Anna Ghidotti, A. Vitali, D. Regazzoni, Miri Weiss Cohen, C. Rizzi
Segmentation of anatomical components is a major step in creating accurate and realistic 3D models of the human body, which are used in many clinical applications, including orthopedics. Recently, many deep learning approaches have been proposed to solve the problem of manual segmentation, that is time-consuming and operator-dependent. In the present study, SegResNet has been adapted from other domains, such as brain tumor, to segment knee bones from Magnetic Resonance images. This algorithm has been compared to the well-known U-Net in terms of evaluation metrics, such as Dice Similarity Coefficient and Hausdorff Distance. In the training phase, various combinations of hyper-parameters, such as epochs and learning rates, have been tested to determine which combination produced the most accurate results. Based on their comparable results, both U-Net and SegResNet performed well in accurately segmenting the femur. Dice Similarity Coefficients of 0.94 and Hausdorff Distances less than or equal to 1 mm indicate that both models are effective at capturing anatomical boundaries in the femur. According to the results of this study, SegResNet is a viable option for automating the creation of 3D femur models. In the future, the performance and applicability of SegResNet in real-world settings will be further validated and tested using a variety of datasets and clinical scenarios.
{"title":"Comparative Analysis of CNN Architectures for Automated Knee Segmentation in Medical Imaging: a Performance Evaluation","authors":"Anna Ghidotti, A. Vitali, D. Regazzoni, Miri Weiss Cohen, C. Rizzi","doi":"10.1115/1.4064450","DOIUrl":"https://doi.org/10.1115/1.4064450","url":null,"abstract":"\u0000 Segmentation of anatomical components is a major step in creating accurate and realistic 3D models of the human body, which are used in many clinical applications, including orthopedics. Recently, many deep learning approaches have been proposed to solve the problem of manual segmentation, that is time-consuming and operator-dependent. In the present study, SegResNet has been adapted from other domains, such as brain tumor, to segment knee bones from Magnetic Resonance images. This algorithm has been compared to the well-known U-Net in terms of evaluation metrics, such as Dice Similarity Coefficient and Hausdorff Distance. In the training phase, various combinations of hyper-parameters, such as epochs and learning rates, have been tested to determine which combination produced the most accurate results. Based on their comparable results, both U-Net and SegResNet performed well in accurately segmenting the femur. Dice Similarity Coefficients of 0.94 and Hausdorff Distances less than or equal to 1 mm indicate that both models are effective at capturing anatomical boundaries in the femur. According to the results of this study, SegResNet is a viable option for automating the creation of 3D femur models. In the future, the performance and applicability of SegResNet in real-world settings will be further validated and tested using a variety of datasets and clinical scenarios.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"56 46","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139447259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. A. Faroughi, Nikhil M. Pawar, Célio Fernandes, Maziar Raissi, Subasish Das, Nima K. Kalantari, S. K. Mahjour
Advancements in computing power have recently made it possible to utilize machine learning and deep learning to push scientific computing forward in a range of disciplines, such as fluid mechanics, solid mechanics, materials science, etc. The incorporation of neural networks is particularly crucial in this hybridization process. Due to their intrinsic architecture, conventional neural networks cannot be successfully trained and scoped when data is sparse, which is the case in many scientific and engineering domains. Nonetheless, neural networks provide a solid foundation to respect physics-driven or knowledge-based constraints during training. Generally speaking, there are three distinct neural network frameworks to enforce the underlying physics: (i) physics-guided neural networks (PgNNs), (ii) physics-informed neural networks (PiNNs), and (iii) physics-encoded neural networks (PeNNs). These methods provide distinct advantages for accelerating the numerical modeling of complex multiscale multi-physics phenomena. In addition, the recent developments in neural operators (NOs) add another dimension to these new simulation paradigms, especially when the real-time prediction of complex multi-physics systems is required. All these models also come with their own unique drawbacks and limitations that call for further fundamental research. This study aims to present a review of the four neural network frameworks (i.e., PgNNs, PiNNs, PeNNs, and NOs) used in scientific computing research. The state-of-the-art architectures and their applications are reviewed, limitations are discussed, and future research opportunities are presented in terms of improving algorithms, considering causalities, expanding applications, and coupling scientific and deep learning solvers.
