Pub Date : 2025-01-01DOI: 10.1016/j.procir.2025.01.001
Sara Shafiee
The manufacturing sector has witnessed significant transformations in recent years, driven by the rapid advancements in artificial intelligence (AI) and its applications. Among the various AI technologies, Generative AI (GenAI) has emerged as a promising tool for revolutionizing the manufacturing process. This review paper provides an overview of the latest developments and applications of GenAI in the manufacturing process, highlighting its potential in the manufacturing process by reviewing the journal articles published in 2024 (Jan-May). This paper explores the landscape of GenAI in manufacturing, focusing on Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Transformer-Based Models. The paper underscores the pivotal role of GenAI in enhancing productivity, quality control, predictive maintenance, supply chain optimization, customization, and sustainability in manufacturing.
{"title":"Generative AI in manufacturing: a literature review of recent applications and future prospects","authors":"Sara Shafiee","doi":"10.1016/j.procir.2025.01.001","DOIUrl":"10.1016/j.procir.2025.01.001","url":null,"abstract":"<div><div>The manufacturing sector has witnessed significant transformations in recent years, driven by the rapid advancements in artificial intelligence (AI) and its applications. Among the various AI technologies, Generative AI (GenAI) has emerged as a promising tool for revolutionizing the manufacturing process. This review paper provides an overview of the latest developments and applications of GenAI in the manufacturing process, highlighting its potential in the manufacturing process by reviewing the journal articles published in 2024 (Jan-May). This paper explores the landscape of GenAI in manufacturing, focusing on Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Transformer-Based Models. The paper underscores the pivotal role of GenAI in enhancing productivity, quality control, predictive maintenance, supply chain optimization, customization, and sustainability in manufacturing.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"132 ","pages":"Pages 1-6"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511920","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}
Pub Date : 2025-01-01DOI: 10.1016/j.procir.2025.01.009
Lorenzo Colantonio , Lucas Equeter , Hugo Giovannelli , Pierre Dehombreux , Saïd Mahmoudi , François Ducobu
Monitoring the degradation of cutting tools is of utmost importance in the manufacturing world. Tools with substantial wear fail to produce high-quality parts in terms of geometry, residual stress, and surface finish. Furthermore, replacing tools in a non-optimal manner can lead to increased production costs and downtime. Therefore, monitoring the condition of the tool is essential to avoid these additional costs and ensure good production quality. This article explores various classification models, specifically VGG19, EfficientNetV2, and Vision Transformers. These models classify the state of tools using their images. Using transfer learning, a comparison of the best-performing artificial intelligence-based image analysis models is conducted to identify those most suitable for monitoring cutting tools. A comparative analysis of their generalizability, performance and explainability is realized. The model with the best performance is VGG19 with an accuracy of 94%, followed by EfficientNetV2 and ViT with an accuracy of 87%. A full comparison of these results is carried out.
{"title":"Image processing with deep-learning and transfer learning for cutting tool degradation monitoring","authors":"Lorenzo Colantonio , Lucas Equeter , Hugo Giovannelli , Pierre Dehombreux , Saïd Mahmoudi , François Ducobu","doi":"10.1016/j.procir.2025.01.009","DOIUrl":"10.1016/j.procir.2025.01.009","url":null,"abstract":"<div><div>Monitoring the degradation of cutting tools is of utmost importance in the manufacturing world. Tools with substantial wear fail to produce high-quality parts in terms of geometry, residual stress, and surface finish. Furthermore, replacing tools in a non-optimal manner can lead to increased production costs and downtime. Therefore, monitoring the condition of the tool is essential to avoid these additional costs and ensure good production quality. This article explores various classification models, specifically VGG19, EfficientNetV2, and Vision Transformers. These models classify the state of tools using their images. Using transfer learning, a comparison of the best-performing artificial intelligence-based image analysis models is conducted to identify those most suitable for monitoring cutting tools. A comparative analysis of their generalizability, performance and explainability is realized. The model with the best performance is VGG19 with an accuracy of 94%, followed by EfficientNetV2 and ViT with an accuracy of 87%. A full comparison of these results is carried out.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"132 ","pages":"Pages 50-55"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511921","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}
Pub Date : 2024-01-01DOI: 10.1016/j.procir.2024.07.012
Dominik Kuhn (M.Sc.) , Martin Karkowski (M.Sc.) , Jannis Pfister (M.Sc.) , Max Eichenwald (M.Sc.) , Rainer Müller (Prof. Dr.-Ing.)
