Pub Date : 2026-01-01DOI: 10.1016/j.procir.2026.01.078
Lionel Damtew , Niklas Michel-Angeli , Nicklas Gerhard , Philipp Ganser , Thomas Bergs
This paper introduces a novel framework for incorporating machine limitations into the design process of turbine compressor blade geometries in 5-axis milling. By utilizing analytical equations, the expected deviation in feed rate and position can be quantified based on the component’s design, leading to the identification of additional geometric boundary conditions. The approach is validated through machining experiments on simple single-blade geometries. The framework enables better collaboration between component design and process design, leading to improved manufacturing precision, reduced process time, and enhanced turbine part quality.
{"title":"A novel framework for incorporating machine limitations into component design for 5-axis milling","authors":"Lionel Damtew , Niklas Michel-Angeli , Nicklas Gerhard , Philipp Ganser , Thomas Bergs","doi":"10.1016/j.procir.2026.01.078","DOIUrl":"10.1016/j.procir.2026.01.078","url":null,"abstract":"<div><div>This paper introduces a novel framework for incorporating machine limitations into the design process of turbine compressor blade geometries in 5-axis milling. By utilizing analytical equations, the expected deviation in feed rate and position can be quantified based on the component’s design, leading to the identification of additional geometric boundary conditions. The approach is validated through machining experiments on simple single-blade geometries. The framework enables better collaboration between component design and process design, leading to improved manufacturing precision, reduced process time, and enhanced turbine part quality.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 450-455"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162160","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 : 2026-01-01DOI: 10.1016/j.procir.2026.01.015
Benjamin Staar , Nicolas Jathe , Michael Lütjen , Michael Freitag
In face of a shrinking workforce, logistics companies need to automate low-skill high-effort tasks in order to remain competitive in terms of market share and job attractiveness. This often includes camera-based detection of parcels. While recent advances in AI-based image processing enable the training of powerful object detection algorithms, acquiring the required annotated data set is tedious and cost-intensive. We test the ability of Segment-Anything type zero-shot segmentation models in assisting data annotation for parcel detection. Evaluation on the publically available Stacked Carton Dataset shows that over 93% of segmentation masks can be extracted successfully with these models while also providing insights for future improvements.
{"title":"Semi-automated data annotation for parcel detection in warehouses with Zero-Shot image segmentation methods: an evaluation","authors":"Benjamin Staar , Nicolas Jathe , Michael Lütjen , Michael Freitag","doi":"10.1016/j.procir.2026.01.015","DOIUrl":"10.1016/j.procir.2026.01.015","url":null,"abstract":"<div><div>In face of a shrinking workforce, logistics companies need to automate low-skill high-effort tasks in order to remain competitive in terms of market share and job attractiveness. This often includes camera-based detection of parcels. While recent advances in AI-based image processing enable the training of powerful object detection algorithms, acquiring the required annotated data set is tedious and cost-intensive. We test the ability of Segment-Anything type zero-shot segmentation models in assisting data annotation for parcel detection. Evaluation on the publically available Stacked Carton Dataset shows that over 93% of segmentation masks can be extracted successfully with these models while also providing insights for future improvements.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 78-83"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146161911","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 : 2026-01-01DOI: 10.1016/j.procir.2026.01.019
Philipp Prünte , Jonathan Determann , Keno Moenck , Eidan Erlich , Dhananjay Patki , Frank Bitte , Martin Gomse , Thorsten Schüppstuhl
Today’s rapidly evolving industrial landscape and the progressive digitization of products, processes, and resources require massive amounts of online data on the current production and logistical status. Fixed-positioned sensor systems have a constrained Field of View (FoV), while a mobile system can significantly extend these, enabling further applications due to the larger observed space. In this work, we elaborate on potential applications that utilize incidentally acquired data from various locations from the perspective of a mobile, vision-based sensor system. We exemplarily demonstrate an application within the scope of capturing and triggering the intralogistics chain with data from a vision-based sensor system that can be carried by an Autonomous Guided Vehicle (AGV).
