A 3D model is a storage method that can accurately describe the objective world. However, the establishment of a 3D model requires a lot of acquisition resources in details, and a precise 3D model often consumes abundant storage space. To eliminate these drawback, we propose a 3D data super-resolution model named three dimension slice reconstruction model(3DSR) that use low resolution 3D data as input to acquire a high resolution result instantaneously and accurately, shortening time and storage when building a precise 3D model. To boost the efficiency and accuracy of deep learning model, the 3D data is split as multiple slices. The 3DSR processes the slice to high resolution 2D image, and reconstruct the image as high resolution 3D data. 3D data slice-up method and slice-reconstruction method are designed to maintain the main features of 3D data. Meanwhile, a pre-trained deep 2D convolution neural network is utilized to expand the resolution of 2D image, which achieve superior performance. Our method saving the time to train deep learning model and computation time when improve the resolution. Furthermore, our model can achieve better performance even less data is utilized to train the model.
{"title":"3D-Slice-Super-Resolution-Net: A Fast Few Shooting Learning Model for 3D Super-resolution Using Slice-up and Slice-reconstruction","authors":"Hongbin Lin, Qingfeng Xu, Handing Xu, Yanjie Xu, Yiming Zheng, Yubin Zhong, Zhenguo Nie","doi":"10.1115/1.4063275","DOIUrl":"https://doi.org/10.1115/1.4063275","url":null,"abstract":"\u0000 A 3D model is a storage method that can accurately describe the objective world. However, the establishment of a 3D model requires a lot of acquisition resources in details, and a precise 3D model often consumes abundant storage space. To eliminate these drawback, we propose a 3D data super-resolution model named three dimension slice reconstruction model(3DSR) that use low resolution 3D data as input to acquire a high resolution result instantaneously and accurately, shortening time and storage when building a precise 3D model. To boost the efficiency and accuracy of deep learning model, the 3D data is split as multiple slices. The 3DSR processes the slice to high resolution 2D image, and reconstruct the image as high resolution 3D data. 3D data slice-up method and slice-reconstruction method are designed to maintain the main features of 3D data. Meanwhile, a pre-trained deep 2D convolution neural network is utilized to expand the resolution of 2D image, which achieve superior performance. Our method saving the time to train deep learning model and computation time when improve the resolution. Furthermore, our model can achieve better performance even less data is utilized to train the model.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49111918","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}
This paper presents a self-supervised learning approach for a robot to learn spatially varying process parameter models for contact-based finishing tasks. In many finishing tasks, a part has spatially varying stiffness. Some regions of the part enable the robot to efficiently execute the task. On the other hand, some other regions on the part may require the robot to move cautiously in order to prevent damage and ensure safety. Compared to the constant process parameter models, spatially varying process parameter models are more complex and challenging to learn. Our self-supervised learning approach consists of utilizing an initial parameter space exploration method, surrogate modeling, selection of region sequencing policy, and development of process parameter selection policy. We showed that by carefully selecting and optimizing learning components, this approach enables a robot to efficiently learn spatially varying process parameter models for a given contact-based finishing task. We demonstrated the effectiveness of our approach through computational simulations and physical experiments with a robotic sanding case study. Our work shows that the learning approach that has been optimized based on task characteristics significantly outperforms an unoptimized learning approach based on the overall task completion time.
{"title":"Self-Supervised Learning of Spatially Varying Process Parameter Models for Robotic Finishing Tasks","authors":"Yeo Jung Yoon, Santosh V. Narayan, S. Gupta","doi":"10.1115/1.4063276","DOIUrl":"https://doi.org/10.1115/1.4063276","url":null,"abstract":"\u0000 This paper presents a self-supervised learning approach for a robot to learn spatially varying process parameter models for contact-based finishing tasks. In many finishing tasks, a part has spatially varying stiffness. Some regions of the part enable the robot to efficiently execute the task. On the other hand, some other regions on the part may require the robot to move cautiously in order to prevent damage and ensure safety. Compared to the constant process parameter models, spatially varying process parameter models are more complex and challenging to learn. Our self-supervised learning approach consists of utilizing an initial parameter space exploration method, surrogate modeling, selection of region sequencing policy, and development of process parameter selection policy. We showed that by carefully selecting and optimizing learning components, this approach enables a robot to efficiently learn spatially varying process parameter models for a given contact-based finishing task. We demonstrated the effectiveness of our approach through computational simulations and physical experiments with a robotic sanding case study. Our work shows that the learning approach that has been optimized based on task characteristics significantly outperforms an unoptimized learning approach based on the overall task completion time.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42064611","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}
In recent years, advances in additive manufacturing (AM) techniques have called for a scalable fabrication framework for high-resolution designs. Despite several process-specific handful design approaches, there is a gap to fill between computer-aided design (CAD) and the manufacturing of highly detailed multi-scale materials, especially for delicate cellular materials design. This gap ought to be filled with an avenue capable of efficiently slicing multi-scale intricate designs. Most existing methods depend on the mesh representation, which is time-consuming and memory-hogging to generate. This paper proposes an adaptive direct slicing (mesh-free) pipeline that exploits the function representation (FRep) for hierarchical architected cellular materials design. To explore the capabilities of the presented approach, several sample structures with delicate architectures are fabricated using a stereolithography (SLA) printer. The computational efficiency of the proposed slicing algorithm is studied. Furthermore, the geometry frustration problem brought by the connection of distinct structures between functionally graded unit cells at the micro-scale level is also investigated.
