Pub Date : 2026-01-01Epub Date: 2026-02-12DOI: 10.1016/j.procir.2026.01.065
Chengjin Tian , Changni Fu , Shuqiang Li , Ying Li , Liyang Wan , Yan Yang , Kejia Zhuang
Cutting-edge geometries directly influence tool life and performance. Appropriate cutting-edge geometries can enhance wear resistance, ensure process reliability, and maintain workpiece integrity. In this work, the single-factor and multi-factor abrasive water jet machining experiments were conducted to explore the factors influencing the formation of the cutting-edge, including jet pressure, angle, and number of strokes. It was found that different jetting parameters have varying effects on different cutting-edge parameters. Jetting pressure most impacted the radius of the cutting-edge formation, while angle significantly affected shape factor K. Multi-factor experiments demonstrated that both pressure and tool orientation significantly affect process stability.
{"title":"Research on formation principle of cutting-edge geometries of carbide turning tools","authors":"Chengjin Tian , Changni Fu , Shuqiang Li , Ying Li , Liyang Wan , Yan Yang , Kejia Zhuang","doi":"10.1016/j.procir.2026.01.065","DOIUrl":"10.1016/j.procir.2026.01.065","url":null,"abstract":"<div><div>Cutting-edge geometries directly influence tool life and performance. Appropriate cutting-edge geometries can enhance wear resistance, ensure process reliability, and maintain workpiece integrity. In this work, the single-factor and multi-factor abrasive water jet machining experiments were conducted to explore the factors influencing the formation of the cutting-edge, including jet pressure, angle, and number of strokes. It was found that different jetting parameters have varying effects on different cutting-edge parameters. Jetting pressure most impacted the radius of the cutting-edge formation, while angle significantly affected shape factor K. Multi-factor experiments demonstrated that both pressure and tool orientation significantly affect process stability.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 375-380"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162074","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}
Pub Date : 2026-01-01Epub Date: 2026-02-12DOI: 10.1016/j.procir.2026.01.070
Andreas Schönle , Florian Vogel , Dirk Biermann , Peter Eberhard
In milling, regenerative chattering results in tool damage and poor workpiece quality. Particle filled cavities in milling heads have shown to be usable as a possible remedy for this effect. The application of particle dampers (PD) in manufacturing processes is therefore promising, yet it is not sufficiently investigated. In this paper, the effect of the rotational speed and the introduction of an obstacle grid is investigated through numerical simulation. The discrete element method is used to model the particle filling in the PD cavity. Effectiveness is analyzed through the particle movement and acting forces on the cavity walls.
{"title":"Investigating the Applicability of Particle Damping in Milling Heads through Numerical Simulation","authors":"Andreas Schönle , Florian Vogel , Dirk Biermann , Peter Eberhard","doi":"10.1016/j.procir.2026.01.070","DOIUrl":"10.1016/j.procir.2026.01.070","url":null,"abstract":"<div><div>In milling, regenerative chattering results in tool damage and poor workpiece quality. Particle filled cavities in milling heads have shown to be usable as a possible remedy for this effect. The application of particle dampers (PD) in manufacturing processes is therefore promising, yet it is not sufficiently investigated. In this paper, the effect of the rotational speed and the introduction of an obstacle grid is investigated through numerical simulation. The discrete element method is used to model the particle filling in the PD cavity. Effectiveness is analyzed through the particle movement and acting forces on the cavity walls.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 404-408"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162077","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}
Pub Date : 2026-01-01Epub Date: 2026-02-12DOI: 10.1016/j.procir.2026.01.094
Eckart Uhlmann , Marco Kopp
Centrifugal disc finishing is an effective post-processing operation for the roughness reduction of additively manufactured workpieces. However, the process leads to an edge rounding, which might result in shape deviations – especially if the workpiece is manufactured near net-shaped. In this study, a model based on the discrete element method is used to predict the edge radius of workpieces machined by centrifugal disc finishing. As shown, the model can be applied to redesign the workpiece with local stock allowance in order to reduce shape deviations resulting from centrifugal disc finishing.
