Self-organizing systems can perform complex tasks in unpredictable situations with adaptability. Previous work has introduced a multiagent reinforcement learning based model as a design approach to solving the rule generation problem with complex tasks. A deep multiagent reinforcement learning algorithm was devised to train self-organizing agents for knowledge acquisition of the task field and social rules. The results showed that there is an optimal number of agents that achieve good learning stability and system performance. However, finding such a number is nontrivial due to the dynamic task constraints and unavailability of agent knowledge before training. Although extensive training can eventually reveal the optimal number, it requires training simulations of all agent numbers under consideration, which can be computationally expensive and time-consuming. Thus, there remains the issue of how to predict such an optimal team size for self-organizing systems with minimal training experiments. In this paper, we proposed a measurement of the complexity of the self-organizing system called effective entropy, which considers the task constraints. A systematic approach, including several key concepts and steps, is proposed to calculate the effective entropy for given task environments, which is then illustrated and tested in a box-pushing case study. The results show that our proposed method and complexity measurement can accurately predict the optimal number of agents in self-organizing systems, and training simulations can be reduced by a factor of 10.
{"title":"Impact of Task Constraint on Agent Team Size of Self-Organizing Systems Measured by Effective Entropy","authors":"Hao Ji, Yan Jin","doi":"10.1115/1.4065343","DOIUrl":"https://doi.org/10.1115/1.4065343","url":null,"abstract":"\u0000 Self-organizing systems can perform complex tasks in unpredictable situations with adaptability. Previous work has introduced a multiagent reinforcement learning based model as a design approach to solving the rule generation problem with complex tasks. A deep multiagent reinforcement learning algorithm was devised to train self-organizing agents for knowledge acquisition of the task field and social rules. The results showed that there is an optimal number of agents that achieve good learning stability and system performance. However, finding such a number is nontrivial due to the dynamic task constraints and unavailability of agent knowledge before training. Although extensive training can eventually reveal the optimal number, it requires training simulations of all agent numbers under consideration, which can be computationally expensive and time-consuming. Thus, there remains the issue of how to predict such an optimal team size for self-organizing systems with minimal training experiments. In this paper, we proposed a measurement of the complexity of the self-organizing system called effective entropy, which considers the task constraints. A systematic approach, including several key concepts and steps, is proposed to calculate the effective entropy for given task environments, which is then illustrated and tested in a box-pushing case study. The results show that our proposed method and complexity measurement can accurately predict the optimal number of agents in self-organizing systems, and training simulations can be reduced by a factor of 10.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140691643","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 study aims to use an improved rotational region convolutional neural network (R2CNN) algorithm to detect the grasping bounding box for the robotic arm that reaches supermarket goods. This algorithm can calculate the final predicted grasping bounding box without any additional architecture, which greatly improves the speed of grasp inferences. In this study, we added the force-closure condition, so that the final grasping bounding box could achieve grasping stability in a physical sense. We experimentally demonstrated that the deep model treated object detection and grasping detection are the same tasks. We used transfer learning to improve the prediction accuracy of the grasping bounding box. In particular, the ResNet-101 network weights, which were originally used in object detection, were used to continue training with the Cornell dataset. In terms of grasping detection, we used the trained model weights that were originally used in object detection as the features of the to-be-grasped objects and fed them to the network for continuous training. For 2,828 test images, this method achieved nearly 98% accuracy and a speed of 14–17 frames per second.