{"title":"STL-Free Adaptive Slicing Scheme for Additive Manufacturing of Cellular Materials","authors":"Sina Rastegarzadeh, Jida Huang","doi":"10.1115/1.4063227","DOIUrl":"https://doi.org/10.1115/1.4063227","url":null,"abstract":"\u0000 In recent years, advances in additive manufacturing (AM) techniques have called for a scalable fabrication framework for high-resolution designs. Despite several process-specific handful design approaches, there is a gap to fill between computer-aided design (CAD) and the manufacturing of highly detailed multi-scale materials, especially for delicate cellular materials design. This gap ought to be filled with an avenue capable of efficiently slicing multi-scale intricate designs. Most existing methods depend on the mesh representation, which is time-consuming and memory-hogging to generate. This paper proposes an adaptive direct slicing (mesh-free) pipeline that exploits the function representation (FRep) for hierarchical architected cellular materials design. To explore the capabilities of the presented approach, several sample structures with delicate architectures are fabricated using a stereolithography (SLA) printer. The computational efficiency of the proposed slicing algorithm is studied. Furthermore, the geometry frustration problem brought by the connection of distinct structures between functionally graded unit cells at the micro-scale level is also investigated.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42085100","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}
Shijie Bian, Daniele Grandi, Tianyang Liu, P. Jayaraman, Karl Willis, Elliot T. Salder, Bodia Borijin, Thomas Lu, Richard Otis, Nhut Ho, Bingbing Li
To enable intelligent CAD design tools, we introduce a machine learning architecture, namely HG-CAD, that supports the automated material prediction and recommendation of assembly bodies through joint learning of body and assembly-level features using a hierarchical graph representation. Specifically, we formulate the material prediction and recommendation process as a node-level classification task over a novel hierarchical graph representation of CAD models, with a low-level graph capturing the body geometry, a high-level graph representing the assembly topology, and a batch-level mask randomization enabling contextual awareness. This enables our network to aggregate geometric and topological features from both the body and assembly levels, leading to superior performance. Qualitative and quantitative evaluation of the proposed architecture on the Fusion 360 Gallery Assembly Dataset demonstrates the feasibility of our approach, outperforming both computer vision and human baselines, while showing promise in application scenarios. The proposed HG-CAD architecture that unifies the processing, encoding, and joint learning of multi-modal CAD features can scale to large repositories, incorporating designers' knowledge into the learning process. These capabilities allow the architecture to serve as a recommendation system for design automation and a baseline for future work.
{"title":"HG-CAD: Hierarchical Graph Learning for Material Prediction and Recommendation in CAD","authors":"Shijie Bian, Daniele Grandi, Tianyang Liu, P. Jayaraman, Karl Willis, Elliot T. Salder, Bodia Borijin, Thomas Lu, Richard Otis, Nhut Ho, Bingbing Li","doi":"10.1115/1.4063226","DOIUrl":"https://doi.org/10.1115/1.4063226","url":null,"abstract":"\u0000 To enable intelligent CAD design tools, we introduce a machine learning architecture, namely HG-CAD, that supports the automated material prediction and recommendation of assembly bodies through joint learning of body and assembly-level features using a hierarchical graph representation. Specifically, we formulate the material prediction and recommendation process as a node-level classification task over a novel hierarchical graph representation of CAD models, with a low-level graph capturing the body geometry, a high-level graph representing the assembly topology, and a batch-level mask randomization enabling contextual awareness. This enables our network to aggregate geometric and topological features from both the body and assembly levels, leading to superior performance. Qualitative and quantitative evaluation of the proposed architecture on the Fusion 360 Gallery Assembly Dataset demonstrates the feasibility of our approach, outperforming both computer vision and human baselines, while showing promise in application scenarios. The proposed HG-CAD architecture that unifies the processing, encoding, and joint learning of multi-modal CAD features can scale to large repositories, incorporating designers' knowledge into the learning process. These capabilities allow the architecture to serve as a recommendation system for design automation and a baseline for future work.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49586545","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}
Nathaniel DeVol, Christopher Saldaña, Katherine Fu
Machine condition monitoring has been proven to reduce machine down time and increase productivity. State of the art research uses vibration monitoring for tasks such as maintenance and tool wear prediction. A less explored aspect is how vibration monitoring might be used to monitor equipment sensitive to vibration. In a manufacturing environment, one example of where this might be needed is in monitoring the vibration of optical linear encoders used in high precision machine tools and coordinate measuring machines. Monitoring the vibration of sensitive equipment presents a unique case for vibration monitoring because an accurate calculation of the maximum sustained vibration is needed, as opposed to extracting trends from the data. To do this, techniques for determining sustained peaks in vibration signals are needed. This work fills this gap by formalizing and testing methods for determining sustained vibration amplitudes. The methods are tested on simulated signals based on experimental data. Results show that processing the signal directly with the novel Expire Timer method produces the smallest amounts of error on average under various test conditions. Additionally, this method can operate in real-time on streaming vibration data.