{"title":"Prediction of the edge rounding of additively manufactured workpieces made of Ti6Al4V during centrifugal disc finishing","authors":"Eckart Uhlmann , Marco Kopp","doi":"10.1016/j.procir.2026.01.094","DOIUrl":"10.1016/j.procir.2026.01.094","url":null,"abstract":"<div><div>Centrifugal disc finishing is an effective post-processing operation for the roughness reduction of additively manufactured workpieces. However, the process leads to an edge rounding, which might result in shape deviations – especially if the workpiece is manufactured near net-shaped. In this study, a model based on the discrete element method is used to predict the edge radius of workpieces machined by centrifugal disc finishing. As shown, the model can be applied to redesign the workpiece with local stock allowance in order to reduce shape deviations resulting from centrifugal disc finishing.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 546-551"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162157","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}
Pub Date : 2026-01-01Epub Date: 2026-02-12DOI: 10.1016/j.procir.2026.01.099
Maschal Hakimiy , Klaus Dröder
In additive manufacturing, fused granular fabrication (FGF) can be considered as an alternative to the established filament fabrication (FFF) of thermoplastics. Based on granular feedstock, FGF is easily and economically scalable to higher volume deposition rates. However, the resulting surface quality and bed adhesion are currently challenging, resulting in reduced dimensional accuracy and limited adoption in industrial contexts. The present study investigates a conceptual initial setup of new thermoplastic materials for FGF. The main objective is to develop a time and cost efficient method for material independent determination of process parameters to streamline the integration of new materials.
{"title":"A concept for in-situ parameterisation of a fused granular fabrication process: A material independent approach","authors":"Maschal Hakimiy , Klaus Dröder","doi":"10.1016/j.procir.2026.01.099","DOIUrl":"10.1016/j.procir.2026.01.099","url":null,"abstract":"<div><div>In additive manufacturing, fused granular fabrication (FGF) can be considered as an alternative to the established filament fabrication (FFF) of thermoplastics. Based on granular feedstock, FGF is easily and economically scalable to higher volume deposition rates. However, the resulting surface quality and bed adhesion are currently challenging, resulting in reduced dimensional accuracy and limited adoption in industrial contexts. The present study investigates a conceptual initial setup of new thermoplastic materials for FGF. The main objective is to develop a time and cost efficient method for material independent determination of process parameters to streamline the integration of new materials.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 573-578"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162162","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}
Pub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.045
Roham Sadeghi Tabar , Andi Kuswoyo , Christos Margadji , Sebastian W. Pattinson
This work presents a methodology for quantifying geometric deviations in metal parts fabricated via Fused Filament Fabrication (FFF) using Ultrafuse 316L stainless steel filament. A blade-shaped geometry is selected as a representative case and analysed before and after sintering using high-resolution X-ray computed tomography (XCT). The XCT data are aligned to nominal and scaled geometries to assess deviations introduced during each manufacturing stage. In parallel, a thermo-mechanical sintering simulation is performed to predict shrinkage and deformation. Comparison between simulated results and XCT data reveals location-dependent discrepancies, with deformation at critical regions exceeding 2 mm and simulation errors ranging from 0.5 to 2 mm. The study highlights the limitations of standard shrinkage scaling and demonstrates the value of XCT-based characterisation in validating and improving predictive models for metal FFF. The proposed approach provides a foundation for model-informed design and process compensation strategies in sintering-based additive manufacturing.