{"title":"Enhancing robotic grasping detection accuracy with the R2CNN algorithm and force-closure","authors":"Hsien-I Lin, M. Shodiq, Hong-Qi Chu","doi":"10.1115/1.4065311","DOIUrl":"https://doi.org/10.1115/1.4065311","url":null,"abstract":"\u0000 This study aims to use an improved rotational region convolutional neural network (R2CNN) algorithm to detect the grasping bounding box for the robotic arm that reaches supermarket goods. This algorithm can calculate the final predicted grasping bounding box without any additional architecture, which greatly improves the speed of grasp inferences. In this study, we added the force-closure condition, so that the final grasping bounding box could achieve grasping stability in a physical sense. We experimentally demonstrated that the deep model treated object detection and grasping detection are the same tasks. We used transfer learning to improve the prediction accuracy of the grasping bounding box. In particular, the ResNet-101 network weights, which were originally used in object detection, were used to continue training with the Cornell dataset. In terms of grasping detection, we used the trained model weights that were originally used in object detection as the features of the to-be-grasped objects and fed them to the network for continuous training. For 2,828 test images, this method achieved nearly 98% accuracy and a speed of 14–17 frames per second.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140699369","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 introduces a methodology for updating the nonlinear stochastic dynamics of a nozzle with uncertain computational model. The approach focuses on a high-dimensional nonlinear computational model constrained by a small target dataset. Challenges include the large number of degrees-of-freedom, geometric nonlinearities, material uncertainties, stochastic external loads, under-observability, and high computational costs. A detailed dynamic analysis of the nozzle is presented. An updated statistical surrogate model relating the observations of interest to the control parameters is constructed. Despite small training and target datasets, and partial observability, the study successfully applies Probabilistic Learning on Manifolds (PLoM) to address these challenges. PLoM captures geometric nonlinear effects and uncertainty propagation, improving conditional mean statistics compared to training data. The conditional confidence region demonstrates the ability of the methodology to accurately represent both observed and unobserved output variables, contributing to advancements in modeling complex systems.
{"title":"Updating Nonlinear Stochastic Dynamics of an Uncertain Nozzle Model using Probabilistic Learning with Partial Observability and Incomplete dataset","authors":"E. Capiez-Lernout, O. Ezvan, Christian Soize","doi":"10.1115/1.4065312","DOIUrl":"https://doi.org/10.1115/1.4065312","url":null,"abstract":"\u0000 This paper introduces a methodology for updating the nonlinear stochastic dynamics of a nozzle with uncertain computational model. The approach focuses on a high-dimensional nonlinear computational model constrained by a small target dataset. Challenges include the large number of degrees-of-freedom, geometric nonlinearities, material uncertainties, stochastic external loads, under-observability, and high computational costs. A detailed dynamic analysis of the nozzle is presented. An updated statistical surrogate model relating the observations of interest to the control parameters is constructed. Despite small training and target datasets, and partial observability, the study successfully applies Probabilistic Learning on Manifolds (PLoM) to address these challenges. PLoM captures geometric nonlinear effects and uncertainty propagation, improving conditional mean statistics compared to training data. The conditional confidence region demonstrates the ability of the methodology to accurately represent both observed and unobserved output variables, contributing to advancements in modeling complex systems.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140702607","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}
Phyo Htet Hein, Elisabeth Kames, Cheng Chen, Beshoy Morkos
Requirements are frequently revised due to iterative nature of the design process. If not properly managed, these changes may result in financial and time losses due to undesired propagating effect. Currently, predictive models to assist designers in making well informed decisions prior to change implementation do not exist. Current modeling methods for managing requirements do not offer formal reasoning necessary to manage requirement change and its propagation. The ability to predict change during the design process may lead to valuable insights in designing artifacts more efficiently by minimizing unanticipated changes due to mismanaged requirement changes. Two research questions (RQs) are addressed in this paper: (1) How do complex network metrics of requirements, considering both node and edge interference, influence the predictability of requirement change propagation across different case studies? (2) How does the performance of the complex network metrics approach compare to the Refined Automated Requirement Change Propagation Prediction (R-ARCPP) tool, developed from our prior study, in accurately predicting requirement change propagation? Requirement changes are simulated by applying the node interference and the edge interference methods. It is found that complex network metrics can be used to predict requirement change propagation. Based on the studied data, the performance ranking of metrics is characterized by edge interference across the changes. The results reveal that the R-ARCPP tool ranks higher than comparatively performing complex network metrics.
