Manufacturing Letters最新文献_第4页

History of NAMRI and NAMRC NAMRI和NAMRC的历史

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.007

引用次数: 0

Formation of uniform laser-induced periodic surface structures on Ti-6Al-4V using double-pulse femtosecond laser irradiation 双脉冲飞秒激光辐照在Ti-6Al-4V表面形成均匀的激光诱导周期结构

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.068

Shuhei Kodama, Ken Okudai

{"title":"Formation of uniform laser-induced periodic surface structures on Ti-6Al-4V using double-pulse femtosecond laser irradiation","authors":"Shuhei Kodama, Ken Okudai","doi":"10.1016/j.mfglet.2026.07.068","DOIUrl":"10.1016/j.mfglet.2026.07.068","url":null,"abstract":"<div><div>Double-pulse femtosecond laser irradiation has attracted increasing attention as an effective technique for tailoring surface properties through the formation of laser-induced periodic surface structures (LIPSS). This method enables precise control over ablation behavior and melting dynamics by adjusting the pulse-to-pulse delay and fluence ratio. In this study, we investigate the formation behavior of LIPSS on Ti-6Al-4V—a titanium alloy widely used in aerospace and biomedical applications—under double-pulse irradiation using a 1033 nm, 300 fs femtosecond laser. Variation of the interpulse delay revealed that, while single-pulse irradiation produced inhomogeneous fine periodic structures, highly uniform periodic structures were achieved at a delay of 300 ps. These structures are consistent with optical interference effects between surface plasmons and incident light within a transient molten layer, re-excited by the second pulse following initial melting. The results demonstrate that tuning the interpulse delay is a promising strategy for controlling the periodicity and uniformity of LIPSS, offering a non-contact and highly precise approach for surface functionalization of titanium alloys.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"49 ","pages":"Pages 570-576"},"PeriodicalIF":2.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149096177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Synthesis and Characterization of ASA-Metal oxide Nanocomposites for FFF and their Efficacy for Outdoor Applications asa -金属氧化物FFF纳米复合材料的合成、表征及其户外应用效能

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.061

Sagar Kailas Gawali, Prashant Kumar Jain

{"title":"Synthesis and Characterization of ASA-Metal oxide Nanocomposites for FFF and their Efficacy for Outdoor Applications","authors":"Sagar Kailas Gawali, Prashant Kumar Jain","doi":"10.1016/j.mfglet.2026.07.061","DOIUrl":"10.1016/j.mfglet.2026.07.061","url":null,"abstract":"<div><div>3D-printed polymer products often experience performance degradation when exposed to prolonged environmental factors (temperature fluctuations, sunlight exposure, moisture, and chemicals). To address this issue, incorporating nanomaterials into polymer matrices is an effective strategy, to enhance shielding capabilities against these environmental factors. This study focuses on developing polymer nanocomposites (PNCs) with improved thermal, UV, and moisture shielding properties by incorporating metal-oxide nanomaterials, (SiO<sub>2</sub>, ZnO and TiO<sub>2</sub>) into an acrylonitrile-styrene-acrylate (ASA) polymer matrix. The ASA-metal oxide nanocomposites were synthesised through a combing solution and melt blending techniques to enhances the compatibility with ASA polymer matrix. Microstructural and phase transformation analyses were performed to assess the dispersibility and interfacial adhesion of the metal-oxide nanoparticles (MO-NPs) within the ASA matrix. Thermal analysis revealed a significant improvement in the thermal properties of the nanocomposites over neat polymer. UV-vis spectroscopy confirmed that TiO<sub>2</sub>-reinforced nanocomposites provided superior UV shielding compared to both the neat polymer and SiO<sub>2</sub>, ZnO-reinforced nanocomposites. Additionally, rheological (MFI) analysis results indicated that the addition of TiO<sub>2</sub> NPs had minimal impact on the flow processability, in contrast to SiO<sub>2</sub>, and ZnO NPs. As a result, ASA-metal oxide nanocomposites offer promising potential as shielding materials for 3D printing to produce durable, customizable products for outdoor use, ensuring excellent performance in harsh environmental factors.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"49 ","pages":"Pages 506-512"},"PeriodicalIF":2.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149096305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel surface polishing method for metal surfaces using corona discharges 一种利用电晕放电进行金属表面抛光的新方法

