Abstract Monitoring the health condition as well as predicting the performance of Lithium-ion batteries are crucial to the reliability and safety of electrical systems such as electric vehicles. However, estimating the discharge capacity and end-of-discharge (EOD) of a battery in real-time remains a challenge. Few works have been reported on the relationship between the capacity degradation of a battery and EOD. We introduce a new data-driven method that combines convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) models to predict the discharge capacity and the EOD using online condition monitoring data. The CNN model extracts long-term correlations among voltage, current, and temperature measurements and then estimates the discharge capacity. The BiLSTM model extracts short-term dependencies in condition monitoring data and predicts the EOD for each discharge cycle while utilizing the capacity predicted by CNN as an additional input. By considering the discharge capacity, the BiLSTM model is able to use the long-term health condition of a battery to improve the prediction accuracy of its short-term performance. We demonstrated that the proposed method can achieve online discharge capacity estimation and EOD prediction efficiently and accurately.
{"title":"Data-Driven Online Prediction of Discharge Capacity and End-of-Discharge of Lithium-ion Battery","authors":"Junchuan Shi, Yupeng Wei, Dazhong Wu","doi":"10.1115/1.4063985","DOIUrl":"https://doi.org/10.1115/1.4063985","url":null,"abstract":"Abstract Monitoring the health condition as well as predicting the performance of Lithium-ion batteries are crucial to the reliability and safety of electrical systems such as electric vehicles. However, estimating the discharge capacity and end-of-discharge (EOD) of a battery in real-time remains a challenge. Few works have been reported on the relationship between the capacity degradation of a battery and EOD. We introduce a new data-driven method that combines convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) models to predict the discharge capacity and the EOD using online condition monitoring data. The CNN model extracts long-term correlations among voltage, current, and temperature measurements and then estimates the discharge capacity. The BiLSTM model extracts short-term dependencies in condition monitoring data and predicts the EOD for each discharge cycle while utilizing the capacity predicted by CNN as an additional input. By considering the discharge capacity, the BiLSTM model is able to use the long-term health condition of a battery to improve the prediction accuracy of its short-term performance. We demonstrated that the proposed method can achieve online discharge capacity estimation and EOD prediction efficiently and accurately.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"44 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584772","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}
Noah Hill, Matthew Ebert, Mena Maurice, Vinayak Krishnamurthy
Abstract We present a novel methodology to generate mechanical structures based on fractal geometry by using the chaos game, which generates self-similar point sets within a polygon. Using the Voronoi decomposition of these points, we are able to generate groups of self-similar structures that can be related back to their chaos game parameters, namely the polygonal domain, fractional distance, and number of samples. Our approach explores the use of forward design of generative structures, which in some cases can be easier to use for designing than inverse generative design techniques. To this end, the central hypothesis of our work is that structures generated using the chaos game can generate families of self-similar structures that, while not identical, exhibit similar mechanical behavior in a statistical sense. We present a systematic study of these self-similar structures through modal analysis and tensile loading and demonstrate a preliminary confirmation of our hypothesis.
{"title":"Cellular Chaos: Statistically Self-Similar Structures based on Chaos Game","authors":"Noah Hill, Matthew Ebert, Mena Maurice, Vinayak Krishnamurthy","doi":"10.1115/1.4063987","DOIUrl":"https://doi.org/10.1115/1.4063987","url":null,"abstract":"Abstract We present a novel methodology to generate mechanical structures based on fractal geometry by using the chaos game, which generates self-similar point sets within a polygon. Using the Voronoi decomposition of these points, we are able to generate groups of self-similar structures that can be related back to their chaos game parameters, namely the polygonal domain, fractional distance, and number of samples. Our approach explores the use of forward design of generative structures, which in some cases can be easier to use for designing than inverse generative design techniques. To this end, the central hypothesis of our work is that structures generated using the chaos game can generate families of self-similar structures that, while not identical, exhibit similar mechanical behavior in a statistical sense. We present a systematic study of these self-similar structures through modal analysis and tensile loading and demonstrate a preliminary confirmation of our hypothesis.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"48 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135584753","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}
Mehdi Taghizadeh, Mohammad Amin Nabian, Negin Alemazkoor
Abstract We propose a novel method for solving partial differential equations using multi-fidelity physics-informed generative adversarial networks. Our approach incorporates physics-supervision into the adversarial optimization process to guide the learning of the generator and discriminator models. The generator has two components: one that approximates the low-fidelity response of the input and another that combines the input and low-fidelity response to generate an approximation of high-fidelity responses. The discriminator identifies whether the input-output pairs accord not only with the actual high-fidelity response distribution, but also with physics. The effectiveness of the proposed method is demonstrated through numerical examples and compared to existing methods.