{"title":"Leveraging passive monitoring applications in production and intralogistics","authors":"Philipp Prünte , Jonathan Determann , Keno Moenck , Eidan Erlich , Dhananjay Patki , Frank Bitte , Martin Gomse , Thorsten Schüppstuhl","doi":"10.1016/j.procir.2026.01.019","DOIUrl":"10.1016/j.procir.2026.01.019","url":null,"abstract":"<div><div>Today’s rapidly evolving industrial landscape and the progressive digitization of products, processes, and resources require massive amounts of online data on the current production and logistical status. Fixed-positioned sensor systems have a constrained Field of View (FoV), while a mobile system can significantly extend these, enabling further applications due to the larger observed space. In this work, we elaborate on potential applications that utilize incidentally acquired data from various locations from the perspective of a mobile, vision-based sensor system. We exemplarily demonstrate an application within the scope of capturing and triggering the intralogistics chain with data from a vision-based sensor system that can be carried by an Autonomous Guided Vehicle (AGV).</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 102-107"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146161934","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 : 2026-01-01DOI: 10.1016/j.procir.2026.01.024
Matthias Klar , Arsalan Jawaid , Peter M. Simon , Marcel Wagner , Jörg Seewig , Bahram Ravani , Jan C. Aurich
The result of the factory layout planning process has a direct impact on the operating costs of the future manufacturing systems. As manual layout planning is a time-consuming process, automated approaches have been developed to optimize factory layouts under varying boundary conditions and optimization objectives. Recent developments show that single-agent reinforcement learning (RL) approaches are capable of optimizing factory layouts. Extending the existing single-agent approache to a multi-agent RL approach offers performance-related potential that has not been investigated so far. The use of a multi-agent RL approach which can distribute the task of layout optimization can lead to improved layout variants. However, building a multi-agent approach also involves several challenges, such as partial observability and competition among agents. It is not clear which approach is more suitable for factory layout planning and under what conditions one approach can be chosen over the other. This paper addresses this research gap by comparing a single-agent and a multi-agent RL approach for factory layout planning. The performance of both approaches is compared based on an application scenario of 30 functional units, using the transportation intensity as the optimization criterion. The results show that the single-agent RL approach outperforms the multi-agent RL approach slightly. One conclusion is that the advantages of using a multi-agent RL approach can not overcome the corresponding challenges.
{"title":"Performance Comparison of Single-Agent and Multi-Agent Reinforcement Learning for Factory Layout Planning","authors":"Matthias Klar , Arsalan Jawaid , Peter M. Simon , Marcel Wagner , Jörg Seewig , Bahram Ravani , Jan C. Aurich","doi":"10.1016/j.procir.2026.01.024","DOIUrl":"10.1016/j.procir.2026.01.024","url":null,"abstract":"<div><div>The result of the factory layout planning process has a direct impact on the operating costs of the future manufacturing systems. As manual layout planning is a time-consuming process, automated approaches have been developed to optimize factory layouts under varying boundary conditions and optimization objectives. Recent developments show that single-agent reinforcement learning (RL) approaches are capable of optimizing factory layouts. Extending the existing single-agent approache to a multi-agent RL approach offers performance-related potential that has not been investigated so far. The use of a multi-agent RL approach which can distribute the task of layout optimization can lead to improved layout variants. However, building a multi-agent approach also involves several challenges, such as partial observability and competition among agents. It is not clear which approach is more suitable for factory layout planning and under what conditions one approach can be chosen over the other. This paper addresses this research gap by comparing a single-agent and a multi-agent RL approach for factory layout planning. The performance of both approaches is compared based on an application scenario of 30 functional units, using the transportation intensity as the optimization criterion. The results show that the single-agent RL approach outperforms the multi-agent RL approach slightly. One conclusion is that the advantages of using a multi-agent RL approach can not overcome the corresponding challenges.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 132-137"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146161939","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 : 2026-01-01DOI: 10.1016/j.procir.2026.01.025
Andreas Herzog , Melanie Rentzsch , Gesa Götte , Sebastian Häberer
Self-organizing production requires interaction mechanisms that enable actors to successfully deal with different, new and undescribed situations. This demands comprehensive recognition and processing of context, target, and status information. A challenge arising from the complexity of information to be processed lies in the slowdown in processing speeds. One solution is the realization of vectors that represent high-dimensional and specific information in low-dimensional and standardized forms. Modelled upon human emotions as expressions of the results of previous evaluation processes, these are referred to as EMOTION vectors. In systems of distributed cognition, they convey the information required for effective cooperation of actors.