Modern manufacturing methods demand highly flexible and reusable assembly systems. Such flexibility and reusability can be attained using systems that are modular. These modular systems have the ability to react faster to market forces and are adaptable beyond the limits of the so-called flexibility corridor. Also, placing the constraints of flexibility and reusability on software paves the way for design and usage of generic systems that have a relatively low initial cost.
However, these advantages are often overshadowed by the complexity of these software systems. Especially, one faces many difficulties in software modularizing the assembly system so that each module can be integrated seamlessly into the entire system. Defining an interface in the development phase is practically impossible given that systems evolve a lot before reaching production phase.
{"title":"Software architecture for adaptable assembly systems","authors":"Dominik Kuhn (M.Sc.) , Martin Karkowski (M.Sc.) , Jannis Pfister (M.Sc.) , Max Eichenwald (M.Sc.) , Rainer Müller (Prof. Dr.-Ing.)","doi":"10.1016/j.procir.2024.07.012","DOIUrl":"10.1016/j.procir.2024.07.012","url":null,"abstract":"<div><div>Modern manufacturing methods demand highly flexible and reusable assembly systems. Such flexibility and reusability can be attained using systems that are modular. These modular systems have the ability to react faster to market forces and are adaptable beyond the limits of the so-called flexibility corridor. Also, placing the constraints of flexibility and reusability on software paves the way for design and usage of generic systems that have a relatively low initial cost.</div><div>However, these advantages are often overshadowed by the complexity of these software systems. Especially, one faces many difficulties in software modularizing the assembly system so that each module can be integrated seamlessly into the entire system. Defining an interface in the development phase is practically impossible given that systems evolve a lot before reaching production phase.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"127 ","pages":"Pages 62-67"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426760","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}
Pub Date : 2024-01-01DOI: 10.1016/j.procir.2024.07.034
Jian XIONG , Zhijing ZHANG , Xinhai YU , Qimuge SAREN , Taiyu SU , Erbo LI
The Cassegrain telescope is widely used in aerospace exploration equipment, characterized by compact structure, complex optical path, and high imaging quality. However, due to the difficulty in establishing an accurate correspondence between the relative pose and imaging quality of a multi mirror group with real machining errors, the current Cassegrain telescope assembly process is very difficult, with blind operation, time-consuming, and low accuracy. This article proposes a high-precision adaptive alignment method for Cassegrain dual mirror optical systems based on machine learning algorisms, and an experimental adaptive alignment system with uncoupled degrees of freedom is developed. Firstly, the overall architecture of the adaptive alignment method is proposed consists of detection, calculation and alignment modules. In the detection module, the Zernike polynomial coefficient of wavefront aberration of the optical system is detected online through the interferometer, meanwhile the pose coordinates of the secondary mirror is accurately fed back through a 6-DOF nanoscale micro mechanism. In the calculation module, machine learning algorithm is applied to build a nonlinear mapping model between the Zernike coefficient and the pose coordinates of the secondary mirror. In the alignment module, the pose coordinates of the secondary mirror can be forced to adjust to the target position. Then, during the real alignment process, the Zernike coefficient test data of the optical system alignment process is monitored in real time, and the nonlinear mapping model is employed to calculate the pose coordinates and then the misalignment of the secondary mirror. Finally, the alignment module is driven to execute the pose correction according to the calculated misalignment value, realizing a high-precision adjustment of the Cassegrain dual mirror optical system. Experimental results shows that the average alignment time cost can be dramatically reduced from around 7 days using the current manual alignment method to just 30 minutes using the proposed adaptive alignment method for achieving a current standard alignment accuracy of wavefront aberration root mean square (RMS) less than 0.1λ, which greatly improves the assembly efficiency. This study proposes a new method for high-precision and efficient alignment of optical systems based on artificial intelligence and contributes to the efficiency improvement for optical assembly.
