiency. However, achieving accurate and reliable multi-step (long-term) predictions remains a substantial challenge. This research proposes a feature enhancement method and constructs a Transformer model that embeds hard-soft physics constraints for multi-step wear and RUL prediction. Firstly, the fast adaptive Brownian bridge aggregation algorithm (fABBA) is employed to extract the features from multiscale signals during machining, alleviating the reliance on domain knowledge inherent in traditional feature engineering to some extent. On this basis, a physics-based feature enhancement method is proposed to improve the model’s generalization. Secondly, a Transformer model based on multi-head self-attention and cross-attention mechanisms is constructed for multi-step tool wear and RUL prediction. Meanwhile, a hard-soft physical constraint embedding module is designed to ensure that the model's output has a certain degree of physical interpretability. Finally, the PHM2010 and self-constructed datasets are employed to verify the effectiveness of the proposed method. Shapley Additive Explanations (SHAP) analysis method is used to quantitatively analyze the contribution of features to the model. The wear comparison experiments on the PHM2010 dataset, using C6 as the test set, show that the proposed model achieves RMSE values of 1.680672 <span><math><mo>±</mo></math></span> 0.137001, 2.220760 <span><math><mo>±</mo></math></span> 0.145516, 3.430798 <span><math><mo>±</mo></math></span> 0.485509, and 5.106184 <span><math><mo>±</mo></math></span> 0.690110 for 12, 24, 36 and 48 step predictions, respectively. Even for the ultra-long wear prediction, the R<sup>2</sup> remains at 0.981760 <span><math><mo>±</mo></math></span> 0.005227, which is better than GRU, BiGRU, BiGRU-AT, and TCN models.</div></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":"65 ","pages":"Pages 179-206"},"PeriodicalIF":5.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978239","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}

引用次数: 0

Mechanical strength of 3D-printed lattices under different environmental conditions 不同环境条件下3d打印格子的机械强度

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2026-01-26 DOI: 10.1016/j.cirpj.2026.01.004

Mohammad Reza Khosravani , Amirmahdi Abdollahi , Hadi Sadeghian , Majid R. Ayatollahi , Tamara Reinicke

In this study Additive Manufacturing (AM, i.e., 3D printing) has been used for fabrication of lattices with three different geometries: honeycomb, fourfold, and re-entrant. The specimens were fabricated based on the material extrusion technique, using Polyethylene Terephthalate Glycol (PETG) filament, which was reinforced with short carbon fiber additives. Since 3D-printed components might be subjected to various environmental conditions during their service life, here some of the test coupons were artificially aged (-5 to 40 °C) to determine effects of this thermal aging on their mechanical behavior. Based on a series of mechanical tests on the aged and unaged specimens, the deformation and energy absorption capabilities of the specimens were compared. Parallel to the experiments, two dimensional Finite Element Model (FEM) was developed to evaluate the mechanical performance and investigate the stress distribution and plastic deformation of the examined lattice structures. Moreover, Fractography analysis was conducted using Scanning Electron Microscope (SEM) images. The experimental findings indicate that energy absorption until damage initiation and energy absorption until the densification have been increased in almost all specimens due to the conducted thermal aging. In addition, SEM images indicate that during the loading process a higher amounts of energy was dissipated in the aged re-entrant lattices structure, compared to unaged test coupons. The documented results can be used for design and fabrication of thermal-stable 3D-printed composite parts.

在这项研究中，增材制造（AM，即3D打印）已被用于制造三种不同几何形状的晶格：蜂窝状、四倍状和重入式。基于材料挤压技术，采用聚对苯二甲酸乙二醇酯（PETG）长丝，添加短碳纤维添加剂进行增强。由于3d打印部件在其使用寿命期间可能会受到各种环境条件的影响，因此在这里，一些测试片被人工老化（-5至40°C），以确定这种热老化对其机械行为的影响。通过对时效和未时效试件进行一系列力学试验，比较了试件的变形和吸能能力。在实验的基础上，建立了二维有限元模型，对晶格结构的力学性能进行了评价，并对晶格结构的应力分布和塑性变形进行了研究。此外，还利用扫描电镜（SEM）图像进行了断口分析。实验结果表明，几乎所有试样在传导热时效作用下，损伤起始前的能量吸收和致密化前的能量吸收都有所增加。此外，SEM图像表明，在加载过程中，与未老化的试验片相比，老化的重入晶格结构中耗散的能量更高。记录的结果可用于设计和制造热稳定的3d打印复合材料部件。

