Procedia CIRPPub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.014
Kendrik Yan Hong Lim , Ziqing Xia , Zhi Hao Ho , Marvin Carl May , Kamal Youcef-Toumi
{"title":"Automating Radio Communication Training: A Protocol-Aware Chatbot Using Context Engineering for Human-centric Industrial Operations","authors":"Kendrik Yan Hong Lim , Ziqing Xia , Zhi Hao Ho , Marvin Carl May , Kamal Youcef-Toumi","doi":"10.1016/j.procir.2025.09.014","DOIUrl":"10.1016/j.procir.2025.09.014","url":null,"abstract":"<div><div>In human-centric industries such as transportation and heavy manufacturing, strict adherence to safety-critical radio communication (RC) protocols is essential for operational efficiency and safety. Traditional training methods rely on human instructors, who may introduce inconsistencies or biases. While chatbots present a scalable alternative, conventional Retrieval-Augmented Generation (RAG) systems often fail to enforce protocol compliance reliably. Hence, a protocol-aware training chatbot is proposed to bridge this gap, leveraging context engineering and few-shot learning with Large Language Models (LLMs) to deliver industry-specific and protocol-compliant responses. Validated through a transportation case study, this chatbot system demonstrates robust consistency in RC protocol enforcement across 18 scenarios of varying complexity. An integrated scoring mechanism evaluates trainee performance and provides corrective feedback, enhancing learning outcomes. By providing practical and human-like experiences in RC training, this system can be adapted across industries to reduce miscommunication risks.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 23-28"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147424329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Procedia CIRPPub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.10.003
Christopher Sowinski , Yufei Feng , Simon Schlichte , Oguz Kedilioglu , Jörg Franke , Sebastian Reitelshöfer
{"title":"Quantum-enhanced discrete-event simulation and optimization of sequence-dependent job scheduling with setup times","authors":"Christopher Sowinski , Yufei Feng , Simon Schlichte , Oguz Kedilioglu , Jörg Franke , Sebastian Reitelshöfer","doi":"10.1016/j.procir.2025.10.003","DOIUrl":"10.1016/j.procir.2025.10.003","url":null,"abstract":"<div><div>Process simulation tools, such as discrete-event simulation (DES), offer domain experts low-barrier environments for designing and evaluating industrial processes, avoiding the expense and complexity of physical prototypes. While classical optimization approaches are routinely embedded in DES workflows, quantum-enhanced optimization remains largely unexplored. With the emergence of advanced quantum computing hardware, integrating it into industrial optimization has become realistic and the potential to unlock faster, more cost-effective solutions for complex scheduling, routing, and resource allocation compared to classical methods. To broaden its adoption among domain experts without a background in quantum theory, we must offer intuitive, application-oriented software tools. Yet the ecosystem of such frameworks is vast, and guidance is lacking as to which platform or library best suits a given domain expert´s needs. In this work, we bridge the gap between DES and quantum optimization by first conducting a literature review of existing quantum application-oriented optimization frameworks. From these findings, we derive recommendations, answering which tools and platforms engineers or researchers can choose to formulate and test their DES optimization problems across multiple quantum backends. Building on our survey, we introduce a theoretical framework that integrates quantum-optimization algorithms directly into the DES optimization cycle. We then apply this framework to the benchmark sequence-dependent job-scheduling problem with setup times (SDJST), which, to the best of our knowledge, constitutes one of the first quantum-enabled simulation-optimization studies for this problem. We further validate that classical optimization approaches outperform for smaller problem sizes, whereas the quantum approach becomes increasingly promising as the problem size grows.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 66-75"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Synchronisation of a machine-integrated monitoring system for recording process emissions in additive manufacturing","authors":"Eckart Uhlmann , Julian Polte , Manuel Bösing , Hao Xu","doi":"10.1016/j.procir.2025.08.188","DOIUrl":"10.1016/j.procir.2025.08.188","url":null,"abstract":"<div><div>In the context of additive manufacturing, process monitoring is of significant importance, given the inherent challenges associated with achieving stable production. Industrial facilities are already equipped with monitoring systems that utilise photodiodes to record process emissions across various wavelength ranges. The photodiodes are coupled to the laser optics, thereby ensuring that only the emissions in the melt pool are recorded. An approach has previously been demonstrated whereby the production strategy of an industrial machine is adapted in such a manner that process emissions are also recorded at a greater distance from the working laser. Nevertheless, the absence of synchronisation between the measurement results poses a significant challenge in this context. This is accompanied by a paucity of clarity regarding the exact location of the recorded process emissions. The present article thus sets out a methodology for synchronising the measurement data, and consequently, for localising the process emissions.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 152-159"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Procedia CIRPPub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.032
Yuexiang Wang , Shengzhu Cao , Peng Lyu