{"title":"A high-precision and efficient adaptive alignment method for Cassegrain dual mirror optical system based on machine learning algorithms","authors":"Jian XIONG , Zhijing ZHANG , Xinhai YU , Qimuge SAREN , Taiyu SU , Erbo LI","doi":"10.1016/j.procir.2024.07.034","DOIUrl":"10.1016/j.procir.2024.07.034","url":null,"abstract":"<div><div>The Cassegrain telescope is widely used in aerospace exploration equipment, characterized by compact structure, complex optical path, and high imaging quality. However, due to the difficulty in establishing an accurate correspondence between the relative pose and imaging quality of a multi mirror group with real machining errors, the current Cassegrain telescope assembly process is very difficult, with blind operation, time-consuming, and low accuracy. This article proposes a high-precision adaptive alignment method for Cassegrain dual mirror optical systems based on machine learning algorisms, and an experimental adaptive alignment system with uncoupled degrees of freedom is developed. Firstly, the overall architecture of the adaptive alignment method is proposed consists of detection, calculation and alignment modules. In the detection module, the Zernike polynomial coefficient of wavefront aberration of the optical system is detected online through the interferometer, meanwhile the pose coordinates of the secondary mirror is accurately fed back through a 6-DOF nanoscale micro mechanism. In the calculation module, machine learning algorithm is applied to build a nonlinear mapping model between the Zernike coefficient and the pose coordinates of the secondary mirror. In the alignment module, the pose coordinates of the secondary mirror can be forced to adjust to the target position. Then, during the real alignment process, the Zernike coefficient test data of the optical system alignment process is monitored in real time, and the nonlinear mapping model is employed to calculate the pose coordinates and then the misalignment of the secondary mirror. Finally, the alignment module is driven to execute the pose correction according to the calculated misalignment value, realizing a high-precision adjustment of the Cassegrain dual mirror optical system. Experimental results shows that the average alignment time cost can be dramatically reduced from around 7 days using the current manual alignment method to just 30 minutes using the proposed adaptive alignment method for achieving a current standard alignment accuracy of wavefront aberration root mean square (RMS) less than 0.1λ, which greatly improves the assembly efficiency. This study proposes a new method for high-precision and efficient alignment of optical systems based on artificial intelligence and contributes to the efficiency improvement for optical assembly.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"127 ","pages":"Pages 194-199"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426801","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}
Pub Date : 2024-01-01DOI: 10.1016/j.procir.2024.07.003
Felix Fraider, Michael Baranowski, Johannes Gerner, Chiara Cassiani, Philipp Geis, Felix Wirth, Jürgen Fleischer
Hairpin technology has recently become the predominant winding technology for the manufacturing of stators used in electric traction motors. In contrast to conventional winding techniques, the manufacturing process chain is based on rectangular wire which is bent into a three-dimensional U-shape – so-called hairpin coils. These hairpin coils have to be individually gripped and assembled to form the stator winding. There can be hundreds of hairpin coils in a single stator, which can also differ in shape. Therefore, gripping and moving the individual hairpin coils is a challenging task in terms of flexibility and cycle time. This paper presents an approach to meet the outlined requirements using additively manufactured vacuum grippers. A concept is investigated in which the vacuum is generated in a conventional vacuum ejector and fed to the vacuum gripper via hose lines. In contrast, the concept of a functionally integrated vacuum gripper manufactured by a new laser-sintering process with automated continuous fibre reinforcement is presented. Based on the laser-sintering process, a lightweight vacuum gripper with an integrated vacuum ejector can be manufactured in a single process step without additional costs for purchased parts. After a review of the state of the art in both hairpin-specific and additively manufactured lightweight grippers, experimental test series are carried out concerning the vacuum quality and the grip strength of the different vacuum gripper designs. Pull-off tests show that high holding forces of several Newtons are possible proving the basic usability of vacuum grippers for hairpins, even though the achievable vacuum quality of the functionally integrated vacuum gripper is lower than that of the conventional ejector. Comparison of the novel approaches with a conventional mechanical hairpin gripper regarding weight, production costs and production time show promising improvements.