{"title":"A Network Interference Approach to Analyzing Change Propagation in Requirements","authors":"Phyo Htet Hein, Elisabeth Kames, Cheng Chen, Beshoy Morkos","doi":"10.1115/1.4065273","DOIUrl":"https://doi.org/10.1115/1.4065273","url":null,"abstract":"\u0000 Requirements are frequently revised due to iterative nature of the design process. If not properly managed, these changes may result in financial and time losses due to undesired propagating effect. Currently, predictive models to assist designers in making well informed decisions prior to change implementation do not exist. Current modeling methods for managing requirements do not offer formal reasoning necessary to manage requirement change and its propagation. The ability to predict change during the design process may lead to valuable insights in designing artifacts more efficiently by minimizing unanticipated changes due to mismanaged requirement changes. Two research questions (RQs) are addressed in this paper: (1) How do complex network metrics of requirements, considering both node and edge interference, influence the predictability of requirement change propagation across different case studies? (2) How does the performance of the complex network metrics approach compare to the Refined Automated Requirement Change Propagation Prediction (R-ARCPP) tool, developed from our prior study, in accurately predicting requirement change propagation? Requirement changes are simulated by applying the node interference and the edge interference methods. It is found that complex network metrics can be used to predict requirement change propagation. Based on the studied data, the performance ranking of metrics is characterized by edge interference across the changes. The results reveal that the R-ARCPP tool ranks higher than comparatively performing complex network metrics.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140739132","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}
Customer preferences are found to evolve over time and correlate with geographical locations. Studying spatiotemporal heterogeneity of customer preferences is crucial to engineering design as it provides a dynamic perspective for understanding the trend of customer preferences. However, existing choice models for demand modeling do not take the spatiotemporal heterogeneity of customer preferences into consideration. Learning-based spatiotemporal data modeling methods usually require large-scale datasets for model training, which are not applicable to small aggregated data, such as the sale records of a product in several regions and years. To fill this research gap, we propose a spatial panel modeling approach to investigate the spatiotemporal heterogeneity of customer preferences. Product and regional attributes varying in time are included as model inputs to support the demand forecasting in engineering design. With a case study using the dataset of small SUV in China’s automotive market, we demonstrate that the spatial panel modeling approach outperforms other statistical spatiotemporal data models and non-parametric regression method in goodness of fit and prediction accuracy. Our results show that the increases of price and fuel consumption of small SUVs tend to have negative impact on their sales in all provinces. We illustrate a potential design application of the proposed approach in a portfolio optimization of two vehicles from the same producer. While the spatial panel modeling approach exists in econometrics, applying this approach to support engineering decisions by considering spatiotemporal heterogeneity and introducing engineering attributes in demand forecasting is the contribution of this work.
研究发现,客户偏好会随着时间的推移而变化,并与地理位置相关。研究客户偏好的时空异质性对工程设计至关重要,因为它为了解客户偏好趋势提供了一个动态视角。然而,现有的需求建模选择模型并未考虑客户偏好的时空异质性。基于学习的时空数据建模方法通常需要大规模数据集进行模型训练,而这些数据集不适用于小规模的聚合数据,如一种产品在多个地区和年份的销售记录。为了填补这一研究空白,我们提出了一种空间面板建模方法来研究顾客偏好的时空异质性。随时间变化的产品和地区属性被作为模型输入,以支持工程设计中的需求预测。通过使用中国汽车市场小型 SUV 数据集进行案例研究,我们证明了空间面板建模方法在拟合优度和预测准确性方面优于其他统计时空数据模型和非参数回归方法。我们的结果表明,小型 SUV 价格和油耗的增加往往会对其在所有省份的销量产生负面影响。我们在同一生产商的两款汽车的组合优化中说明了建议方法的潜在设计应用。虽然空间面板建模方法存在于计量经济学中,但通过考虑时空异质性和在需求预测中引入工程属性,将这种方法应用于支持工程决策,是这项工作的贡献所在。