{"title":"Study on Molecular Dynamics of Grain Regulation in Polycrystalline Tin under Plasma Modification and Annealing Processes","authors":"Yuexiang Wang , Shengzhu Cao , Peng Lyu","doi":"10.1016/j.procir.2025.09.032","DOIUrl":"10.1016/j.procir.2025.09.032","url":null,"abstract":"<div><div>Soft polycrystalline tin, owing to its exceptional physical properties, finds various applications, such as energy and medical devices. However, achieving superior surface quality in machining of this material remains challenging due to the deleterious impact of grain boundary (GB) step effects on surface roughness. This study systematically investigates the mechanistic interplay between plasma modification and annealing treatments on GB evolution in polycrystalline tin, employing molecular dynamics simulations to elucidate atomic-scale behaviors. Complementary experimental comparisons of grain growth dynamics are conducted using electron backscatter diffraction and white-light interferometry for microstructural and topographical characterization. Results demonstrate that while thermal annealing induces moderate grain coarsening through temperature-driven GB migration and subsequent boundary reduction, plasma modification introduces a distinct transformation pathway. The localized thermal effects of plasma treatment enable directional grain growth via transient high-temperature melting-induced grain fusion, yielding more pronounced grain enlargement and significant GB density reduction. It is confirmed that single-point diamond turning of plasma-modified specimens is capable of achieving sub-nanometer surface roughness, surpassing the performance of conventionally annealed counterparts.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 292-297"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"6D Pose Estimation of Stator Windings from CT-Measurements","authors":"Erik Bär , Edwin Blum , Florian Stamer , Gisela Lanza","doi":"10.1016/j.procir.2025.08.190","DOIUrl":"10.1016/j.procir.2025.08.190","url":null,"abstract":"<div><div>In the manufacturing of electric motors, the quality of wire windings is a critical factor determining motor performance and reliability. Defective windings typically result in motor rejection during production, necessitating effective quality control methods. Non-destructive evaluation via computed tomography (CT) offers a promising approach for assessing internal components, although data analysis presents significant challenges. In this study, we introduce a novel method to extract the complete 6D pose of stator windings from CT measurements. The method applies a topology-preserving thinning algorithm to reduce segmented wires to their medial axis, from which positional and curvature data are derived. Local twist about the wire’s axis is quantified by analysing image moments in orthogonal cross-sections along the winding. Validation with synthetic CT data and physical motor replicas demonstrates high precision in estimating wire positions and rotations, including intricate bending and twisting behaviours. Future work will focus on optimizing the method to enhance its robustness against the noise inherent in real-world CT scans.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 268-273"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Procedia CIRPPub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.046
Banghai Zhang , Deteng Liu , Ziyan Luo , Jingde Li , Xiansheng Qin , Zhanxi Wang
{"title":"Non-destructive Testing System for High-curvature Laminated Composite Workpieces","authors":"Banghai Zhang , Deteng Liu , Ziyan Luo , Jingde Li , Xiansheng Qin , Zhanxi Wang","doi":"10.1016/j.procir.2025.09.046","DOIUrl":"10.1016/j.procir.2025.09.046","url":null,"abstract":"<div><div>The automatic ultrasonic scanning system integrating a gantry mobile platform and a robot has shown high effectiveness in detecting large-curvature laminated composites. However, for large-curvature laminated wing workpieces, achieving full-surface coverage during automatic scanning remains a critical technical challenge. To address this, this study first identifies the key factors influencing the efficiency and accuracy of robot scanning. It then proposes adopting the Zig-Zag scanning strategy for trajectory planning: the size and quantity of the robot’s single scanning area are determined based on its working range, and the overall scanning trajectory is subsequently formed. Additionally, a four-sensor normal detection algorithm is developed to real-time detect the normal vector of the scanning area, enabling real-time adjustment of the robot’s end-effector attitude. This approach ensures the accuracy of the automatic ultrasonic scanning system while significantly improving scanning efficiency.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 379-384"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147423940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Procedia CIRPPub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.08.187
Lucas Manassés Pinheiro de Souza , Abhishek Deshmukh , Kedar Rajpathak , Alexander Moriz , Amon Göppert , Robert H. Schmitt
{"title":"Embodied AI Agent Framework for (Re)Programming Robotic Tasks in Flexible Assembly using LLMs and VLMs","authors":"Lucas Manassés Pinheiro de Souza , Abhishek Deshmukh , Kedar Rajpathak , Alexander Moriz , Amon Göppert , Robert H. Schmitt","doi":"10.1016/j.procir.2025.08.187","DOIUrl":"10.1016/j.procir.2025.08.187","url":null,"abstract":"<div><div>The increasing product variability and skilled labor shortages in manufacturing intensify the need for more flexible and adaptive automation solutions, particularly in assembly systems. However, existing robotic automation typically requires expert-level programming, preventing adaptability to new tasks or product variants. This work presents a modular embodied AI agent framework that enables non-programming operators to implement and reconfigure robotic tasks through intuitive natural language (NL) commands in text or voice format. By integrating open-source Large Language Models (LLMs) and Visual Language Models (VLMs) with a Robot Operating System 2 (ROS2)-based stack, the agent translates user instructions into perception, grasp generation, and motion planning actions. The framework is evaluated in real-world experiments across four scenarios: low-level motion control, vision-guided cable grasping, visual scene feedback, and task-cycle recording with replay for scalable execution. Results show 100% command parsing accuracy for basic motions, reliable visual feedback, and 70% success in dual-cable manipulation, with failures mainly from trajectory planning or self-collisions. VLM inference latency proved highly hardware-dependent, with near real-time performance on high-end GPUs but significant slowdowns on consumer devices, highlighting deployment challenges. These findings show the potential of embodied AI agents to bridge NL interaction with robotic execution, lowering barriers to deploying adaptive, operator-friendly robotic systems in dynamic manufacturing.