{"title":"Multi-fidelity Physics-informed Generative Adversarial Network for Solving Partial Differential Equations","authors":"Mehdi Taghizadeh, Mohammad Amin Nabian, Negin Alemazkoor","doi":"10.1115/1.4063986","DOIUrl":"https://doi.org/10.1115/1.4063986","url":null,"abstract":"Abstract We propose a novel method for solving partial differential equations using multi-fidelity physics-informed generative adversarial networks. Our approach incorporates physics-supervision into the adversarial optimization process to guide the learning of the generator and discriminator models. The generator has two components: one that approximates the low-fidelity response of the input and another that combines the input and low-fidelity response to generate an approximation of high-fidelity responses. The discriminator identifies whether the input-output pairs accord not only with the actual high-fidelity response distribution, but also with physics. The effectiveness of the proposed method is demonstrated through numerical examples and compared to existing methods.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135634426","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 In the rapidly advancing field of multi-modal machine learning (MMML), the convergence of multiple data modalities has the potential to reshape various applications. This paper presents a comprehensive overview of the current state, advancements, and challenges of MMML within the sphere of engineering design. The review begins with a deep dive into five fundamental concepts of MMML:multi-modal information representation, fusion, alignment, translation, and co-learning. Following this, we explore the cutting-edge applications of MMML, placing a particular emphasis on tasks pertinent to engineering design, such as cross-modal synthesis, multi-modal prediction, and cross-modal information retrieval. Through this comprehensive overview, we highlight the inherent challenges in adopting MMML in engineering design, and proffer potential directions for future research. To spur on the continued evolution of MMML in engineering design, we advocate for concentrated efforts to construct extensive multi-modal design datasets, develop effective data-driven MMML techniques tailored to design applications, and enhance the scalability and interpretability of MMML models. MMML models, as the next generation of intelligent design tools, hold a promising future to impact how products are designed.
{"title":"Multi-modal Machine Learning in Engineering Design: A Review and Future Directions","authors":"Binyang Song, Rui Zhou, Faez Ahmed","doi":"10.1115/1.4063954","DOIUrl":"https://doi.org/10.1115/1.4063954","url":null,"abstract":"Abstract In the rapidly advancing field of multi-modal machine learning (MMML), the convergence of multiple data modalities has the potential to reshape various applications. This paper presents a comprehensive overview of the current state, advancements, and challenges of MMML within the sphere of engineering design. The review begins with a deep dive into five fundamental concepts of MMML:multi-modal information representation, fusion, alignment, translation, and co-learning. Following this, we explore the cutting-edge applications of MMML, placing a particular emphasis on tasks pertinent to engineering design, such as cross-modal synthesis, multi-modal prediction, and cross-modal information retrieval. Through this comprehensive overview, we highlight the inherent challenges in adopting MMML in engineering design, and proffer potential directions for future research. To spur on the continued evolution of MMML in engineering design, we advocate for concentrated efforts to construct extensive multi-modal design datasets, develop effective data-driven MMML techniques tailored to design applications, and enhance the scalability and interpretability of MMML models. MMML models, as the next generation of intelligent design tools, hold a promising future to impact how products are designed.