{"title":"EMOTION Vectors: Enabling Self-Organizing Production Through Efficient Information Processing in Distributed Cognitive Systems","authors":"Andreas Herzog , Melanie Rentzsch , Gesa Götte , Sebastian Häberer","doi":"10.1016/j.procir.2026.01.025","DOIUrl":"10.1016/j.procir.2026.01.025","url":null,"abstract":"<div><div>Self-organizing production requires interaction mechanisms that enable actors to successfully deal with different, new and undescribed situations. This demands comprehensive recognition and processing of context, target, and status information. A challenge arising from the complexity of information to be processed lies in the slowdown in processing speeds. One solution is the realization of vectors that represent high-dimensional and specific information in low-dimensional and standardized forms. Modelled upon human emotions as expressions of the results of previous evaluation processes, these are referred to as EMOTION vectors. In systems of distributed cognition, they convey the information required for effective cooperation of actors.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 138-143"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146161940","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}
Industrial robots suffer from low absolute pose accuracy, hampering their widespread use in manufacturing tasks such as milling, additive manufacturing or forming. Meanwhile, computer vision is becoming increasingly relevant in terms of digitalization. This paper introduces a method for direct closed-loop control of industrial robot’s pose deviations using a redundant camera tracking system. The approach is compatible with commercially available robot controllers. In particular, a real-time data interface for FANUC robot controllers is presented. By means of the proposed method, the absolute pose accuracy can be increased by more than 90 % in position and orientation even under external loading.
{"title":"Real-time direct pose control of industrial robots with proprietary robot controller based on a redundant camera tracking system","authors":"Eckart Uhlmann , Mitchel Polte , Julian Blumberg , Oliver Sobiak","doi":"10.1016/j.procir.2026.01.049","DOIUrl":"10.1016/j.procir.2026.01.049","url":null,"abstract":"<div><div>Industrial robots suffer from low absolute pose accuracy, hampering their widespread use in manufacturing tasks such as milling, additive manufacturing or forming. Meanwhile, computer vision is becoming increasingly relevant in terms of digitalization. This paper introduces a method for direct closed-loop control of industrial robot’s pose deviations using a redundant camera tracking system. The approach is compatible with commercially available robot controllers. In particular, a real-time data interface for FANUC robot controllers is presented. By means of the proposed method, the absolute pose accuracy can be increased by more than 90 % in position and orientation even under external loading.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 280-285"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162010","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 : 2026-01-01DOI: 10.1016/j.procir.2026.01.062
Markus Brillinger , Josef Mündler , Jörg Edler , Michael Heiss , Franz Haas
Moving towards sustainable production, zero-defect manufacturing plays an important role. Achieving this, the identification of material defects during machining is a decisive factor. This paper introduces innovation through a theoretical model for the smallest detectable material defect in machining, solely based on machine data from the existing numerical controller, eliminating the need for external sensors. The verified model correlates the material defect size with spindle torque changes (affected by tool-, material-, machine-, and machining parameters) and demonstrates the identification of 0.2mm defects compared to 0.7mm in the literature as a remarkable contribution to zero-defect manufacturing.