最近，发夹技术已成为制造电力牵引电机定子的主要绕组技术。与传统绕组技术不同的是，该制造工艺链以矩形线材为基础，将其弯曲成三维 U 形--即所谓的发夹线圈。这些发夹式线圈必须单独抓取并组装成定子绕组。一个定子中可能有数百个发夹线圈，它们的形状也可能各不相同。因此，抓取和移动单个发夹线圈在灵活性和周期时间方面都是一项具有挑战性的任务。本文介绍了一种使用快速成型真空夹具来满足上述要求的方法。本文研究的概念是在传统的真空喷射器中产生真空，并通过软管输送到真空机械手。相比之下，本文提出了一种功能集成式真空机械手的概念，该机械手采用新型激光烧结工艺制造，并配有自动连续纤维加固装置。在激光烧结工艺的基础上，只需一道工序就能制造出带有集成真空喷射器的轻型真空抓取器，而无需增加外购部件的成本。在回顾了发夹式和加成型轻型机械手的技术现状之后，对不同真空机械手设计的真空质量和抓取强度进行了一系列实验测试。拉拔测试表明，尽管功能集成式真空夹具可达到的真空质量低于传统顶出器，但仍可实现几牛顿的高夹持力，这证明真空夹具对发卡的基本可用性。在重量、生产成本和生产时间方面，新方法与传统的机械发夹夹具进行了比较，结果表明两者都有很大的改进。
{"title":"Additively manufactured vacuum grippers for the flexible handling and assembly of hairpin coils in electric motor production","authors":"Felix Fraider, Michael Baranowski, Johannes Gerner, Chiara Cassiani, Philipp Geis, Felix Wirth, Jürgen Fleischer","doi":"10.1016/j.procir.2024.07.003","DOIUrl":"10.1016/j.procir.2024.07.003","url":null,"abstract":"<div><div>Hairpin technology has recently become the predominant winding technology for the manufacturing of stators used in electric traction motors. In contrast to conventional winding techniques, the manufacturing process chain is based on rectangular wire which is bent into a three-dimensional U-shape – so-called hairpin coils. These hairpin coils have to be individually gripped and assembled to form the stator winding. There can be hundreds of hairpin coils in a single stator, which can also differ in shape. Therefore, gripping and moving the individual hairpin coils is a challenging task in terms of flexibility and cycle time. This paper presents an approach to meet the outlined requirements using additively manufactured vacuum grippers. A concept is investigated in which the vacuum is generated in a conventional vacuum ejector and fed to the vacuum gripper via hose lines. In contrast, the concept of a functionally integrated vacuum gripper manufactured by a new laser-sintering process with automated continuous fibre reinforcement is presented. Based on the laser-sintering process, a lightweight vacuum gripper with an integrated vacuum ejector can be manufactured in a single process step without additional costs for purchased parts. After a review of the state of the art in both hairpin-specific and additively manufactured lightweight grippers, experimental test series are carried out concerning the vacuum quality and the grip strength of the different vacuum gripper designs. Pull-off tests show that high holding forces of several Newtons are possible proving the basic usability of vacuum grippers for hairpins, even though the achievable vacuum quality of the functionally integrated vacuum gripper is lower than that of the conventional ejector. Comparison of the novel approaches with a conventional mechanical hairpin gripper regarding weight, production costs and production time show promising improvements.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"127 ","pages":"Pages 8-13"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142426808","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}
Spatial data fusion algorithms are widely applied in dimensional metrology for quality assessment or surface reconstruction. Multi-sensor point cloud fusion combines the advantages of multiple sensors by merging their measurements into a single coordinate system and reducing the prediction uncertainty and systematic errors. Algorithms designed for these tasks employ many methods that require thorough evaluations through a common framework. To address this need, this paper proposes a framework for simultaneous registration and approximation, and introduces a reference data generator for unbiased evaluations of data fusion algorithms with heterogeneous and anisotropic noise assumptions for applications involving multiple sensors. The bias for the generated reference data is evaluated close to floating point accuracy, which validates the generation method, and uncertainty evaluation on ICP variants reveals that reference data is more suitable to evaluate point cloud fusion algorithms. The proposed framework and data generator allows developing and validating more accurate data fusion algorithms.