{"title":"Mechanical strength of 3D-printed lattices under different environmental conditions","authors":"Mohammad Reza Khosravani , Amirmahdi Abdollahi , Hadi Sadeghian , Majid R. Ayatollahi , Tamara Reinicke","doi":"10.1016/j.cirpj.2026.01.004","DOIUrl":"10.1016/j.cirpj.2026.01.004","url":null,"abstract":"<div><div>In this study Additive Manufacturing (AM, i.e., 3D printing) has been used for fabrication of lattices with three different geometries: honeycomb, fourfold, and re-entrant. The specimens were fabricated based on the material extrusion technique, using Polyethylene Terephthalate Glycol (PETG) filament, which was reinforced with short carbon fiber additives. Since 3D-printed components might be subjected to various environmental conditions during their service life, here some of the test coupons were artificially aged (-5 to 40 °C) to determine effects of this thermal aging on their mechanical behavior. Based on a series of mechanical tests on the aged and unaged specimens, the deformation and energy absorption capabilities of the specimens were compared. Parallel to the experiments, two dimensional Finite Element Model (FEM) was developed to evaluate the mechanical performance and investigate the stress distribution and plastic deformation of the examined lattice structures. Moreover, Fractography analysis was conducted using Scanning Electron Microscope (SEM) images. The experimental findings indicate that energy absorption until damage initiation and energy absorption until the densification have been increased in almost all specimens due to the conducted thermal aging. In addition, SEM images indicate that during the loading process a higher amounts of energy was dissipated in the aged re-entrant lattices structure, compared to unaged test coupons. The documented results can be used for design and fabrication of thermal-stable 3D-printed composite parts.</div></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":"65 ","pages":"Pages 261-272"},"PeriodicalIF":5.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078291","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}

引用次数: 0

Intelligent interpretable milling force prediction: A method based on vibration signals fusing data-driven and physical features 智能可解释铣削力预测：一种基于振动信号融合数据驱动和物理特征的方法

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2026-01-03 DOI: 10.1016/j.cirpj.2025.12.020

Wen Hou , Tong Zhu , Jiachang Wang , Song Zhang

To address the limitations in accuracy and interpretability of milling force prediction, this research proposes HyDCFF-Net, an interpretable model integrating physical time-frequency features with deep learning. First, vibration signals are processed using sliding windows, and a dual-channel neural network is developed to fuse these features, establishing a robust nonlinear mapping to milling force. Next, the Captum framework provides interpretability by visualizing feature contributions. Finally, extensive experiments under varied conditions validate its high prediction accuracy and strong generalization, achieving R² scores above 0.98 on primary tests with robust cross-dataset performance, demonstrating its effectiveness as a reliable milling force monitoring solution.

为了解决铣削力预测精度和可解释性的局限性，本研究提出了HyDCFF-Net，这是一种将物理时频特征与深度学习相结合的可解释模型。首先，利用滑动窗对振动信号进行处理，并建立双通道神经网络来融合这些特征，建立强健的非线性铣削力映射。接下来，Captum框架通过可视化特性贡献来提供可解释性。最后，在不同条件下的大量实验验证了该方法的预测精度高，泛化能力强，在主要测试中R²得分在0.98以上，具有良好的跨数据集性能，证明了该方法是一种可靠的铣削力监测解决方案的有效性。

引用次数: 0

Voxel-based rapid modeling of milling material removal for machining deformation prediction using finite cell method 基于体素的铣削材料去除快速建模及有限单元法加工变形预测

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2026-01-27 DOI: 10.1016/j.cirpj.2025.12.017