{"title":"Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks and Operators in Scientific Computing: Fluid and Solid Mechanics","authors":"S. A. Faroughi, Nikhil M. Pawar, Célio Fernandes, Maziar Raissi, Subasish Das, Nima K. Kalantari, S. K. Mahjour","doi":"10.1115/1.4064449","DOIUrl":"https://doi.org/10.1115/1.4064449","url":null,"abstract":"\u0000 Advancements in computing power have recently made it possible to utilize machine learning and deep learning to push scientific computing forward in a range of disciplines, such as fluid mechanics, solid mechanics, materials science, etc. The incorporation of neural networks is particularly crucial in this hybridization process. Due to their intrinsic architecture, conventional neural networks cannot be successfully trained and scoped when data is sparse, which is the case in many scientific and engineering domains. Nonetheless, neural networks provide a solid foundation to respect physics-driven or knowledge-based constraints during training. Generally speaking, there are three distinct neural network frameworks to enforce the underlying physics: (i) physics-guided neural networks (PgNNs), (ii) physics-informed neural networks (PiNNs), and (iii) physics-encoded neural networks (PeNNs). These methods provide distinct advantages for accelerating the numerical modeling of complex multiscale multi-physics phenomena. In addition, the recent developments in neural operators (NOs) add another dimension to these new simulation paradigms, especially when the real-time prediction of complex multi-physics systems is required. All these models also come with their own unique drawbacks and limitations that call for further fundamental research. This study aims to present a review of the four neural network frameworks (i.e., PgNNs, PiNNs, PeNNs, and NOs) used in scientific computing research. The state-of-the-art architectures and their applications are reviewed, limitations are discussed, and future research opportunities are presented in terms of improving algorithms, considering causalities, expanding applications, and coupling scientific and deep learning solvers.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"28 12","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139445874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Manufacturing industries are increasingly adopting additive manufacturing (AM) technologies to produce functional parts in critical systems. However, the inherent complexity of both AM designs and AM processes render them attractive targets for cyber-attacks. Risk-based Information Technology (IT) and Operational Technology (OT) security guidance standards are useful resources for AM security practitioners, but the guidelines they provide are insufficient without additional AM-specific revisions. Therefore, a structured layering approach is needed to efficiently integrate these revisions with preexisting IT and OT security guidance standards. To implement such an approach, this paper proposes leveraging the National Institute of Standards and Technology's Cybersecurity Framework (CSF) to develop layered, risk-based guidance for fulfilling specific security outcomes. It begins with an in-depth literature review that reveals the importance of AM data and asset management to risk-based security. Next, this paper adopts the CSF asset identification and management security outcomes as an example for providing AM-specific guidance and identifies the AM geometry and process definitions to aid manufacturers in mapping data flows and documenting processes. Finally, this paper uses the Open Security Controls Assessment Language to integrate the AM-specific guidance together with existing IT and OT security guidance in a rigorous and traceable manner. This paper's contribution is to show how a risk-based layered approach enables the authoring, publishing, and management of AM-specific security guidance that is currently lacking. The authors believe implementation of the layered approach would result in value-added, non-redundant security guidance for AM that is consistent with the preexisting guidance.