{"title":"Methods for the Automated Determination of Sustained Maximum Amplitudes in Oscillating Signals","authors":"Nathaniel DeVol, Christopher Saldaña, Katherine Fu","doi":"10.1115/1.4063130","DOIUrl":"https://doi.org/10.1115/1.4063130","url":null,"abstract":"\u0000 Machine condition monitoring has been proven to reduce machine down time and increase productivity. State of the art research uses vibration monitoring for tasks such as maintenance and tool wear prediction. A less explored aspect is how vibration monitoring might be used to monitor equipment sensitive to vibration. In a manufacturing environment, one example of where this might be needed is in monitoring the vibration of optical linear encoders used in high precision machine tools and coordinate measuring machines. Monitoring the vibration of sensitive equipment presents a unique case for vibration monitoring because an accurate calculation of the maximum sustained vibration is needed, as opposed to extracting trends from the data. To do this, techniques for determining sustained peaks in vibration signals are needed. This work fills this gap by formalizing and testing methods for determining sustained vibration amplitudes. The methods are tested on simulated signals based on experimental data. Results show that processing the signal directly with the novel Expire Timer method produces the smallest amounts of error on average under various test conditions. Additionally, this method can operate in real-time on streaming vibration data.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43002284","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}
In the past decade, human digital twins (HDTs) attracted much attention in and beyond digital twin (DT) applications. In this paper, we discuss the concept and the development of HDTs with a focus on their architecture, ethical concerns, key enabling technologies, and the opportunities of using HDTs in design. Based on the literature, we identified that data, model, and interface are three key modules in the proposed HDT architecture. Ethics is an important concern in the development and the use of the HDT from the humanities perspective. For key enabling technologies that support the functions of the HDT, we argue that the IoT infrastructure, data security, wearables, human modeling, explainable artificial intelligence, minimum viable sensing, and data visualization are strongly associated with the development of HDTs. Based on current applications, we highlight the design opportunities of using HDTs in designing products, services, and systems, as well as a design tool to facilitate the design process.
{"title":"Human digital twin, the development and impact on design","authors":"Yun-Hwa Song","doi":"10.1115/1.4063132","DOIUrl":"https://doi.org/10.1115/1.4063132","url":null,"abstract":"\u0000 In the past decade, human digital twins (HDTs) attracted much attention in and beyond digital twin (DT) applications. In this paper, we discuss the concept and the development of HDTs with a focus on their architecture, ethical concerns, key enabling technologies, and the opportunities of using HDTs in design. Based on the literature, we identified that data, model, and interface are three key modules in the proposed HDT architecture. Ethics is an important concern in the development and the use of the HDT from the humanities perspective. For key enabling technologies that support the functions of the HDT, we argue that the IoT infrastructure, data security, wearables, human modeling, explainable artificial intelligence, minimum viable sensing, and data visualization are strongly associated with the development of HDTs. Based on current applications, we highlight the design opportunities of using HDTs in designing products, services, and systems, as well as a design tool to facilitate the design process.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43914245","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}
Accurate registration of Cartesian coordinate systems is necessary to facilitate metrology-based solutions for industrial robots in production environments. Conducting coordinate registration between industrial robots and their metrological systems requires measuring multiple points in the robot's and sensor system's coordinate frames. However, operators lack intuitive tools to interface, visualize, and characterize the quality of the selected points in the robot workspace for robot-sensor coordinate registration. This paper proposes an augmented reality system for human-in-the-loop, robot-sensor coordinate registration to efficiently record and visualize the pose-dependent quality of computing the robot-sensor transformation. Furthermore, this work establishes metrics to define the relative quality of measurement points used in robot-sensor coordinate registration, which are shown by the augmented reality application. Experiments were conducted demonstrating the augmented reality environment in addition to investigating the pose-dependency of the measurement point quality. The results indicate that the proposed metrics highlight the dependency of the poses on both robot and sensor placement and that the augmented reality system can provide a human-in-the-loop interface for robot-sensor coordinate registration.