{"title":"Characterisation of Geometric Accuracy in Metal Fused Filament Fabricated Parts Using X-ray Computed Tomography","authors":"Roham Sadeghi Tabar , Andi Kuswoyo , Christos Margadji , Sebastian W. Pattinson","doi":"10.1016/j.procir.2025.09.045","DOIUrl":"10.1016/j.procir.2025.09.045","url":null,"abstract":"<div><div>This work presents a methodology for quantifying geometric deviations in metal parts fabricated via Fused Filament Fabrication (FFF) using Ultrafuse 316L stainless steel filament. A blade-shaped geometry is selected as a representative case and analysed before and after sintering using high-resolution X-ray computed tomography (XCT). The XCT data are aligned to nominal and scaled geometries to assess deviations introduced during each manufacturing stage. In parallel, a thermo-mechanical sintering simulation is performed to predict shrinkage and deformation. Comparison between simulated results and XCT data reveals location-dependent discrepancies, with deformation at critical regions exceeding 2 mm and simulation errors ranging from 0.5 to 2 mm. The study highlights the limitations of standard shrinkage scaling and demonstrates the value of XCT-based characterisation in validating and improving predictive models for metal FFF. The proposed approach provides a foundation for model-informed design and process compensation strategies in sintering-based additive manufacturing.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 343-348"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147423935","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}
Pub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.008
Kenrick Howin Chai , Stefan Hildebrand , Tobias Lachnit , Martin Benfer , Gisela Lanza , Sandra Klinge
Rental-based business models and increasing sustainability requirements intensify the need for efficient strategies to manage large machine and vehicle fleet renewal and upgrades. Optimized fleet upgrade strategies maximize overall utility, cost, and sustainability. However, conventional fleet optimization does not account for upgrade options and is based on integer programming with exponential runtime scaling, which leads to substantial computational cost when dealing with large fleets and repeated decision-making processes. This contribution firstly suggests an extended integer programming approach that determines optimal renewal and upgrade decisions. The computational burden is addressed by a second, alternative machine learning-based method that transforms the task to a mixed discrete-continuous optimization problem. Both approaches are evaluated in a real-world automotive industry case study, which shows that the machine learning approach achieves near-optimal solutions with significant improvements in the scalability and overall computational performance, thus making it a practical alternative for large-scale fleet management.
{"title":"Accelerating Fleet Upgrade Decisions with Machine-Learning Enhanced Optimization","authors":"Kenrick Howin Chai , Stefan Hildebrand , Tobias Lachnit , Martin Benfer , Gisela Lanza , Sandra Klinge","doi":"10.1016/j.procir.2025.09.008","DOIUrl":"10.1016/j.procir.2025.09.008","url":null,"abstract":"<div><div>Rental-based business models and increasing sustainability requirements intensify the need for efficient strategies to manage large machine and vehicle fleet renewal and upgrades. Optimized fleet upgrade strategies maximize overall utility, cost, and sustainability. However, conventional fleet optimization does not account for upgrade options and is based on integer programming with exponential runtime scaling, which leads to substantial computational cost when dealing with large fleets and repeated decision-making processes. This contribution firstly suggests an extended integer programming approach that determines optimal renewal and upgrade decisions. The computational burden is addressed by a second, alternative machine learning-based method that transforms the task to a mixed discrete-continuous optimization problem. Both approaches are evaluated in a real-world automotive industry case study, which shows that the machine learning approach achieves near-optimal solutions with significant improvements in the scalability and overall computational performance, thus making it a practical alternative for large-scale fleet management.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 7-12"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147424327","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}
Pub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.010
Carl Willy Mehling, Sven Pieper, Tobias Lüke, Julius Döbelt, Steffen Ihlenfeldt
As manufacturing systems become more automated and interconnected, diagnosing faults and identifying their root cause has become increasingly complex for human operators. Data-driven methods can help prevent costly downtime by leveraging Causal Discovery (CD) to map out how different machine components affect each other, while automated Root Cause Analysis (RCA) tracks down fault origins. However, progress in developing RCA and CD methods is hindered by the lack of real-world datasets that support their joint benchmarking in realistic manufacturing environments. We introduce the causRCA manufacturing dataset to fill this gap. The dataset comprises 170 data recordings from normal operation of a CNC vertical lathe and 100 simulated fault data recordings generated through a hardware-in-the-loop setup that combines a digital twin of the lathe with a physical controller. The dataset includes an expert-validated causal graph connecting the 92 included variables and alarms, serving as ground truth for evaluating both CD and causal RCA methods. We illustrate the versatility of causRCA through exemplary benchmarks that compare supervised RCA methods, unsupervised RCA methods, and CD algorithms on the dataset. Furthermore, we demonstrate its potential for answering research questions regarding causal RCA methods by analyzing how the quality of learned causal graphs affects RCA performance. All data, code, and documentation are publicly available to accelerate research in CD and automated RCA.