制造业越来越多地采用增材制造（AM）技术来生产关键系统中的功能部件。然而，AM 设计和 AM 工艺固有的复杂性使其成为网络攻击的目标。基于风险的信息技术 (IT) 和操作技术 (OT) 安全指导标准是 AM 安全从业人员的有用资源，但如果不针对 AM 进行额外的修订，这些标准所提供的指导是不够的。因此，需要一种结构化的分层方法，将这些修订与现有的 IT 和 OT 安全指导标准有效整合。为了实施这种方法，本文建议利用美国国家标准与技术研究院的网络安全框架（CSF）来制定分层的、基于风险的指南，以实现特定的安全成果。本文首先进行了深入的文献综述，揭示了 AM 数据和资产管理对基于风险的安全的重要性。接下来，本文以 CSF 资产识别和管理安全成果为例，提供 AM 专用指南，并确定 AM 几何形状和流程定义，以帮助制造商绘制数据流和记录流程。最后，本文使用开放式安全控制评估语言，以严格和可追溯的方式将 AM 专用指南与现有的 IT 和 OT 安全指南整合在一起。本文的贡献在于展示了基于风险的分层方法如何实现目前缺乏的 AM 专用安全指南的编写、发布和管理。作者认为，分层方法的实施将产生增值的、非冗余的 AM 安全指南，并与现有指南保持一致。
{"title":"Layered Security Guidance for Data Asset Management in Additive Manufacturing.","authors":"Fahad Ali Milaat, Joshua Lubell","doi":"10.1115/1.4064128","DOIUrl":"10.1115/1.4064128","url":null,"abstract":"<p><p>Manufacturing industries are increasingly adopting additive manufacturing (AM) technologies to produce functional parts in critical systems. However, the inherent complexity of both AM designs and AM processes render them attractive targets for cyber-attacks. Risk-based Information Technology (IT) and Operational Technology (OT) security guidance standards are useful resources for AM security practitioners, but the guidelines they provide are insufficient without additional AM-specific revisions. Therefore, a structured layering approach is needed to efficiently integrate these revisions with preexisting IT and OT security guidance standards. To implement such an approach, this paper proposes leveraging the National Institute of Standards and Technology's Cybersecurity Framework (CSF) to develop layered, risk-based guidance for fulfilling specific security outcomes. It begins with an in-depth literature review that reveals the importance of AM data and asset management to risk-based security. Next, this paper adopts the CSF asset identification and management security outcomes as an example for providing AM-specific guidance and identifies the AM geometry and process definitions to aid manufacturers in mapping data flows and documenting processes. Finally, this paper uses the Open Security Controls Assessment Language to integrate the AM-specific guidance together with existing IT and OT security guidance in a rigorous and traceable manner. This paper's contribution is to show how a risk-based layered approach enables the authoring, publishing, and management of AM-specific security guidance that is currently lacking. The authors believe implementation of the layered approach would result in value-added, non-redundant security guidance for AM that is consistent with the preexisting guidance.</p>","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"24 7","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10895930/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139984609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Novel Approach to Line Clipping Against a Rectangular Window","authors":"Hongfeng Yu, Y. He, W. J. Zhang","doi":"10.1115/1.4062634","DOIUrl":"https://doi.org/10.1115/1.4062634","url":null,"abstract":"","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"113 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82313876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Soner Camuz, Anders Liljerehn, Kristina Wärmefjord, R. Söderberg
Maintaining an even pressure distribution in an indexable cutting tool interface is crucial to the life expectancy of a carbide insert. Avoiding uneven pressure distribution is highly relevant for intermittent cutting operations because two load cases arise for full immersion, inside and outside the cutting zone, which can cause alternating contact positioning. Current positioning methodologies, such as 3-2-1 principles, do not consider external mechanical forces, which must be considered for insert-tool body positioning designs. Therefore, this paper proposes an algorithm to calculate a contact index to aid in the design of locating schemes for the early design phases of insert-tool body interface design. The results indicate that it is possible to visualize where a contact condition needs to exist to give support based on the mechanical loads acting on the insert.