{"title":"Augmented Reality Interface for Robot-Sensor Coordinate Registration","authors":"Vinh Nguyen, Xiaofeng Liu, J. Marvel","doi":"10.1115/1.4063131","DOIUrl":"https://doi.org/10.1115/1.4063131","url":null,"abstract":"\u0000 Accurate registration of Cartesian coordinate systems is necessary to facilitate metrology-based solutions for industrial robots in production environments. Conducting coordinate registration between industrial robots and their metrological systems requires measuring multiple points in the robot's and sensor system's coordinate frames. However, operators lack intuitive tools to interface, visualize, and characterize the quality of the selected points in the robot workspace for robot-sensor coordinate registration. This paper proposes an augmented reality system for human-in-the-loop, robot-sensor coordinate registration to efficiently record and visualize the pose-dependent quality of computing the robot-sensor transformation. Furthermore, this work establishes metrics to define the relative quality of measurement points used in robot-sensor coordinate registration, which are shown by the augmented reality application. Experiments were conducted demonstrating the augmented reality environment in addition to investigating the pose-dependency of the measurement point quality. The results indicate that the proposed metrics highlight the dependency of the poses on both robot and sensor placement and that the augmented reality system can provide a human-in-the-loop interface for robot-sensor coordinate registration.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49330088","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}
J. Michopoulos, A. Iliopoulos, J. Steuben, N. Apetre
The ever-improving advances of computational technologies have forced the user to manage higher resource complexity and motivates the modeling of more complex multiphysics systems than before. Consequently, the time for the user's iterations within the context space characterizing all choices required for a successful computation far exceeds the time required for the runtime software execution to produce acceptable results. This paper presents metacomputing as an approach to address this issue, starting with describing this high-dimensional context space. Then it highlights the abstract process of multiphysics model generation/solution and proposes performing top-down and bottom-up metacomputing. In the top-down approach, metacomputing is used for: Automating the process of generating theories; Raising the semantic dimensionality of these theories in higher dimensional algebraic systems that enable simplification of the equational representation and raising the syntactic dimensionality of equational representation from 1-D equational forms to 2-D and 3-D algebraic solution graphs that reduce solving to path-following. In the bottom-up approach, already existing legacy codes evolving over multiple decades are encapsulated at the bottom layer of a multilayer semantic framework that utilizes Category Theory based operations on specifications to enable the user to spend time only for defining the physics of the relevant problem and not have to deal with the rest of the details involved in deploying and executing the solution of the problem at hand. Consequently, these two metacomputing approaches enable the generation, composition, deployment, and execution of directly computable multiphysics models.
{"title":"Metacomputing for Directly Computable Multiphysics Models","authors":"J. Michopoulos, A. Iliopoulos, J. Steuben, N. Apetre","doi":"10.1115/1.4063103","DOIUrl":"https://doi.org/10.1115/1.4063103","url":null,"abstract":"\u0000 The ever-improving advances of computational technologies have forced the user to manage higher resource complexity and motivates the modeling of more complex multiphysics systems than before. Consequently, the time for the user's iterations within the context space characterizing all choices required for a successful computation far exceeds the time required for the runtime software execution to produce acceptable results. This paper presents metacomputing as an approach to address this issue, starting with describing this high-dimensional context space. Then it highlights the abstract process of multiphysics model generation/solution and proposes performing top-down and bottom-up metacomputing. In the top-down approach, metacomputing is used for: Automating the process of generating theories; Raising the semantic dimensionality of these theories in higher dimensional algebraic systems that enable simplification of the equational representation and raising the syntactic dimensionality of equational representation from 1-D equational forms to 2-D and 3-D algebraic solution graphs that reduce solving to path-following. In the bottom-up approach, already existing legacy codes evolving over multiple decades are encapsulated at the bottom layer of a multilayer semantic framework that utilizes Category Theory based operations on specifications to enable the user to spend time only for defining the physics of the relevant problem and not have to deal with the rest of the details involved in deploying and executing the solution of the problem at hand. Consequently, these two metacomputing approaches enable the generation, composition, deployment, and execution of directly computable multiphysics models.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45475226","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}
Hao Chen, Hongbin Lin, Qingfeng Xu, Yaguan Li, Yiming Zheng, Jianghua Fei, Kang Yang, Wenhui Fan, Zhenguo Nie
Defect detection is a crucial direction of deep learning, which is suitable for industrial inspection of product quality in strip steel. As the strip steel production line continuously outputs products, it is necessary to take corresponding measures for the type of defect, once a subtle quality problem is found on steel strips. We propose a new defect area detection and classification method for automation strip steel defect detection. In order to eliminate the way of insufficient data in industrial production line scenarios, we design a transfer learning scheme to support the training of defect region detection. Subsequently, in order to achieve a more accurate classification of defect categories, we designed a deep learning model that integrated the detection results of defect regions and defects feature extraction. After applying our method to the test set and production line, we can achieve extremely high accuracy, reaching 87.11%, while meeting the production speed of the production line compared with other methods. The accuracy and speed of the model realize automatic quality monitoring in the manufacturing process of strip steel.