{"title":"Enabling Joint Benchmarking of Automated Root Cause Analysis and Causal Discovery in Manufacturing Using the causRCA Dataset","authors":"Carl Willy Mehling, Sven Pieper, Tobias Lüke, Julius Döbelt, Steffen Ihlenfeldt","doi":"10.1016/j.procir.2025.09.010","DOIUrl":"10.1016/j.procir.2025.09.010","url":null,"abstract":"<div><div>As manufacturing systems become more automated and interconnected, diagnosing faults and identifying their root cause has become increasingly complex for human operators. Data-driven methods can help prevent costly downtime by leveraging Causal Discovery (CD) to map out how different machine components affect each other, while automated Root Cause Analysis (RCA) tracks down fault origins. However, progress in developing RCA and CD methods is hindered by the lack of real-world datasets that support their joint benchmarking in realistic manufacturing environments. We introduce the causRCA manufacturing dataset to fill this gap. The dataset comprises 170 data recordings from normal operation of a CNC vertical lathe and 100 simulated fault data recordings generated through a hardware-in-the-loop setup that combines a digital twin of the lathe with a physical controller. The dataset includes an expert-validated causal graph connecting the 92 included variables and alarms, serving as ground truth for evaluating both CD and causal RCA methods. We illustrate the versatility of causRCA through exemplary benchmarks that compare supervised RCA methods, unsupervised RCA methods, and CD algorithms on the dataset. Furthermore, we demonstrate its potential for answering research questions regarding causal RCA methods by analyzing how the quality of learned causal graphs affects RCA performance. All data, code, and documentation are publicly available to accelerate research in CD and automated RCA.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 114-120"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425073","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}
Pub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.016
Marc A. Ahrens , Nicole Stricker
Machine Learning (ML) and Artificial Intelligence (AI) are well-established technologies in object classification and detection, with applications spanning from consumer products to industrial implementations such as part identification and quality inspection. Increasingly, ML and AI are seen as key enablers of the circular economy, particularly within disassembly and remanufacturing. Both fields are faced with challenges well suited for intelligent systems, notably the variability of parts. In disassembly, a wide range of different components in diverse states of wear from numerous products need to be identified and treated accordingly. This poses difficulties for traditional image-based computer vision systems, especially when training data is limited. This study investigates the application of point-cloud (PC) classification as a means to distinguish between products, enabling the identification of correct disassembly sequences and following remanufacturing treatment based on geometric differences, using real-world data to assess its practical applicability.