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.033

Lokesh Reddy Vadde, Murali Sundaram

{"title":"A novel surface polishing method for metal surfaces using corona discharges","authors":"Lokesh Reddy Vadde, Murali Sundaram","doi":"10.1016/j.mfglet.2026.07.033","DOIUrl":"10.1016/j.mfglet.2026.07.033","url":null,"abstract":"<div><div>Surface finishing is one of the most important post-processing operations. The purpose of surface finishing ranges from fatigue</div><div>life improvement and friction reduction to aesthetics. Surface polishing is also a subset of surface finishing that focuses on reducing surface roughness through fine-scale material removal. Existing conventional and electrochemical polishing techniques are associated with material loss, long processing time, and are less accessible to complex geometries. This study investigates a novel non-contact surface polishing method for metal surfaces using corona discharges. The idea of this research is to use an innovative, non-contact approach to use the “field enhancement effect” to produce intense localized corona discharges that selectively remove material from surface asperities, causing the surface to become smoother. The proposed technique is conceptually similar to electropolishing in preferentially modifying surface peaks, but differs fundamentally by operating in a dry, gas-phase environment without liquid electrolytes. Using an in-house built experimental setup that involved a resonant transformer as the energy source to generate corona discharges, a feasibility study of polishing brass and stainless steel 304 samples was conducted for a duration of 10 minutes. The experimental results showed a significant reduction in average surface roughness (Ra) after treatment. In addition to Ra, the maximum profile height (Rz) was evaluated to provide peak-to-valley surface information. Ra values in the range of 0.09-0.16 µm and 0.03-0.09 µm were achieved for brass and stainless steel, respectively. The proposed novel technique will have numerous applications, including finishing of additively manufactured surfaces, owing to its non-contact and dry nature.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"49 ","pages":"Pages 240-246"},"PeriodicalIF":2.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149096614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of Fe3O4 Content on Mechanical Performance of PLA/APHA Composites Fe3O4含量对PLA/APHA复合材料力学性能的影响

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.042

Mamoun Alshihabi, Shafahat Ali, Abdelkrem Eltaggaz, Ibrahim Deiab

{"title":"Effect of Fe3O4 Content on Mechanical Performance of PLA/APHA Composites","authors":"Mamoun Alshihabi, Shafahat Ali, Abdelkrem Eltaggaz, Ibrahim Deiab","doi":"10.1016/j.mfglet.2026.07.042","DOIUrl":"10.1016/j.mfglet.2026.07.042","url":null,"abstract":"<div><div>The study explores the design and mechanical characteristics of biodegradable PLA/PHA composite in the form of additive manufacturing materials by incorporating magnetic iron oxide (Fe<sub>3</sub>O<sub>4</sub>) nanoparticles. The weight ratios of PLA and PHA were combined at 75/25 and Fe<sub>3</sub>O<sub>4</sub> at different weight concentrations (0-20 wt.%) to observe their impact on mechanical performance. The composite filament was obtained with the help of a single screw extruder equipment, and 3D-printed in the conditions of controlled working conditions of the FDM. Tensile, flexural, and impact tests were performed in accordance with the ASTM standards. The findings indicate that reinforcing Fe<sub>3</sub>O<sub>4</sub> makes the PLA/PHA mixture have considerable tensile strength, Young’s modulus, and flexural rigidity up to optimum composites of about 10-15 wt.%. Modulus and flexural properties showed a similar positive change, but tensile strength, which was 35 MPa with the neat blend, improved to more than 42 MPa with 15 wt.% of Fe<sub>3</sub>O<sub>4</sub>. It was, however, found that ductility reduced with increasing filler loading because of the stiffness produced by the particles and the reduced chain mobility. The strength of the impact increased progressively with the content of Fe<sub>3</sub>O<sub>4,</sub> with a maximum content of about 8 kJ/m<sup>2</sup> at 20 wt.%, suggesting improvement in toughness via improved energy dissipation and crack resistance. The addition of the Fe<sub>3</sub>O<sub>4</sub> nanoparticles offers moderate enhancement in stiffness, strength, and toughness, making the PLA/PHA/Fe<sub>3</sub>O<sub>4</sub> composites a promising sustainable material that can be used in further FDM and possibly 4D printing.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"49 ","pages":"Pages 330-336"},"PeriodicalIF":2.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149096533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unsupervised learning for detection of defects during machining of additively manufactured components 增材制造零件加工过程中缺陷检测的无监督学习方法