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"252 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135320575","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 In machining simulations, dexel models are often used to represent objects to achieve high accuracy and real-time performance. However, this approach leads to the loss of original surface information and topological relationships, thereby affecting the visualization effect of simulations. Furthermore, existing reconstruction methods have the drawbacks of generalization or redundancy. To reconstruct the surface of dexel models efficiently and accurately, this paper proposes an algorithm based on “composite block” partition, which converts the dexel model into a polyhedral model. The algorithm begins by partitioning the entire dexel model within the grids into several composite blocks based on the “Connectivity Principle” and generating their end faces. Subsequently, the transitional zone's surface is reconstructed based on the connectivity relationships of the boundaries of composite blocks. Finally, an optimization process refines the boundaries to generate smoother side faces at a low computational cost. The paper first validates the algorithm's reconstruction capability and the effectiveness of edge refinement through the reconstruction of various dexel models with different precision levels. It's observed that edge refinement doesn't introduce excessive additional computation, doubling the overall efficiency compared to existing algorithms. Furthermore, by changing model volumes and performing separate reconstructions, it's noted that as the volume increases, the incremental growth in conversion time gradually decreases. This makes the algorithm particularly suitable for reconstructing large-scale complex dexel models. Finally, the application of this algorithm in virtual-real simulation system and industrial digital twin system is briefly introduced.
{"title":"Reconstruction Algorithm for Complex Dexel Models Based on Composite Block Partition","authors":"Haiwen Yu, Dianliang Wu, Xu Hanzhong","doi":"10.1115/1.4063955","DOIUrl":"https://doi.org/10.1115/1.4063955","url":null,"abstract":"Abstract In machining simulations, dexel models are often used to represent objects to achieve high accuracy and real-time performance. However, this approach leads to the loss of original surface information and topological relationships, thereby affecting the visualization effect of simulations. Furthermore, existing reconstruction methods have the drawbacks of generalization or redundancy. To reconstruct the surface of dexel models efficiently and accurately, this paper proposes an algorithm based on “composite block” partition, which converts the dexel model into a polyhedral model. The algorithm begins by partitioning the entire dexel model within the grids into several composite blocks based on the “Connectivity Principle” and generating their end faces. Subsequently, the transitional zone's surface is reconstructed based on the connectivity relationships of the boundaries of composite blocks. Finally, an optimization process refines the boundaries to generate smoother side faces at a low computational cost. The paper first validates the algorithm's reconstruction capability and the effectiveness of edge refinement through the reconstruction of various dexel models with different precision levels. It's observed that edge refinement doesn't introduce excessive additional computation, doubling the overall efficiency compared to existing algorithms. Furthermore, by changing model volumes and performing separate reconstructions, it's noted that as the volume increases, the incremental growth in conversion time gradually decreases. This makes the algorithm particularly suitable for reconstructing large-scale complex dexel models. Finally, the application of this algorithm in virtual-real simulation system and industrial digital twin system is briefly introduced.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"76 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135321637","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 kinematics calibration for quadruped robots is essential in ensuring motion accuracy and control stability. The angle of the leg joints of the quadruped robot is error-compensated to improve its position accuracy. This paper proposes an online intelligent kinematics calibration method for quadruped robots using machine vision and artificial neural networks to simplify the calibration process and improve calibration accuracy. The method includes two parts: identifying the markers fixed on the legs through target detection and calculating the center coordinates of the markers and building an error model based on an artificial neural network to solve the angle error of each joint and compensate for it. A series of experiments have been carried out to verify the model's accuracy. The experimental results show that, compared to the traditional manual calibration, by adding an error correction model to the inverse kinematics neural network, the calibration efficiency can be significantly improved while the calibration accuracy is met.