{"title":"Exploring the edge of the edge: Utilization of available CNC machine data for material defect detection","authors":"Markus Brillinger , Josef Mündler , Jörg Edler , Michael Heiss , Franz Haas","doi":"10.1016/j.procir.2026.01.062","DOIUrl":"10.1016/j.procir.2026.01.062","url":null,"abstract":"<div><div>Moving towards sustainable production, zero-defect manufacturing plays an important role. Achieving this, the identification of material defects during machining is a decisive factor. This paper introduces innovation through a theoretical model for the smallest detectable material defect in machining, solely based on machine data from the existing numerical controller, eliminating the need for external sensors. The verified model correlates the material defect size with spindle torque changes (affected by tool-, material-, machine-, and machining parameters) and demonstrates the identification of 0.2mm defects compared to 0.7mm in the literature as a remarkable contribution to zero-defect manufacturing.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 357-362"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162071","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 : 2026-01-01DOI: 10.1016/j.procir.2026.01.067
Andreas Baumann, Peter Eberhard
Single-lip deep hole drilling is characterized by a high-quality hole and a high level of productivity achieved. It is performed using high feed rates in a single pass, and, therefore, chips must be removed by the cooling liquid. However, chip jamming is a significant problem when chips wrap around the tool, leading to marks on the borehole wall and an increased drilling torque, potentially causing sudden tool failure. The Smoothed Particle Hydrodynamics method is applied to simulate the challenging fluid flow and elastic bodies. A first approach is developed to model the effects of chip jamming and the possible consequence of drill breakage for a deeper understanding of the process behavior.
{"title":"Investigation of Chip Jamming and Drill Breakage in Deep-Hole Drilling using Smoothed Particle Hydrodynamics","authors":"Andreas Baumann, Peter Eberhard","doi":"10.1016/j.procir.2026.01.067","DOIUrl":"10.1016/j.procir.2026.01.067","url":null,"abstract":"<div><div>Single-lip deep hole drilling is characterized by a high-quality hole and a high level of productivity achieved. It is performed using high feed rates in a single pass, and, therefore, chips must be removed by the cooling liquid. However, chip jamming is a significant problem when chips wrap around the tool, leading to marks on the borehole wall and an increased drilling torque, potentially causing sudden tool failure. The Smoothed Particle Hydrodynamics method is applied to simulate the challenging fluid flow and elastic bodies. A first approach is developed to model the effects of chip jamming and the possible consequence of drill breakage for a deeper understanding of the process behavior.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 387-392"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162076","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 : 2026-01-01DOI: 10.1016/j.procir.2026.01.087
Markus Diegel , Markus Meurer , Thomas Bergs
The use of tungsten carbide for components of stamping and forming tools increases the efficiency of the manufacturing process and improves product quality. The limiting factor for the application of this material is the time and cost intensive machinability. To improve process understanding and facilitate tool design for machining tungsten carbide with defined cutting edge, orthogonal cutting tests with diamond coated carbide tools were carried out in this study. The occurrence and influence of a flaking of coating on the rake face were evaluated by monitoring the cutting force, cutting normal force, temperature and chip formation. Observed was an improved machinability caused by a self-sharpening effect of the tool due to the flaking of the coating.
{"title":"Improved cutting of tungsten carbide after flaking of diamond coating","authors":"Markus Diegel , Markus Meurer , Thomas Bergs","doi":"10.1016/j.procir.2026.01.087","DOIUrl":"10.1016/j.procir.2026.01.087","url":null,"abstract":"<div><div>The use of tungsten carbide for components of stamping and forming tools increases the efficiency of the manufacturing process and improves product quality. The limiting factor for the application of this material is the time and cost intensive machinability. To improve process understanding and facilitate tool design for machining tungsten carbide with defined cutting edge, orthogonal cutting tests with diamond coated carbide tools were carried out in this study. The occurrence and influence of a flaking of coating on the rake face were evaluated by monitoring the cutting force, cutting normal force, temperature and chip formation. Observed was an improved machinability caused by a self-sharpening effect of the tool due to the flaking of the coating.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"138 ","pages":"Pages 504-509"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146162150","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