Zixuan Wang , Bingran Li , Hui Zhang , Peiqing Ye

In the milling of thin-walled workpiece, deformation induced by cutting force is a critical factor affecting machining quality. Accurately and efficiently predicting the milling deformation caused by cutting force before machining is an essential method for deformation optimization in thin-walled workpiece machining. In this paper, we present a novel framework that integrates voxel-based modeling of material removal volume with the finite cell method (FCM) for the efficient prediction of machining deformation. This method leverages the voxel model's ordered data storage characteristics for efficient calculation of cutter-workpiece engagement (CWE) and instantaneous cutting forces, while enabling fast stiffness matrix updates without re-meshing. This approach significantly enhances the computational efficiency and accuracy of deformation prediction based on FCM and the voxel model, while simultaneously overcoming the mesh generation challenges inherent in traditional finite element method. Finally, both simulation and physical milling experiments on thin-walled parts were conducted to verify the significant improvement in computational efficiency over traditional algorithms and the accuracy in predicting cutting-force-induced deformation, demonstrating great potential for engineering applications.

在薄壁工件的铣削加工中，切削力引起的变形是影响加工质量的关键因素。在加工前准确、高效地预测切削力引起的铣削变形是薄壁工件加工变形优化的重要方法。在本文中，我们提出了一种新的框架，该框架将基于体素的材料去除体积建模与有限单元法（FCM）相结合，以有效地预测加工变形。该方法利用体素模型的有序数据存储特性，有效计算刀具-工件啮合（CWE）和瞬时切削力，同时实现快速刚度矩阵更新，无需重新网格划分。该方法显著提高了基于FCM和体素模型的变形预测的计算效率和精度，同时克服了传统有限元法在网格生成方面存在的问题。最后，对薄壁零件进行了仿真和物理铣削实验，验证了该算法在计算效率和预测切削力引起的变形方面比传统算法有显著提高，显示了巨大的工程应用潜力。

{"title":"Voxel-based rapid modeling of milling material removal for machining deformation prediction using finite cell method","authors":"Zixuan Wang , Bingran Li , Hui Zhang , Peiqing Ye","doi":"10.1016/j.cirpj.2025.12.017","DOIUrl":"10.1016/j.cirpj.2025.12.017","url":null,"abstract":"<div><div>In the milling of thin-walled workpiece, deformation induced by cutting force is a critical factor affecting machining quality. Accurately and efficiently predicting the milling deformation caused by cutting force before machining is an essential method for deformation optimization in thin-walled workpiece machining. In this paper, we present a novel framework that integrates voxel-based modeling of material removal volume with the finite cell method (FCM) for the efficient prediction of machining deformation. This method leverages the voxel model's ordered data storage characteristics for efficient calculation of cutter-workpiece engagement (CWE) and instantaneous cutting forces, while enabling fast stiffness matrix updates without re-meshing. This approach significantly enhances the computational efficiency and accuracy of deformation prediction based on FCM and the voxel model, while simultaneously overcoming the mesh generation challenges inherent in traditional finite element method. Finally, both simulation and physical milling experiments on thin-walled parts were conducted to verify the significant improvement in computational efficiency over traditional algorithms and the accuracy in predicting cutting-force-induced deformation, demonstrating great potential for engineering applications.</div></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":"65 ","pages":"Pages 295-309"},"PeriodicalIF":5.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078294","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}

引用次数: 0

Effects of composition, recycling and processing on deep drawing performance of automotive 6016 aluminium sheets 成分、回收和加工对汽车用6016铝板拉深性能的影响

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2025-12-29 DOI: 10.1016/j.cirpj.2025.12.012

Angela Thum , Emir Hodžić , Josef Domitner , Stefan Pogatscher

The ability to undergo complex forming operations without failure due to necking or cracking is an essential feature for automotive sheet material. The present study examines the effects of chemical composition and processing parameters on the mechanical properties of industrial 6016 aluminium sheets. The homogenization process and the Mn content were used to investigate the influence of dispersoids. Moreover, the solution treatment, the Si content and the use of recycling-friendly compositions were studied. A (semi-)industrial scale deep drawing tool with a fixed drawing depth and varying blank holder force was used to characterize the formability of the sheets at different drawing speeds. An analysis of the strain hardening behaviour via Kocks-Mecking plots revealed remarkable predictive power, enabling the estimation of the behaviour under complex sheet forming conditions from tensile testing. Microstructural investigations demonstrated that dispersoids or constituent particles exerted a minimal influence on strain hardening at high degrees of deformation, whereas dissolved Si exerted a significant influence, resulting in markedly enhanced forming performance. This is linked to the suppression of dynamic recovery, which in turn leads to the interesting results that an alloy produced with higher recycled content performed very well.