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.031

Jaydeep Karandikar, Akash Tiwari, Gregory Corson, Blane Fillingim, Christopher Tyler, Scott Smith

{"title":"Unsupervised learning for detection of defects during machining of additively manufactured components","authors":"Jaydeep Karandikar, Akash Tiwari, Gregory Corson, Blane Fillingim, Christopher Tyler, Scott Smith","doi":"10.1016/j.mfglet.2026.07.031","DOIUrl":"10.1016/j.mfglet.2026.07.031","url":null,"abstract":"<div><div>Detection of defects such as porosities is important in additive manufacturing to ensure the desired material properties. Most additively manufactured components require finish machining to achieve the desired surface finish and geometric tolerances. This paper presents an unsupervised machine learning approach using an autoencoder to detect defects during the machining of additively manufactured components. To train the autoencoder, machining tests at different process parameters were completed on fully dense wrought Grade 91 steel. The spindle power and the tool position were monitored during these machining tests. The autoencoder reconstruction error in the wrought machining tests was used to establish a threshold to detect defects during the machining of Grade 91 samples manufactured using directed energy deposition. Results show that the autoencoder was able to detect multiple porosities along the length of the cut at different machining process parameters with accuracy greater than 0.8. Although the machining process is destructive, it is a fast and low-cost approach for defect detection in additive manufacturing. The method can also be implemented in a hybrid setup to ensure defect-free components or for rapid identification of optimal process parameters.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"49 ","pages":"Pages 216-227"},"PeriodicalIF":2.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149096535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Cost-Effective IoT-Based Non-Invasive Glucose Monitoring System with Individualized Calibration for Scalable Biomedical Device Production 一种具有成本效益的基于物联网的无创血糖监测系统，可用于可扩展的生物医学设备生产

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.011

Maram Shqair, Konstantinos Mykoniatis

{"title":"A Cost-Effective IoT-Based Non-Invasive Glucose Monitoring System with Individualized Calibration for Scalable Biomedical Device Production","authors":"Maram Shqair, Konstantinos Mykoniatis","doi":"10.1016/j.mfglet.2026.07.011","DOIUrl":"10.1016/j.mfglet.2026.07.011","url":null,"abstract":"<div><div>This study presents a cost-effective, IoT-enabled, non-invasive glucose monitoring system that employs photoplethysmography (PPG) biosignals and individualized calibration to enhance measurement accuracy and long-term stability. The system integrates the MAX30101 Pulse Oximeter and Heart Rate Sensor for high-fidelity biosignal acquisition and the MAX32664 Biometric Sensor Hub for noise reduction and signal processing. An Arduino Uno R4 WiFi microcontroller with cloud-based storage and real-time dashboards handles data. A personalized polynomial regression model was developed for a single user, as a proof-of-concept. The model uses heart rate (HR) and peripheral capillary oxygen saturation (SpO2) as input features to predict glucose levels, while accounting for physiological variability. Model evaluation demonstrated strong predictive performance, achieving an R<sup>2</sup> of 0.8576 during training and 0.789 during testing, with a mean absolute error (MAE) of 6.58 mg/dL, a root mean square error (RMSE) of 7.75 mg/dL, and a mean absolute relative difference (MARD) of 7.13%. The achieved accuracy is comparable to values reported in the PPG-based non-invasive glucose monitoring literature, while the use of individualized calibration in this study provides a key advantage: tailoring the regression model to each user’s specific physiological characteristics, thereby minimizing the need for frequent recalibration and enhancing long-term stability. To the best of the authors’ knowledge, this is the first low-cost IoT-based glucose monitoring system that combines PPG sensing with individualized calibration. This low-cost proof-of-concept can be generalized and scaled through a structured pathway that progresses from multi-subject clinical validation to engineering design transfer with factory-level verification, followed by broader deployment supported by regulated quality and approval processes.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"49 ","pages":"Pages 18-29"},"PeriodicalIF":2.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149095959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Control System Design of Inertial Moment Actuator using Gyroscopic Spindle for Robotic Machining 机器人加工用陀螺主轴惯性力矩作动器控制系统设计