{"title":"Multi-sensor data fusion framework and validation of algorithms with reference datasets","authors":"Louis-Ferdinand Lafon , Alain Vissière , Charyar Mehdi-Souzani , Hichem Nouira , Nabil Anwer","doi":"10.1016/j.procir.2024.10.024","DOIUrl":"10.1016/j.procir.2024.10.024","url":null,"abstract":"<div><div>Spatial data fusion algorithms are widely applied in dimensional metrology for quality assessment or surface reconstruction. Multi-sensor point cloud fusion combines the advantages of multiple sensors by merging their measurements into a single coordinate system and reducing the prediction uncertainty and systematic errors. Algorithms designed for these tasks employ many methods that require thorough evaluations through a common framework. To address this need, this paper proposes a framework for simultaneous registration and approximation, and introduces a reference data generator for unbiased evaluations of data fusion algorithms with heterogeneous and anisotropic noise assumptions for applications involving multiple sensors. The bias for the generated reference data is evaluated close to floating point accuracy, which validates the generation method, and uncertainty evaluation on ICP variants reveals that reference data is more suitable to evaluate point cloud fusion algorithms. The proposed framework and data generator allows developing and validating more accurate data fusion algorithms.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"129 ","pages":"Pages 133-138"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142555679","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}
Pub Date : 2024-01-01DOI: 10.1016/j.procir.2024.03.037
J. Hidalgo-Crespo , Andreas Riel , Paulina Golinska-Dawson , Jef R. Peeters , Karolina Werner-Lewandowska , Joost R. Duflou
The move towards a circular economy brings a range of practical challenges for product and service designers that will need to facilitate this transformation from a linear take-make-dispose model to a more circular model. The concept of Product-as-a-Service (PaaS) emerges as an innovative business model capable of catalyzing this fundamental shift. In a PaaS context, any product will be used by several different customers during its lifetime through different operational methodologies and value delivery mechanisms, so incorporating circularity into both product and service design is pivotal for the establishment of more sustainable product-service systems. To facilitate circularity, it is imperative to be able to close loops in the current PaaS offerings by the development of reuse, refurbishment, repair, remanufacturing, and recycling. However, different challenges arise from each of them, which translate into different design guidelines. With the help of the literature and through a cooperative ERA-MIN project, different expert partners provided their insights on the proposed PaaS offering for electrical and electronic equipment (EEE). The objective of this paper is to present the main challenges and describe the design guidelines derived from them.