{"title":"Cross-domain Transfer Learning for Galvanized Steel Strips Defect Detection and Recognition","authors":"Hao Chen, Hongbin Lin, Qingfeng Xu, Yaguan Li, Yiming Zheng, Jianghua Fei, Kang Yang, Wenhui Fan, Zhenguo Nie","doi":"10.1115/1.4063102","DOIUrl":"https://doi.org/10.1115/1.4063102","url":null,"abstract":"\u0000 Defect detection is a crucial direction of deep learning, which is suitable for industrial inspection of product quality in strip steel. As the strip steel production line continuously outputs products, it is necessary to take corresponding measures for the type of defect, once a subtle quality problem is found on steel strips. We propose a new defect area detection and classification method for automation strip steel defect detection. In order to eliminate the way of insufficient data in industrial production line scenarios, we design a transfer learning scheme to support the training of defect region detection. Subsequently, in order to achieve a more accurate classification of defect categories, we designed a deep learning model that integrated the detection results of defect regions and defects feature extraction. After applying our method to the test set and production line, we can achieve extremely high accuracy, reaching 87.11%, while meeting the production speed of the production line compared with other methods. The accuracy and speed of the model realize automatic quality monitoring in the manufacturing process of strip steel.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45020229","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}
The automotive industry is undergoing a massive transformation, driven by the mega-trends of “CASE”: connected, automated, shared, and electric. These trends are affecting the nature of automobiles, both internally and externally. Internally, the transition from internal combustion engines (ICE) to electric drive-trains has resulted in a shift from hardware-defined vehicles to software-defined vehicles (SDVs), where software is increasingly becoming the dominant asset in the automotive value chain. These trends are leading to new design challenges such as how to manage different configurations of design, how to decouple the design of software and services from hardware, and how to design hardware to allow for upgrades. Externally, automobiles are no longer isolated products. Instead, they are part of the larger digital ecosystem with cloud connectivity. Vehicle usage data are increasingly connected with smart factories, which creates new opportunities for agile product development and mass customization of features. The role of the human driver is also changing with increasing levels of autonomy features. In this paper, the authors discuss the ongoing transformation in the automotive industry and its implications for engineering design. The paper presents a road map for engineering design research for next-generation automotive applications.
{"title":"Design of Next Generation Automotive Systems: Challenges and Research Opportunities","authors":"Jitesh H. Panchal, Ziran Wang","doi":"10.1115/1.4063067","DOIUrl":"https://doi.org/10.1115/1.4063067","url":null,"abstract":"\u0000 The automotive industry is undergoing a massive transformation, driven by the mega-trends of “CASE”: connected, automated, shared, and electric. These trends are affecting the nature of automobiles, both internally and externally. Internally, the transition from internal combustion engines (ICE) to electric drive-trains has resulted in a shift from hardware-defined vehicles to software-defined vehicles (SDVs), where software is increasingly becoming the dominant asset in the automotive value chain. These trends are leading to new design challenges such as how to manage different configurations of design, how to decouple the design of software and services from hardware, and how to design hardware to allow for upgrades. Externally, automobiles are no longer isolated products. Instead, they are part of the larger digital ecosystem with cloud connectivity. Vehicle usage data are increasingly connected with smart factories, which creates new opportunities for agile product development and mass customization of features. The role of the human driver is also changing with increasing levels of autonomy features. In this paper, the authors discuss the ongoing transformation in the automotive industry and its implications for engineering design. The paper presents a road map for engineering design research for next-generation automotive applications.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47105333","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：