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 59-65"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Procedia CIRPPub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.08.185
Seán Comerford , JeanLuc Oudshoorn , Ionut Barbu , Joris Ruis , Di H. Nguyen
{"title":"Capacitated Multi-Source Energy Optimisation with Time-of-Use Pricing","authors":"Seán Comerford , JeanLuc Oudshoorn , Ionut Barbu , Joris Ruis , Di H. Nguyen","doi":"10.1016/j.procir.2025.08.185","DOIUrl":"10.1016/j.procir.2025.08.185","url":null,"abstract":"<div><div>We investigate an energy optimisation problem at a European steel manufacturing facility. In this problem, the company seeks to integrate green energy with grid electricity using battery storage systems. The electricity drawn from the grid is subject to a time-of-use tariff, creating opportunities for cost savings through using solar or battery energy during expensive peak periods. A mathematical model is developed to minimise the energy usage cost from multiple sources, while ensuring the facility’s energy demand is met. The model accounts for constraints on solar energy availability, battery capacity, and charge/discharge rates. We conduct computational experiments using historical energy demand and time-of-use rates. Different sizes of energy storage systems up to 500kWh are considered. The results show up to a 23% reduction in energy costs relative to a baseline solution that relies solely on energy from the grid, demonstrating the value of combining on-site green energy generation with battery storage in reducing operational costs in energy-intensive industries. Finally, stochastic extensions that incorporate uncertainty pricing, energy supply and demand are provided along with the corresponding solution approaches.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 128-133"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Procedia CIRPPub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.015
Peijiang Li , Yuanyuan Wang , Chengtao Liu , Shengquan Li , Yi Xiong
{"title":"Leveraging LLMs for personalized and manufacturable design generation of multirotor unmanned aerial vehicles","authors":"Peijiang Li , Yuanyuan Wang , Chengtao Liu , Shengquan Li , Yi Xiong","doi":"10.1016/j.procir.2025.09.015","DOIUrl":"10.1016/j.procir.2025.09.015","url":null,"abstract":"<div><div>With the growth of customization demands, product design needs to simultaneously consider efficiency, novelty, and manufacturability. However, the mainstream design model suffers from issues such as information islands, long design cycles, and high collaboration costs, making it challenging to satisfy personalized customization demands. Thus, this paper proposes an intelligent design framework for product personalization, which includes three stages: requirement analysis, intelligent generation of solution, and assembly of system. More specifically, intelligent design based on fully automated three-dimensional model generation is implemented with large language models that adhere to natural language expressions of functional requirements, design rules, and manufacturability constraints. To ensure manufacturability, the process is divided into three stages: In the customer requirements stage, LLM extracts and integrates manufacturing constraints to ensure design feasibility. During the intelligent generation stage, LLM optimizes the design based on manufacturable processes and equipment limitations, balancing performance with manufacturability. Finally, in the assembly stage, LLM refines module interfaces, ensuring efficient integration and verifying alignment with manufacturing constraints, thus enhancing overall manufacturability. The workflow is demonstrated by designing the structure of a multirotor unmanned aerial vehicle (MUAV) frame for different design scenarios. The designed MUAV frame undergoes physical prototyping, with additive manufacturing and assembly.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 140-145"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Procedia CIRPPub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.036
Fabian Hock , Joachim Metternich
{"title":"An Empirical Study On Enhancing Productivity With Human-centered Worker Assistance Systems In Manual Assembly","authors":"Fabian Hock , Joachim Metternich","doi":"10.1016/j.procir.2025.09.036","DOIUrl":"10.1016/j.procir.2025.09.036","url":null,"abstract":"<div><div>Human-centered design in production aims at improving efficiency, safety, and user satisfaction by designing work environments integrating human requirements. To provide these improvements, worker assistance systems are deployed at manual workstations but there remains a gap in understanding how these systems can be effectively tailored to the diverse needs of workers. This paper presents a study on the impact of various worker assistance functions on both productivity and human-centeredness in manual assembly using a streaming analytics framework to acquire key performance indicators. The findings provide valuable insights into the effective configuration of worker assistance systems.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 397-402"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}