{"title":"Modeling Spatiotemporal Heterogeneity of Customer Preferences with Small-scale Aggregated Data: A Spatial Panel Modeling Approach","authors":"Yuyang Chen, Youyi Bi, Jian Xie, Zhenghui Sha, Mingxian Wang, Yan Fu, Wei Chen","doi":"10.1115/1.4065211","DOIUrl":"https://doi.org/10.1115/1.4065211","url":null,"abstract":"\u0000 Customer preferences are found to evolve over time and correlate with geographical locations. Studying spatiotemporal heterogeneity of customer preferences is crucial to engineering design as it provides a dynamic perspective for understanding the trend of customer preferences. However, existing choice models for demand modeling do not take the spatiotemporal heterogeneity of customer preferences into consideration. Learning-based spatiotemporal data modeling methods usually require large-scale datasets for model training, which are not applicable to small aggregated data, such as the sale records of a product in several regions and years. To fill this research gap, we propose a spatial panel modeling approach to investigate the spatiotemporal heterogeneity of customer preferences. Product and regional attributes varying in time are included as model inputs to support the demand forecasting in engineering design. With a case study using the dataset of small SUV in China’s automotive market, we demonstrate that the spatial panel modeling approach outperforms other statistical spatiotemporal data models and non-parametric regression method in goodness of fit and prediction accuracy. Our results show that the increases of price and fuel consumption of small SUVs tend to have negative impact on their sales in all provinces. We illustrate a potential design application of the proposed approach in a portfolio optimization of two vehicles from the same producer. While the spatial panel modeling approach exists in econometrics, applying this approach to support engineering decisions by considering spatiotemporal heterogeneity and introducing engineering attributes in demand forecasting is the contribution of this work.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140761600","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}
Some industrial components, such as valves, relay switches, and motors occasionally experience intermittent faults (IFs) that usually disappear without any repair or intervention. This phenomenon occurs at a relatively low frequency even in components that are in an “as good as new” state. However, an increase in the frequency of IFs often indicates the onset of degradation. We develop an integrated detection-prognostics model for components that exhibit IFs and whose degradation data is high-dimensional. We discuss the use of Dynamic Time Warping (DTW) and a Variational Autoencoder (VAE) to perform feature engineering on the data. We then propose a Hidden Markov Model (HMM) based monitoring strategy composed of two parts: (1) a detection model that tracks and flags changes in the intermittent fault frequency (IFF), and (2) a prognostic model that leverages how the transition probabilities of the HMM evolve with progressive degradation to compute the remaining life distribution (RLD) of the component. We examine the performance of our modeling framework using high-dimensional data generated from a vehicular electrical system testbed designed to accelerate the degradation of a vehicle starter motor.
{"title":"An Integrated Detection-Prognostics Methodology for Components with Intermittent Faults","authors":"Michael Ibrahim, Heraldo Rozas, N. Gebraeel","doi":"10.1115/1.4065212","DOIUrl":"https://doi.org/10.1115/1.4065212","url":null,"abstract":"\u0000 Some industrial components, such as valves, relay switches, and motors occasionally experience intermittent faults (IFs) that usually disappear without any repair or intervention. This phenomenon occurs at a relatively low frequency even in components that are in an “as good as new” state. However, an increase in the frequency of IFs often indicates the onset of degradation. We develop an integrated detection-prognostics model for components that exhibit IFs and whose degradation data is high-dimensional. We discuss the use of Dynamic Time Warping (DTW) and a Variational Autoencoder (VAE) to perform feature engineering on the data. We then propose a Hidden Markov Model (HMM) based monitoring strategy composed of two parts: (1) a detection model that tracks and flags changes in the intermittent fault frequency (IFF), and (2) a prognostic model that leverages how the transition probabilities of the HMM evolve with progressive degradation to compute the remaining life distribution (RLD) of the component. We examine the performance of our modeling framework using high-dimensional data generated from a vehicular electrical system testbed designed to accelerate the degradation of a vehicle starter motor.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140784946","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}
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":null,"pages":null},"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":null,"pages":null},"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":null,"pages":null},"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":null,"pages":null},"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}