Frontiers in Manufacturing Technology最新文献

{"title":"Optical character recognition on engineering drawings to achieve automation in production quality control","authors":"Javier Villena Toro, A. Wiberg, M. Tarkian","doi":"10.3389/fmtec.2023.1154132","DOIUrl":"https://doi.org/10.3389/fmtec.2023.1154132","url":null,"abstract":"Introduction: Digitization is a crucial step towards achieving automation in production quality control for mechanical products. Engineering drawings are essential carriers of information for production, but their complexity poses a challenge for computer vision. To enable automated quality control, seamless data transfer between analog drawings and CAD/CAM software is necessary. Methods: This paper focuses on autonomous text detection and recognition in engineering drawings. The methodology is divided into five stages. First, image processing techniques are used to classify and identify key elements in the drawing. The output is divided into three elements: information blocks and tables, feature control frames, and the rest of the image. For each element, an OCR pipeline is proposed. The last stage is output generation of the information in table format. Results: The proposed tool, called eDOCr, achieved a precision and recall of 90% in detection, an F1-score of 94% in recognition, and a character error rate of 8%. The tool enables seamless integration between engineering drawings and quality control. Discussion: Most OCR algorithms have limitations when applied to mechanical drawings due to their inherent complexity, including measurements, orientation, tolerances, and special symbols such as geometric dimensioning and tolerancing (GD&T). The eDOCr tool overcomes these limitations and provides a solution for automated quality control. Conclusion: The eDOCr tool provides an effective solution for automated text detection and recognition in engineering drawings. The tool's success demonstrates that automated quality control for mechanical products can be achieved through digitization. The tool is shared with the research community through Github.","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127114557","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":"Automation of unstructured production environment by applying reinforcement learning","authors":"Sanjay Nambiar, A. Wiberg, M. Tarkian","doi":"10.3389/fmtec.2023.1154263","DOIUrl":"https://doi.org/10.3389/fmtec.2023.1154263","url":null,"abstract":"Implementation of Machine Learning (ML) to improve product and production development processes poses a significant opportunity for manufacturing industries. ML has the capability to calibrate models with considerable adaptability and high accuracy. This capability is specifically promising for applications where classical production automation is too expensive, e.g., for mass customization cases where the production environment is uncertain and unstructured. To cope with the diversity in production systems and working environments, Reinforcement Learning (RL) in combination with lightweight game engines can be used from initial stages of a product and production development process. However, there are multiple challenges such as collecting observations in a virtual environment which can interact similar to a physical environment. This project focuses on setting up RL methodologies to perform path-finding and collision detection in varying environments. One case study is human assembly evaluation method in the automobile industry which is currently manual intensive to investigate digitally. For this case, a mannequin is trained to perform pick and place operations in varying environments and thus automating assembly validation process in early design phases. The next application is path-finding of mobile robots including an articulated arm to perform pick and place operations. This application is expensive to setup with classical methods and thus RL enables an automated approach for this task as well.","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"37 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114126027","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":"Potential environmental impacts of a plastic waste export ban in Germany","authors":"Ronja Strobel, Tabea Hagedorn, A. C. Lopes","doi":"10.3389/fmtec.2023.1077313","DOIUrl":"https://doi.org/10.3389/fmtec.2023.1077313","url":null,"abstract":"Up to 800,000 t/a of plastic waste generated in Germany is exported, of which more than a quarter is packaging. However, a sustainable waste management system aims at treating waste under consideration of environmental benefits generation and the reduction of negative environmental impacts. Thus, this brief research deals with the question to what extent negative environmental impacts could be avoided by an export ban. Further, this brief research serves as a preliminary basis for further discussions and studies in the field of the plastic export ban. Two scenarios were developed based on expert interviews to estimate alternative management for the otherwise exported plastic waste generated in Germany. A consequential life cycle assessment (LCA) was carried out to look into the possible Global Warming Potential changes of such scenarios compared to the current situation scenario. The LCA showed that an export ban in Germany offers the possibility of avoiding up to 80 CO2-equivalent per ton of exported packaging plastic. However, this would be only possible if most of the plastic packaging that is no longer exported is recycled and not burned for energy