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.016

Jongyoup Shim, Jooho Hwang, Seung Guk Baek, Seung Kook Ro

{"title":"Control System Design of Inertial Moment Actuator using Gyroscopic Spindle for Robotic Machining","authors":"Jongyoup Shim, Jooho Hwang, Seung Guk Baek, Seung Kook Ro","doi":"10.1016/j.mfglet.2026.07.016","DOIUrl":"10.1016/j.mfglet.2026.07.016","url":null,"abstract":"<div><div>This study presents the controller design procedure and method for inertial moment actuator suppressing robot vibrations during machining. The gyroscopic spindle actuator was introduced for vibration suppression in robotic machining and the experimental validation demonstrated significant suppression of low-frequency vibrations alongside reductions in higher-frequency structural vibrations in our previous work. The actuator utilizes a rotating flywheel, driven by an air-pressure turbine, to generate stabilizing gyroscopic moments, enhancing machining precision and stability. Key design features include a lightweight structure, a wireless optical angular speed sensor, and an electro-pneumatic proportional valve for flywheel speed control. In this work firstly the formulating equation procedures for geometric relation among motor driving axes, actuator axes and machining head axes are presented. And the procedures for formulating proposed controller structure are shown with considering dynamic working principle and some assumptions. For control stability and efficiency a band-pass filter was adopted and the procedure for formulating discrete time filter equation is shown. And in order to tune the controller gain an experimentally tuning method is presented with considering dynamic relations. Experimental validation confirmed substantial attenuation of low-frequency vibrations, with the most pronounced reduction observed near 6 Hz, together with clear suppression of higher-frequency structural modes. These outcomes indicate that the proposed actuator improves machining stability and surface finish while maintaining robust and reliable performance. The results demonstrate the effectiveness of the gyroscopic spindle actuator in mitigating vibration-induced limitations in robotic machining and provide a practical foundation for further advances in robotic manufacturing systems.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"49 ","pages":"Pages 66-73"},"PeriodicalIF":2.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149095962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Learning-based high-resolution spectrogram reconstruction for robust bearing fault diagnosis 基于深度学习的高分辨率谱图重建鲁棒轴承故障诊断

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.019

Sabyasachi Biswas, Saifur Rahman Tushar, Md Ebtidaul Karim, Abdullah Al Mamun, Mahathir Mohammad Bappy