{"title":"An automatic high-precision calibration method of legs and feet for quadruped robots using machine vision and artificial neural networks","authors":"Yaguan Li, Handing Xu, Yanjie Xu, Qingxue Huang, Xin-Jun Liu, Zhenguo Nie","doi":"10.1115/1.4063891","DOIUrl":"https://doi.org/10.1115/1.4063891","url":null,"abstract":"Abstract The kinematics calibration for quadruped robots is essential in ensuring motion accuracy and control stability. The angle of the leg joints of the quadruped robot is error-compensated to improve its position accuracy. This paper proposes an online intelligent kinematics calibration method for quadruped robots using machine vision and artificial neural networks to simplify the calibration process and improve calibration accuracy. The method includes two parts: identifying the markers fixed on the legs through target detection and calculating the center coordinates of the markers and building an error model based on an artificial neural network to solve the angle error of each joint and compensate for it. A series of experiments have been carried out to verify the model's accuracy. The experimental results show that, compared to the traditional manual calibration, by adding an error correction model to the inverse kinematics neural network, the calibration efficiency can be significantly improved while the calibration accuracy is met.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134971634","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}
Zhangyue Shi, Boris Oskolkov, Wenmeng Tian, Chen Kan, Chenang Liu
Abstract The advancement of sensing technology enables efficient data collection from manufacturing systems for monitoring and control. Furthermore, with the rapid development of the Internet of Things (IoT) and information technologies, more and more manufacturing systems become cyber-enabled, facilitating real-time data sharing and information exchange, which significantly improves the flexibility and efficiency of manufacturing systems. However, the cyber-enabled environment may pose the collected sensor data under high risks of cyber-physical attacks during the data and information sharing. Specifically, cyber-physical attacks could target the manufacturing process and/or the data transmission process to maliciously tamper the sensor data, resulting in false alarms or failures in anomaly detection in monitoring. In addition, the cyber-physical attacks may also enable illegal data access without authorization and cause the leakage of key product/process information. Therefore, it becomes critical to develop an effective approach to protect data from these attacks so that the cyber-physical security of the manufacturing systems could be assured in the cyber-enabled environment. To achieve this goal, this paper proposes an integrative blockchain-enabled data protection method by leveraging camouflaged asymmetry encryption. A real-world case study that protects cyber-physical security of collected sensor data in additive manufacturing is presented to demonstrate the effectiveness of the proposed method. The results demonstrate that malicious tampering could be detected in a relatively short time (less than 0.05ms) and the risk of unauthorized data access is significantly reduced as well.
{"title":"Sensor Data Protection through Integration of Blockchain and Camouflaged Encryption in Cyber-physical Manufacturing Systems","authors":"Zhangyue Shi, Boris Oskolkov, Wenmeng Tian, Chen Kan, Chenang Liu","doi":"10.1115/1.4063859","DOIUrl":"https://doi.org/10.1115/1.4063859","url":null,"abstract":"Abstract The advancement of sensing technology enables efficient data collection from manufacturing systems for monitoring and control. Furthermore, with the rapid development of the Internet of Things (IoT) and information technologies, more and more manufacturing systems become cyber-enabled, facilitating real-time data sharing and information exchange, which significantly improves the flexibility and efficiency of manufacturing systems. However, the cyber-enabled environment may pose the collected sensor data under high risks of cyber-physical attacks during the data and information sharing. Specifically, cyber-physical attacks could target the manufacturing process and/or the data transmission process to maliciously tamper the sensor data, resulting in false alarms or failures in anomaly detection in monitoring. In addition, the cyber-physical attacks may also enable illegal data access without authorization and cause the leakage of key product/process information. Therefore, it becomes critical to develop an effective approach to protect data from these attacks so that the cyber-physical security of the manufacturing systems could be assured in the cyber-enabled environment. To achieve this goal, this paper proposes an integrative blockchain-enabled data protection method by leveraging camouflaged asymmetry encryption. A real-world case study that protects cyber-physical security of collected sensor data in additive manufacturing is presented to demonstrate the effectiveness of the proposed method. The results demonstrate that malicious tampering could be detected in a relatively short time (less than 0.05ms) and the risk of unauthorized data access is significantly reduced as well.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135569527","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}
Yani Wang, Xiang Wang, Ruiyang Hao, Bingyu Lu, Biqing Huang
Abstract In contemporary industrial systems, ensuring the quality of object surfaces has become an essential and inescapable aspect of factory inspections. Cascade Regional Convolutional Neural Network (Cascade R-CNN), an object detection and instance segmentation algorithm based on deep learning, has been widely applied in numerous industrial applications. Nonetheless, there is still space for improving the detection of defects on metal surfaces. This paper proposes an enhanced metal defect detection method based on Cascade R-CNN. Specifically, the improved backbone network is employed to acquire the features of images, which enables more precise localization. Additionally, up and down sampling is combined to extract multi-scale defect feature maps, and contrast histogram equalization enhancement is utilized to tackle the issue of unclear contrast in the data. Experimental results demonstrate that the proposed approach achieves a mean Average Precision (mAP) of 0.754 on the NEU-DET dataset, and outperforms the Cascade R-CNN model by 9.2%.