{"title":"Algorithm for Detecting Load-Carrying Regions within the Tip Seat of an Indexable Cutting Tool","authors":"Soner Camuz, Anders Liljerehn, Kristina Wärmefjord, R. Söderberg","doi":"10.1115/1.4064255","DOIUrl":"https://doi.org/10.1115/1.4064255","url":null,"abstract":"\u0000 Maintaining an even pressure distribution in an indexable cutting tool interface is crucial to the life expectancy of a carbide insert. Avoiding uneven pressure distribution is highly relevant for intermittent cutting operations because two load cases arise for full immersion, inside and outside the cutting zone, which can cause alternating contact positioning. Current positioning methodologies, such as 3-2-1 principles, do not consider external mechanical forces, which must be considered for insert-tool body positioning designs. Therefore, this paper proposes an algorithm to calculate a contact index to aid in the design of locating schemes for the early design phases of insert-tool body interface design. The results indicate that it is possible to visualize where a contact condition needs to exist to give support based on the mechanical loads acting on the insert.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"13 7","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139007456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Weiwei Liu, Jiahe Qiu, YuJiang Wang, Tao Li, Shujie Liu, Guangda Hu, Lin Xue
The detection of surface damage is an important part of the process before remanufacturing retired steel shaft (RSS). Traditional damage detection is mainly done manually, which is time-consuming and error-prone. In recent years, computer vision methods have been introduced into the community of surface damage detection. However, some advanced typical object detection methods perform poorly in the detection of surface damage on RSS due to the complex surface background and rich diversity of damage patterns and scales. To address these issues, we propose a Faster-RCNN-based surface damage detection method for RSS. To improve the adaptability of the network, we endow it with a feature pyramid network (FPN) as well as adaptable multi-scale information modifications to the region proposal network (RPN). In this paper, a detailed study of an FPN-based feature extraction network and the multi-scale object detection network is conducted. Experimental results show that our method improves the mAP score by 8.9% compared with the original Faster-RCNN for surface damage detection of RSS, and the average detection accuracy for small objects is improved by 18.2%. Compared with the current advanced object detection methods, our method is more advantageous for the detection of multi-scale objects.
{"title":"Multi-scale feature fusion convolutional neural network for surface damage detection in retired steel shafts","authors":"Weiwei Liu, Jiahe Qiu, YuJiang Wang, Tao Li, Shujie Liu, Guangda Hu, Lin Xue","doi":"10.1115/1.4064257","DOIUrl":"https://doi.org/10.1115/1.4064257","url":null,"abstract":"\u0000 The detection of surface damage is an important part of the process before remanufacturing retired steel shaft (RSS). Traditional damage detection is mainly done manually, which is time-consuming and error-prone. In recent years, computer vision methods have been introduced into the community of surface damage detection. However, some advanced typical object detection methods perform poorly in the detection of surface damage on RSS due to the complex surface background and rich diversity of damage patterns and scales. To address these issues, we propose a Faster-RCNN-based surface damage detection method for RSS. To improve the adaptability of the network, we endow it with a feature pyramid network (FPN) as well as adaptable multi-scale information modifications to the region proposal network (RPN). In this paper, a detailed study of an FPN-based feature extraction network and the multi-scale object detection network is conducted. Experimental results show that our method improves the mAP score by 8.9% compared with the original Faster-RCNN for surface damage detection of RSS, and the average detection accuracy for small objects is improved by 18.2%. Compared with the current advanced object detection methods, our method is more advantageous for the detection of multi-scale objects.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"24 13","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139010009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Singh, Rahul Rai, Raj Pradip Khawale, Darshil Patel, Dustin Bielecki, Ryan Nguyen, Jun Wang, Zhibo Zhang
A paradigm shift in the computational design synthesis domain is being witnessed by the onset of the innovative usage of machine learning techniques. The rapidly evolving paradigmatic shift calls for systematic and comprehensive assimilation of extant knowledge at the intersection of machine learning and computational design synthesis. Understanding nuances, identifying research gaps, and outlining the future direction for cutting-edge research is imperative. This paper outlines a hybrid literature review consisting of a thematic and framework synthesis survey to enable conceptual synthesis of information at the convergence of computational design, machine learning, and big-data models. The thematic literature survey aims at conducting an in-depth descriptive survey along the lines of a broader theme of machine learning in computational design. The framework synthesis-based survey tries to encapsulate the research findings in a conceptual framework to understand the domain better. The framework is based on the computational design synthesis (CDS) process, which consists of four sub-modules: representation, generation, evaluation, and guidance. Each sub-module has undergone an analysis to identify potential research gaps and formulate research questions. Additionally, we consider the limitations of our study and pinpoint the realms where the research can be extended in the future.