production in the case of Germany.","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130923432","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":"Towards a multi-abrasive grinding model for the material point method","authors":"S. Leroch, P. Grützmacher, H. Heckes, S. Eder","doi":"10.3389/fmtec.2023.1114414","DOIUrl":"https://doi.org/10.3389/fmtec.2023.1114414","url":null,"abstract":"An efficient optimization of surface finishing processes can save high amounts of energy and resources. Because of the large occurring deformations, grinding processes are notoriously difficult to model using standard (mesh-based) micro-scale modeling techniques. In this work, we use the meshless material point method to study the influence of abrasive shape, orientation, rake angle, and infeed depth on the grinding result. We discuss the chip morphology, the surface topography, cutting versus plowing mode, the material removal rate, and the chip temperature. A generalization of our model from a straightforward single-abrasive approach to a multiple-abrasive simulation with pseudo-periodical boundary conditions greatly increases the degree of realism and lays the foundation for comparison with real finishing processes. We finally compare our results for multiple abrasives to those obtained for a scaled-down molecular dynamics system and discuss similarities and differences.","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117061641","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":"Investigation of probing repeatability inside a micro-hole by changing probe approach direction for a local surface interaction force detection type microprobe","authors":"Masakazu Aruga, S. Ito, Daichi Kato, Kimihisa Matsumoto, K. Kamiya","doi":"10.3389/fmtec.2023.1104742","DOIUrl":"https://doi.org/10.3389/fmtec.2023.1104742","url":null,"abstract":"The inner diameter measurement of the micro-hole was performed by a tactile microprobing system using a method of the local surface interaction force detection. The inner diameter of the micro-hole was calculated by the least square method based on the probing coordinates obtained by a custom-made micro-coordinate measuring machine. The dispersion of the probing coordinates was investigated by changing the probe approaching direction with respect to the normal direction of the inner side of the micro-hole. During the probing inside the micro-hole, it was confirmed that the dispersion of the probing coordinates increased when the disagreement between the probe approaching direction and the normal direction of the micro-hole at the measured point became large. The influence of the dispersion of the probing coordinates was evaluated through the uncertainty analysis of the inner diameter measurement. It was revealed that the uncertainty of the inner diameter measurement could be improved when limiting the disagreement between the probe approaching direction and the normal direction of the micro-hole to within ±pi/4 rad.","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131139300","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":"A pricing model to monetize your industrial data","authors":"Gorka Mendizabal-Arrieta, Eduardo Castellano-Fernández, M. Rapaccini","doi":"10.3389/fmtec.2023.1057537","DOIUrl":"https://doi.org/10.3389/fmtec.2023.1057537","url":null,"abstract":"Data monetization has become a relevant aspect of the industrial manufacturing. Consequently, this paper proposes a theoretical framework as well as a mathematical model to price industrial data. For this purpose, three characteristics of the data were considered, i.e. 1) quality; 2) entropy and 3) value. Besides, the role of data marketplace’s players was analyzed. In order to validate the economic equation, a case study was carried out by a Spanish manufacturer.","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"76 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131726152","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":"Potentials of grinding process simulations for the analysis of individual grain engagement and complete grinding processes","authors":"P. Wiederkehr, A. Grimmert, Ines Heining, T. Siebrecht, F. Wöste","doi":"10.3389/fmtec.2022.1102140","DOIUrl":"https://doi.org/10.3389/fmtec.2022.1102140","url":null,"abstract":"Grinding processes are very complex due to the multitude of influencing parameters, resulting from the stochastic tool topography with numerous geometrically undefined abrasive cutting edges. Thus, the efficient design and optimization of these processes is a challenging task. Process simulations can be used as a flexible tool for analyzing interdependencies between several process parameters and identifying suitable process parameter values. For a precise process analysis, the choice of a process model with a corresponding model scale as well as the representation of optimization-relevant process effects are necessary. While macroscopic model approaches can be used to estimate the thermo-mechanical loads occurring in the contact zone, explicit modeling of the individual abrasive grains is required to predict the resulting surface topographies. In this paper, the use of simulation approaches for different scales for the analysis of different process parameters is discussed on the basis of selected application examples. The analysis of surface structuring in NC form grinding processes, e.g., was conducted by using an explicit geometric modeling of the individual abrasive grains in a geometric-physically based simulation approach to estimate