能够经受复杂的成形操作而不因颈缩或开裂而失效是汽车板材材料的基本特征。本研究考察了化学成分和加工参数对工业6016铝板机械性能的影响。采用均质化工艺和Mn含量考察了分散体的影响。此外，还研究了固溶处理、硅含量和循环友好型成分的使用。采用固定拉深和不同压边力的（半）工业规模拉深工具，对不同拉深速度下板材的成形性能进行了表征。通过Kocks-Mecking图分析应变硬化行为显示出显著的预测能力，可以通过拉伸测试估计复杂板料成形条件下的行为。显微组织研究表明，在高度变形时，分散体或组成颗粒对应变硬化的影响很小，而溶解的Si对应变硬化的影响很大，从而显著提高了成形性能。这与动态恢复的抑制有关，这反过来又导致了有趣的结果，即具有较高回收含量的合金性能非常好。

{"title":"Effects of composition, recycling and processing on deep drawing performance of automotive 6016 aluminium sheets","authors":"Angela Thum , Emir Hodžić , Josef Domitner , Stefan Pogatscher","doi":"10.1016/j.cirpj.2025.12.012","DOIUrl":"10.1016/j.cirpj.2025.12.012","url":null,"abstract":"<div><div>The ability to undergo complex forming operations without failure due to necking or cracking is an essential feature for automotive sheet material. The present study examines the effects of chemical composition and processing parameters on the mechanical properties of industrial 6016 aluminium sheets. The homogenization process and the Mn content were used to investigate the influence of dispersoids. Moreover, the solution treatment, the Si content and the use of recycling-friendly compositions were studied. A (semi-)industrial scale deep drawing tool with a fixed drawing depth and varying blank holder force was used to characterize the formability of the sheets at different drawing speeds. An analysis of the strain hardening behaviour via Kocks-Mecking plots revealed remarkable predictive power, enabling the estimation of the behaviour under complex sheet forming conditions from tensile testing. Microstructural investigations demonstrated that dispersoids or constituent particles exerted a minimal influence on strain hardening at high degrees of deformation, whereas dissolved Si exerted a significant influence, resulting in markedly enhanced forming performance. This is linked to the suppression of dynamic recovery, which in turn leads to the interesting results that an alloy produced with higher recycled content performed very well.</div></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":"65 ","pages":"Pages 70-80"},"PeriodicalIF":5.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885777","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}

引用次数: 0

A grey-box approach based on Johnson-Cook constitutive model to improve predictions of mechanical loads of cutting simulations for normalized AISI 1045 基于Johnson-Cook本构模型的灰盒方法改进标准化aisi1045切削模拟机械载荷预测

IF 5.4 2区工程技术 Q2 ENGINEERING, MANUFACTURING

CIRP Journal of Manufacturing Science and Technology

Pub Date : 2026-04-01 Epub Date: 2026-01-07 DOI: 10.1016/j.cirpj.2025.12.014

Jan Wolf , Erik Krumme , Nithin Kumar Bandaru , Martin Dienwiebel , Andreas Zabel , Hans-Christian Möhring

In machining, high temperatures and strain rates impact the flow stress of the workpiece material, making it essential to understand the materials behaviour in these process conditions for meaningful finite element analysis (FEA) of the cutting process. The Johnson-Cook constitutive model, despite being the most widely applied, is reported to struggle in capturing the material behaviour outside of the reference conditions it was calibrated on. However determining these parameters in conventional material tests is challenging. To solve this issue, this study proposes a grey-box approach which aims to increase the accuracy of process force prediction of FEA, employing a Johnson-Cook model determined by experiments conducted on a Split-Hopkins Pressure Bar and compression tests at elevated temperatures on a Gleeble 3800c for AISI 1045, over a variety of cutting parameters. In total 110 cutting experiments and their corresponding simulations were carried out in a fully factorial experimental design with eleven cutting speeds and ten uncut chip thicknesses. Succeeding the white-box model, a black box model is trained to capture the non-linear behaviour between the simulation and the cutting experiments. Among the tested algorithms, XGBoost and Support Vector Regression outperformed Random Forests and Neural Network for predicting cutting force and feed force. The proposed grey-box approach showed an improved capability of predicting cutting force and feed force, reducing the mean absolute error and mean squared error compared to the white-box model by 97.9 % and 99.9 % for cutting force and by 94.9 % and 99.7 % for feed force, respectively. The grey-box model achieved a mean error of 1.3 % with a standard deviation of 0.1 in process force prediction.