{"title":"Deep Learning in Computational Design Synthesis: A Comprehensive Review","authors":"S. Singh, Rahul Rai, Raj Pradip Khawale, Darshil Patel, Dustin Bielecki, Ryan Nguyen, Jun Wang, Zhibo Zhang","doi":"10.1115/1.4064215","DOIUrl":"https://doi.org/10.1115/1.4064215","url":null,"abstract":"\u0000 A paradigm shift in the computational design synthesis domain is being witnessed by the onset of the innovative usage of machine learning techniques. The rapidly evolving paradigmatic shift calls for systematic and comprehensive assimilation of extant knowledge at the intersection of machine learning and computational design synthesis. Understanding nuances, identifying research gaps, and outlining the future direction for cutting-edge research is imperative. This paper outlines a hybrid literature review consisting of a thematic and framework synthesis survey to enable conceptual synthesis of information at the convergence of computational design, machine learning, and big-data models. The thematic literature survey aims at conducting an in-depth descriptive survey along the lines of a broader theme of machine learning in computational design. The framework synthesis-based survey tries to encapsulate the research findings in a conceptual framework to understand the domain better. The framework is based on the computational design synthesis (CDS) process, which consists of four sub-modules: representation, generation, evaluation, and guidance. Each sub-module has undergone an analysis to identify potential research gaps and formulate research questions. Additionally, we consider the limitations of our study and pinpoint the realms where the research can be extended in the future.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"31 7","pages":""},"PeriodicalIF":3.1,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138590218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract The Journal of Computing and Information Science in Engineering (JCISE) publishes articles related to scientific computing methods (e.g., modeling, simulation, representation, algorithm) and computational tools (e.g., high-performance computing, virtual and augmented reality) that aim to improve engineering products and systems for their complete lifecycle (e.g., design, manufacturing, operation, maintenance, disposal, and recycling). The interest areas include computational geometry, computer-aided design and manufacturing, cyber-physical systems, human-machine interface, machine intelligence, machine learning, modeling and simulation, precision engineering, product lifecycle management, reverse engineering, and systems engineering.
{"title":"JCISE Editorial Board - Year 2023","authors":"Yan Wang","doi":"10.1115/1.4064046","DOIUrl":"https://doi.org/10.1115/1.4064046","url":null,"abstract":"Abstract The Journal of Computing and Information Science in Engineering (JCISE) publishes articles related to scientific computing methods (e.g., modeling, simulation, representation, algorithm) and computational tools (e.g., high-performance computing, virtual and augmented reality) that aim to improve engineering products and systems for their complete lifecycle (e.g., design, manufacturing, operation, maintenance, disposal, and recycling). The interest areas include computational geometry, computer-aided design and manufacturing, cyber-physical systems, human-machine interface, machine intelligence, machine learning, modeling and simulation, precision engineering, product lifecycle management, reverse engineering, and systems engineering.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"20 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135092539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Laetitia Monnier, William Bernstein, Vincenzo Ferrero, Sebti Foufou
Abstract Developing a more automated industrial digital thread is vital to realize the smart manufacturing and Industry 4.0 vision. The digital thread allows for efficient sharing across product lifecycle stages. Current techniques are not robust in relating downstream data, such as manufac- turing and inspection information, back to design for bet- ter decision making. In response, we previously presented a methodology that aligns numerical control (NC) code, a standard for representing machine tool instructions, to controller data represented in MTConnect, a standard that provides a vocabulary for generalizing execution logs from different machine tools and devices. This paper ex- tends our previous work by automating the tool identifi- cation using a k-means clustering algorithm to refine the alignment of the data. In doing so, we compare differ- ent distance techniques to analyze the spatial-temporal registration of the two datasets, i.e., the NC code and MTConnect data. Then, we assess the efficiency of our method through an error measurement technique that ex- presses the quality of the alignment. Finally, we apply our methodology to a case study that includes verified process plans and real execution data, derived from the Smart Manufacturing Systems Test Bed hosted at the National Institute of Standards and Technology. Our anal- ysis illustrates that dynamic time warping achieves the best point registration with the least errors compared with other alignment techniques.