{"title":"Facilitating circularity: challenges and design guidelines of Product-as-a-Service (PaaS) business model offers for electrical and electronic equipment","authors":"J. Hidalgo-Crespo , Andreas Riel , Paulina Golinska-Dawson , Jef R. Peeters , Karolina Werner-Lewandowska , Joost R. Duflou","doi":"10.1016/j.procir.2024.03.037","DOIUrl":"10.1016/j.procir.2024.03.037","url":null,"abstract":"<div><div>The move towards a circular economy brings a range of practical challenges for product and service designers that will need to facilitate this transformation from a linear take-make-dispose model to a more circular model. The concept of Product-as-a-Service (PaaS) emerges as an innovative business model capable of catalyzing this fundamental shift. In a PaaS context, any product will be used by several different customers during its lifetime through different operational methodologies and value delivery mechanisms, so incorporating circularity into both product and service design is pivotal for the establishment of more sustainable product-service systems. To facilitate circularity, it is imperative to be able to close loops in the current PaaS offerings by the development of reuse, refurbishment, repair, remanufacturing, and recycling. However, different challenges arise from each of them, which translate into different design guidelines. With the help of the literature and through a cooperative ERA-MIN project, different expert partners provided their insights on the proposed PaaS offering for electrical and electronic equipment (EEE). The objective of this paper is to present the main challenges and describe the design guidelines derived from them.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"128 ","pages":"Pages 567-572"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142437631","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}
Pub Date : 2024-01-01DOI: 10.1016/j.procir.2024.03.017
Rieke Leder , Ann-Kathrin Rohde , Nicolas Jathe , Michael Lütjen , Michael Freitag
Employee assistance systems are essential for companies to manage the growing complexity of information and processes. However, current systems mainly provide process-oriented support through documentation options, leaving a gap in real-time quality assessment. Real-time or in-process quality assessment becomes increasingly attractive for large and complex components where automated inspection is not feasible. To fill this gap, this paper proposes a new modeling framework for quality-centric assistance systems that are tailored to the Smart Factory environment. The framework integrates digital design principles, standard manufacturing processes, and quality parameters, facilitating seamless integration and standardized data exchange. An expert evaluation of the framework yielded positive ratings across various dimensions, underscoring its potential impact. Feedback from experts indicated the need for further refinement, including enhancing credibility through implementation and field tests, providing more detailed procedure models, and addressing challenges in sensor integration. Overall, this framework represents a significant advancement towards process-oriented assistance in various application areas, with implications for optimizing production and quality processes.
{"title":"Framework for Designing Quality-Centered Assistance Systems for the Smart Factory","authors":"Rieke Leder , Ann-Kathrin Rohde , Nicolas Jathe , Michael Lütjen , Michael Freitag","doi":"10.1016/j.procir.2024.03.017","DOIUrl":"10.1016/j.procir.2024.03.017","url":null,"abstract":"<div><div>Employee assistance systems are essential for companies to manage the growing complexity of information and processes. However, current systems mainly provide process-oriented support through documentation options, leaving a gap in real-time quality assessment. Real-time or in-process quality assessment becomes increasingly attractive for large and complex components where automated inspection is not feasible. To fill this gap, this paper proposes a new modeling framework for quality-centric assistance systems that are tailored to the Smart Factory environment. The framework integrates digital design principles, standard manufacturing processes, and quality parameters, facilitating seamless integration and standardized data exchange. An expert evaluation of the framework yielded positive ratings across various dimensions, underscoring its potential impact. Feedback from experts indicated the need for further refinement, including enhancing credibility through implementation and field tests, providing more detailed procedure models, and addressing challenges in sensor integration. Overall, this framework represents a significant advancement towards process-oriented assistance in various application areas, with implications for optimizing production and quality processes.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"128 ","pages":"Pages 381-386"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142437635","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}
Pub Date : 2024-01-01DOI: 10.1016/j.procir.2024.06.013
Gibson P. Chirinda , Stephen Matope , Philani Zincume , Whisper Maisiri , Andreas Sterzing
The United Nations (UN) Sustainable Development Goal 13 focuses on taking urgent action to combat climate change and its impacts. Resource efficient production and strict emission regulations have made vehicle weight reduction a subject of great interest. Common lightweighting techniques include topology optimization and material substitution. The benefits include reduced raw material usage, low fuel consumption, and low carbon emissions. There is a gap in the complex balance of decision-making. If an engineer is faced with the option of topologically optimizing or materially substituting, is one method better than the other? This paper comparatively analyses these lightweight design strategies.