在机械加工中，高温和应变率会影响工件材料的流动应力，因此了解这些工艺条件下的材料行为对于切削过程的有意义的有限元分析（FEA）至关重要。Johnson-Cook本构模型尽管应用最为广泛，但据报道，它难以捕捉其校准的参考条件之外的材料行为。然而，在常规材料测试中确定这些参数是具有挑战性的。为了解决这一问题，本研究提出了一种灰盒方法，旨在提高有限元分析过程力预测的准确性，采用Johnson-Cook模型，该模型是通过在Split-Hopkins压力棒上进行的实验和在Gleeble 3800℃的AISI 1045上进行的高温压缩试验确定的。在全析因试验设计中，共进行了110次切削实验并进行了相应的仿真，实验设计有11种切削速度和10种未切削切屑厚度。在白盒模型之后，训练了一个黑盒模型来捕捉仿真和切割实验之间的非线性行为。在测试算法中，XGBoost和支持向量回归在预测切削力和进给力方面优于随机森林和神经网络。提出的灰盒方法预测切削力和进给力的能力有所提高，与白盒模型相比，切削力的平均绝对误差和均方误差分别降低了97.9% %和99.9 %，进给力的平均绝对误差和均方误差分别降低了94.9% %和99.7 %。灰盒模型在工艺力预测中的平均误差为1.3 %，标准差为0.1。

{"title":"A grey-box approach based on Johnson-Cook constitutive model to improve predictions of mechanical loads of cutting simulations for normalized AISI 1045","authors":"Jan Wolf , Erik Krumme , Nithin Kumar Bandaru , Martin Dienwiebel , Andreas Zabel , Hans-Christian Möhring","doi":"10.1016/j.cirpj.2025.12.014","DOIUrl":"10.1016/j.cirpj.2025.12.014","url":null,"abstract":"<div><div>In machining, high temperatures and strain rates impact the flow stress of the workpiece material, making it essential to understand the materials behaviour in these process conditions for meaningful finite element analysis (FEA) of the cutting process. The Johnson-Cook constitutive model, despite being the most widely applied, is reported to struggle in capturing the material behaviour outside of the reference conditions it was calibrated on. However determining these parameters in conventional material tests is challenging. To solve this issue, this study proposes a grey-box approach which aims to increase the accuracy of process force prediction of FEA, employing a Johnson-Cook model determined by experiments conducted on a Split-Hopkins Pressure Bar and compression tests at elevated temperatures on a Gleeble 3800c for AISI 1045, over a variety of cutting parameters. In total 110 cutting experiments and their corresponding simulations were carried out in a fully factorial experimental design with eleven cutting speeds and ten uncut chip thicknesses. Succeeding the white-box model, a black box model is trained to capture the non-linear behaviour between the simulation and the cutting experiments. Among the tested algorithms, XGBoost and Support Vector Regression outperformed Random Forests and Neural Network for predicting cutting force and feed force. The proposed grey-box approach showed an improved capability of predicting cutting force and feed force, reducing the mean absolute error and mean squared error compared to the white-box model by 97.9 % and 99.9 % for cutting force and by 94.9 % and 99.7 % for feed force, respectively. The grey-box model achieved a mean error of 1.3 % with a standard deviation of 0.1 in process force prediction.</div></div>","PeriodicalId":56011,"journal":{"name":"CIRP Journal of Manufacturing Science and Technology","volume":"65 ","pages":"Pages 163-178"},"PeriodicalIF":5.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927231","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}

引用次数: 0