{"title":"Deep Learning-based high-resolution spectrogram reconstruction for robust bearing fault diagnosis","authors":"Sabyasachi Biswas, Saifur Rahman Tushar, Md Ebtidaul Karim, Abdullah Al Mamun, Mahathir Mohammad Bappy","doi":"10.1016/j.mfglet.2026.07.019","DOIUrl":"10.1016/j.mfglet.2026.07.019","url":null,"abstract":"<div><div>Accurate and reliable bearing fault diagnosis is critical for the safe and efficient operation of rotating machinery. Conventional time–frequency (TF) analysis techniques, such as the short-time Fourier transform (STFT), are limited by their fixed window sizes and the inherent trade-off between time and frequency resolution, often leading to suboptimal fault representation under varying operating conditions. To address these challenges, this paper proposes a deep learning-based framework that reconstructs high-resolution, noise-robust TF representations directly from raw vibration signals. The proposed model integrates a denoising encoder with a learnable TF transformation network to adaptively capture fault related frequency patterns without manual parameter tuning. The proposed model’s performance is evaluated using multiple CNN-based classifiers on two benchmark datasets: Case Western Reserve University (CWRU) and HUST. Experimental results demonstrate that the proposed approach achieves superior classification performance, with improvements of up to <span><math><mrow><mn>1.5</mn><mspace></mspace><mspace></mspace><mspace></mspace><mn>2</mn><mo>%</mo></mrow></math></span> in accuracy and F1-score over HRSpecNet, and over 13% compared to TFA-Net. These results confirm the proposed model’s ability to generate discriminative, high-resolution TF representations suitable for intelligent bearing-fault analysis and real-time industrial predictive maintenance.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"49 ","pages":"Pages 98-109"},"PeriodicalIF":2.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149095966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AutoSlice: A Fully Automatic LLM-driven Slicing Configuration Framework for Additive Manufacturing AutoSlice：用于增材制造的全自动llm驱动的切片配置框架

IF 2.8

Manufacturing Letters Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1016/j.mfglet.2026.07.084

Syed Ziaul Bin Bashar, Jesus Diaz, Chaitanya Mahajan, Satyajayant Misra

{"title":"AutoSlice: A Fully Automatic LLM-driven Slicing Configuration Framework for Additive Manufacturing","authors":"Syed Ziaul Bin Bashar, Jesus Diaz, Chaitanya Mahajan, Satyajayant Misra","doi":"10.1016/j.mfglet.2026.07.084","DOIUrl":"10.1016/j.mfglet.2026.07.084","url":null,"abstract":"<div><div>Producing reliable, production-quality 3D prints depends on an expert tuning multiple slicer parameters, which is a manual and graphical interface-bound process. While Large Language Models (LLMs) excel at reasoning tasks, their application to automate the slicing workflow remains underexplored. To address this challenge, we developed AutoSlice, a novel, modular framework that automates the generation of slicer configurations, which has an LLM as the core reasoning engine. The framework is designed to be scalable with a plug-and-play architecture, taking advantage of future versions in LLMs. The AutoSlice pipeline locally extracts non-invertible geometric features from a 3D model. These non-invertible design features, combined with schema-anchored rules and printer-material metadata, are then passed to an LLM agent, which reasons about the geometry and machine-specific heuristics to generate a complete and syntactically valid configuration file. This framework executes a headless command-line slicer, yielding machine-ready G-code. AutoSlice encapsulates expert knowledge, demonstrating a viable path to democratizing AM by enabling non-experts to reliably translate digital designs into high-quality objects. We conducted a comprehensive evaluation to demonstrate the framework’s robustness and modularity. We evaluated several versions of LLMs: both proprietary (Gemini-2.5-Flash, GPT-5-Mini) and open-source (Llama-3.2-3B-Instruct, Qwen-2.5-7B-Instruct), and evaluated also the Zero-Shot and One-Shot prompting strategies across two printers (Ender 3 S1, Prusa XL) and materials (PLA, ABS). The results show that while smaller models struggle with reliability, larger LLMs achieve high efficacy. The One-Shot strategy with proprietary LLMs yielded over 97% valid G-code generation and printability, validated by successful physical prints.</div></div>","PeriodicalId":38186,"journal":{"name":"Manufacturing Letters","volume":"49 ","pages":"Pages 698-709"},"PeriodicalIF":2.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149096081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0