{"title":"Comparative analysis of topology optimization versus material substitution: Is there a best method for vehicle weight reduction?","authors":"Gibson P. Chirinda , Stephen Matope , Philani Zincume , Whisper Maisiri , Andreas Sterzing","doi":"10.1016/j.procir.2024.06.013","DOIUrl":"10.1016/j.procir.2024.06.013","url":null,"abstract":"<div><div>The United Nations (UN) Sustainable Development Goal 13 focuses on taking urgent action to combat climate change and its impacts. Resource efficient production and strict emission regulations have made vehicle weight reduction a subject of great interest. Common lightweighting techniques include topology optimization and material substitution. The benefits include reduced raw material usage, low fuel consumption, and low carbon emissions. There is a gap in the complex balance of decision-making. If an engineer is faced with the option of topologically optimizing or materially substituting, is one method better than the other? This paper comparatively analyses these lightweight design strategies.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"128 ","pages":"Pages 132-137"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142437683","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}
Pub Date : 2024-01-01DOI: 10.1016/j.procir.2024.06.015
Sander Evenrud Kildal , Jonas Rossavik Johannessen , Daniel Nygård Ege , Martin Francis Berg , Martin Steinert
This paper explores the practical adoption challenges of Industry 4.0 principles in Small Enterprises (SEs), particularly through the development of an automated stapler prototype for acoustic slat panel production. The study presents a case where the prototype, costing less than 400 euros, is shown to potentially increase the production rate by 42%, showcasing the feasibility of cost-effective, tailored solutions in digitizing manufacturing processes within SEs. It demonstrates that such incremental improvements can substantially boost productivity and efficiency, enabling SEs to better compete in increasingly demanding markets while also mitigating the high cost and physical strains associated with manual labor. The presented approach of prioritizing significant improvements over complete automation aligns well with the practical and financial constraints of SEs. Moreover, the paper challenges the notion that the adoption of Industry 4.0 necessitates substantial investment, by highlighting the importance of flexible, low-cost prototyping in overcoming financial and technical constraints, suggesting a shift towards accessible digital transformation in the manufacturing sector.
{"title":"Prototyping Industry 4.0: The Case of an Automated Stapler for Acoustic Slat Panel Production","authors":"Sander Evenrud Kildal , Jonas Rossavik Johannessen , Daniel Nygård Ege , Martin Francis Berg , Martin Steinert","doi":"10.1016/j.procir.2024.06.015","DOIUrl":"10.1016/j.procir.2024.06.015","url":null,"abstract":"<div><div>This paper explores the practical adoption challenges of Industry 4.0 principles in Small Enterprises (SEs), particularly through the development of an automated stapler prototype for acoustic slat panel production. The study presents a case where the prototype, costing less than 400 euros, is shown to potentially increase the production rate by 42%, showcasing the feasibility of cost-effective, tailored solutions in digitizing manufacturing processes within SEs. It demonstrates that such incremental improvements can substantially boost productivity and efficiency, enabling SEs to better compete in increasingly demanding markets while also mitigating the high cost and physical strains associated with manual labor. The presented approach of prioritizing significant improvements over complete automation aligns well with the practical and financial constraints of SEs. Moreover, the paper challenges the notion that the adoption of Industry 4.0 necessitates substantial investment, by highlighting the importance of flexible, low-cost prototyping in overcoming financial and technical constraints, suggesting a shift towards accessible digital transformation in the manufacturing sector.</div></div>","PeriodicalId":20535,"journal":{"name":"Procedia CIRP","volume":"128 ","pages":"Pages 144-149"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142437685","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}
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