{"title":"An automated approach for segmenting numerical control data with controller data for machine tools","authors":"Laetitia Monnier, William Bernstein, Vincenzo Ferrero, Sebti Foufou","doi":"10.1115/1.4064036","DOIUrl":"https://doi.org/10.1115/1.4064036","url":null,"abstract":"Abstract Developing a more automated industrial digital thread is vital to realize the smart manufacturing and Industry 4.0 vision. The digital thread allows for efficient sharing across product lifecycle stages. Current techniques are not robust in relating downstream data, such as manufac- turing and inspection information, back to design for bet- ter decision making. In response, we previously presented a methodology that aligns numerical control (NC) code, a standard for representing machine tool instructions, to controller data represented in MTConnect, a standard that provides a vocabulary for generalizing execution logs from different machine tools and devices. This paper ex- tends our previous work by automating the tool identifi- cation using a k-means clustering algorithm to refine the alignment of the data. In doing so, we compare differ- ent distance techniques to analyze the spatial-temporal registration of the two datasets, i.e., the NC code and MTConnect data. Then, we assess the efficiency of our method through an error measurement technique that ex- presses the quality of the alignment. Finally, we apply our methodology to a case study that includes verified process plans and real execution data, derived from the Smart Manufacturing Systems Test Bed hosted at the National Institute of Standards and Technology. Our anal- ysis illustrates that dynamic time warping achieves the best point registration with the least errors compared with other alignment techniques.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"98 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135391013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This paper presents an approach based on deep neural networks for interactive digital transformation and simulation of n-bar planar linkages composed of revolute and prismatic joints from hand-drawn sketches. Rather than relying solely on computer vision, our approach leverages the topological knowledge of linkage mechanisms in combination with the output of a convolutional deep neural network. This creates a framework for recognition of hand-drawn sketches. Our methodology involves first generating a dataset of synthetic images of linkage mechanism sketches that resemble hand-drawn sketches. We then fine-tune a state-of-the-art deep neural network capable of detecting discrete objects using a set of building blocks of linkage mechanisms, specifically joints and links in various positions, scales, and orientations. We perform a topological analysis on the set of detected objects to create a kinematic model of the sketched mechanisms. Results indicate that our algorithm performs well on hand-drawn sketches, and it can aid in the conversion of such sketches into their digital representations. This has implications for effective communication, analysis, cataloging, and classification of planar mechanisms. Furthermore, our approach could lay the groundwork for image-based synthesis of planar mechanisms, which would be insensitive to their complexity or properties, such as the algebraic degree of the coupler curves.
{"title":"Transforming Hand-drawn Sketches of Linkage Mechanisms into their Digital Representation","authors":"Anar Nurizada, Anurag Purwar","doi":"10.1115/1.4064037","DOIUrl":"https://doi.org/10.1115/1.4064037","url":null,"abstract":"Abstract This paper presents an approach based on deep neural networks for interactive digital transformation and simulation of n-bar planar linkages composed of revolute and prismatic joints from hand-drawn sketches. Rather than relying solely on computer vision, our approach leverages the topological knowledge of linkage mechanisms in combination with the output of a convolutional deep neural network. This creates a framework for recognition of hand-drawn sketches. Our methodology involves first generating a dataset of synthetic images of linkage mechanism sketches that resemble hand-drawn sketches. We then fine-tune a state-of-the-art deep neural network capable of detecting discrete objects using a set of building blocks of linkage mechanisms, specifically joints and links in various positions, scales, and orientations. We perform a topological analysis on the set of detected objects to create a kinematic model of the sketched mechanisms. Results indicate that our algorithm performs well on hand-drawn sketches, and it can aid in the conversion of such sketches into their digital representations. This has implications for effective communication, analysis, cataloging, and classification of planar mechanisms. Furthermore, our approach could lay the groundwork for image-based synthesis of planar mechanisms, which would be insensitive to their complexity or properties, such as the algebraic degree of the coupler curves.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"98 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135391009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：