{"title":"Addressing Part Variability in Disassembly using Point Cloud-based Machine Learning","authors":"Marc A. Ahrens , Nicole Stricker","doi":"10.1016/j.procir.2025.09.016","DOIUrl":"10.1016/j.procir.2025.09.016","url":null,"abstract":"<div><div>Machine Learning (ML) and Artificial Intelligence (AI) are well-established technologies in object classification and detection, with applications spanning from consumer products to industrial implementations such as part identification and quality inspection. Increasingly, ML and AI are seen as key enablers of the circular economy, particularly within disassembly and remanufacturing. Both fields are faced with challenges well suited for intelligent systems, notably the variability of parts. In disassembly, a wide range of different components in diverse states of wear from numerous products need to be identified and treated accordingly. This poses difficulties for traditional image-based computer vision systems, especially when training data is limited. This study investigates the application of point-cloud (PC) classification as a means to distinguish between products, enabling the identification of correct disassembly sequences and following remanufacturing treatment based on geometric differences, using real-world data to assess its practical applicability.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 185-190"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425034","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}
Pub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.08.192
Pascal Cambatzu , Elisabeth Schmidl , Matthias Wenk
Asset Administration Shells (AAS) are a core element of Industry 4.0, which helps to create interoperability across machines and companies in production plants and hence support global digitalization. The capabilities of AAS for semantic description and the management of cross-machine data are usually the focus of attention. However, AAS can also be used for direct control by aggregating and historicizing machine data and making this data available to control applications. Using AAS in this way simplifies and reduces the necessary network connections between data sources and sinks and enables standardized access to production data. In addition to the basic capabilities of local communication, the software which interacts with the AAS must also have event-based functionalities for network communication. This paper presents such a software architecture that uses the BaSyx Python SDK to extend the AAS with event-based communication via OPC UA and enables historization through time series. Furthermore, an industrial plant is used to show how such software can structure the network topology to reach a more effective, decentralized control of individual plant areas.
{"title":"Asset Administration Shells in production environments: Implementation of decentralized, modular Agents with event-driven capabilities","authors":"Pascal Cambatzu , Elisabeth Schmidl , Matthias Wenk","doi":"10.1016/j.procir.2025.08.192","DOIUrl":"10.1016/j.procir.2025.08.192","url":null,"abstract":"<div><div>Asset Administration Shells (AAS) are a core element of Industry 4.0, which helps to create interoperability across machines and companies in production plants and hence support global digitalization. The capabilities of AAS for semantic description and the management of cross-machine data are usually the focus of attention. However, AAS can also be used for direct control by aggregating and historicizing machine data and making this data available to control applications. Using AAS in this way simplifies and reduces the necessary network connections between data sources and sinks and enables standardized access to production data. In addition to the basic capabilities of local communication, the software which interacts with the AAS must also have event-based functionalities for network communication. This paper presents such a software architecture that uses the BaSyx Python SDK to extend the AAS with event-based communication via OPC UA and enables historization through time series. Furthermore, an industrial plant is used to show how such software can structure the network topology to reach a more effective, decentralized control of individual plant areas.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 331-336"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425387","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}
Pub Date : 2026-01-01Epub Date: 2026-02-18DOI: 10.1016/j.procir.2025.09.040
Tim Hertzschuch , Marcel Merten , Johannes Koal , Hans Christian Schmale
In order to ensure the quality and sufficient clamping force of a bolted joint, real-time monitoring using measurement data is essential. Traditionally, expert systems or control windows analyze process signals such as torque and rotation angle. However, due to the large volume of data, some anomalies or faulty screw connections may go undetected. This article introduces a new hybrid method that combines machine learning with control windows. The method works by scaling both torque and rotation angle, making it applicable to all types of bolted connections. The algorithm requires only 20 training curves, significantly reducing the time needed for setup while still maintaining high accuracy.
{"title":"Hybrid model monitoring approach for screw tightening processes","authors":"Tim Hertzschuch , Marcel Merten , Johannes Koal , Hans Christian Schmale","doi":"10.1016/j.procir.2025.09.040","DOIUrl":"10.1016/j.procir.2025.09.040","url":null,"abstract":"<div><div>In order to ensure the quality and sufficient clamping force of a bolted joint, real-time monitoring using measurement data is essential. Traditionally, expert systems or control windows analyze process signals such as torque and rotation angle. However, due to the large volume of data, some anomalies or faulty screw connections may go undetected. This article introduces a new hybrid method that combines machine learning with control windows. The method works by scaling both torque and rotation angle, making it applicable to all types of bolted connections. The algorithm requires only 20 training curves, significantly reducing the time needed for setup while still maintaining high accuracy.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"139 ","pages":"Pages 237-243"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147425455","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号