wear-dependent resulting surface topographies. The parameterization of the empirical models used was based on numerical approaches for the detailed analysis of individual grain interventions. Using the complex production process of a turbine blade as an example, the utilization of a macroscopic simulation model for estimating the thermo-mechanical loads and the resulting temperatures in the workpiece during profile grinding processes is discussed.","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116514384","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":"Editorial: Zero defect manufacturing in the era of industry 4.0 for achieving sustainable and resilient manufacturing","authors":"F. Psarommatis, F. Fraile, J. Mendonça, O. Meyer, Óscar Lázaro, D. Kiritsis","doi":"10.3389/fmtec.2023.1124624","DOIUrl":"https://doi.org/10.3389/fmtec.2023.1124624","url":null,"abstract":"Department of Informatics, University of Oslo, Oslo, Norway, Research Centre on Production Management and Engineering, Universitat Politècnica de València, Valencia, Spain, Department of Mechanical Engineering, TecMinho University of Minho, Guimarães, Portugal, Fraunhofer Institute for Production Systems and Design Technology, Berlin, Germany, Innovalia (Spain), Bilbao, Spain, Swiss Federal Institute of Technology Lausanne, Lausanne, Switzerland","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124586884","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":"Tool design for low-frequency vibration cutting on surface property","authors":"Shogo Nakamura, K. Nakanishi, Kenji Ohara, Yoshikatsu Nakamura, Zongwei Ren, Toru Kizaki, N. Sugita","doi":"10.3389/fmtec.2022.1079127","DOIUrl":"https://doi.org/10.3389/fmtec.2022.1079127","url":null,"abstract":"Low-frequency vibration cutting is a machining technology in which chips are broken by applying periodic vibrations along a specific axis. Periodic vibration deteriorates the surface roughness and roundness of the workpiece when compared to without vibration cutting. In this study, the properties of a machined surface under low-frequency vibration were simulated. Based on the simulation results, a tool was designed to reduce the effects of periodic vibration on the surface properties. Actual machining experiments were conducted using the proposed tool to clarify the relationship between tool shape, surface roughness, and roundness under low-frequency vibration. Using the proposed tool on low-frequency vibration cutting, the surface roughness was reduced (from 5.74 µm to .94 µm in Ra and 23.09 µm–6.66 µm in Rz), average roundness improved (from 4.73 µm to 2.95 µm), and maximum roundness decreased (from 15.34 µm to 3.61 µm) compared with those of the conventional tool.","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126669271","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":"Increasing resilience of material supply by decentral urban factories and secondary raw materials","authors":"K. Meyer, S. Görgens, M. Juraschek, C. Herrmann","doi":"10.3389/fmtec.2023.1106965","DOIUrl":"https://doi.org/10.3389/fmtec.2023.1106965","url":null,"abstract":"Current production processes are frequently dependent on global supply chains for raw materials and prefabricated inputs. With rising political and global risks, these supply networks are threatened, which leads to a reduction of supply chain resilience. At the same time, urban areas are currently one of the main consumers of products and waste material generators. The raw material sourcing for this consumption commonly takes place in globally connected supply chains due to economy of scale effects. Therefore, cities are especially vulnerable to supply chain disruptions. A recent development which could reduce this vulnerability is the installation of urban factories among other urban production concepts, which can be symbiotically embedded into the urban metabolism to utilize the locally available (waste) materials. This, however, is hampered by the smaller production scale of decentralized urban production facilities, limited knowledge and challenges about the urban material flows and their characteristics. Against this background, we introduce a new factory type which is placed between the primary and secondary industrial sector: An urban secondary raw material factory which utilizes local waste material and other urban material flows for the extraction and refinement of secondary raw materials to supply production sites in its surrounding environment. To enable this small-to medium-scale factory type, the application of new production technologies plays a crucial role. Therefore, this paper proposes an approach for matching relevant potential waste streams to different technologies for waste-to-resource refinement. The applicability of the method for identification and evaluation of suitable technologies regarding their potential to be located in urban environments is demonstrated for plastic and metallic materials. Subsequently, key challenges and characteristics of the new factory type are summarized. With the introduction of this new factory type, the lack of scale effects in urban symbiotic networks is expected to be reduced. In conclusion, challenges such as the data-based management of symbiotic relationships among manufacturing companies are highlighted as still relevant in decentral value chains.","PeriodicalId":330401,"journal":{"name":"Frontiers in Manufacturing Technology","volume":"283 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133436978","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}