{"title":"Metal Surface Defect Detection Method Based on Improved Cascade R-CNN","authors":"Yani Wang, Xiang Wang, Ruiyang Hao, Bingyu Lu, Biqing Huang","doi":"10.1115/1.4063860","DOIUrl":"https://doi.org/10.1115/1.4063860","url":null,"abstract":"Abstract In contemporary industrial systems, ensuring the quality of object surfaces has become an essential and inescapable aspect of factory inspections. Cascade Regional Convolutional Neural Network (Cascade R-CNN), an object detection and instance segmentation algorithm based on deep learning, has been widely applied in numerous industrial applications. Nonetheless, there is still space for improving the detection of defects on metal surfaces. This paper proposes an enhanced metal defect detection method based on Cascade R-CNN. Specifically, the improved backbone network is employed to acquire the features of images, which enables more precise localization. Additionally, up and down sampling is combined to extract multi-scale defect feature maps, and contrast histogram equalization enhancement is utilized to tackle the issue of unclear contrast in the data. Experimental results demonstrate that the proposed approach achieves a mean Average Precision (mAP) of 0.754 on the NEU-DET dataset, and outperforms the Cascade R-CNN model by 9.2%.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135569692","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}
Jake Janssen, Ghadir Haikal, Erin DeCarlo, Michael Hartnett, Matthew Kirby
Abstract Despite their effectiveness in modeling complex phenomena, the adoption of machine learning (ML) methods in computational mechanics has been hindered by the lack of availability of training datasets, limitations on accuracy of out-of-sample predictions, and computational cost. This work presents a physics-informed ML approach and network architecture that addresses these challenges in the context of modeling the behavior of materials with damage. The proposed methodology is a novel Physics-Informed General Convolutional Network (PIGCN) framework that features (1) the fusion of a dense edge network with a convolutional neural network (CNN) for specifying and enforcing boundary conditions and geometry information, (2) a data augmentation approach for learning more information from a static dataset that significantly reduces the necessary data for training, and (3) the use of a CNN for physics-informed ML applications, which is not as well explored as graph networks in the current literature. The PIGCN framework is demonstrated for a simple two-dimensional, rectangular plate with a hole or elliptical defect in a linear elastic material, but the approach is extensible to three dimensions and more complex problems. The results presented in the paper show that the PIGCN framework improves physics-based loss convergence and predictive capability compared to ML-only (physics-uninformed) architectures. A key outcome of this research is the significant reduction in training data requirements compared to ML-only models, which could reduce a considerable hurdle to using data-driven models in materials engineering where material experimental data is often limited.
{"title":"A Physics-Informed General Convolutional Network for the Computational Modeling of Materials with Damage","authors":"Jake Janssen, Ghadir Haikal, Erin DeCarlo, Michael Hartnett, Matthew Kirby","doi":"10.1115/1.4063863","DOIUrl":"https://doi.org/10.1115/1.4063863","url":null,"abstract":"Abstract Despite their effectiveness in modeling complex phenomena, the adoption of machine learning (ML) methods in computational mechanics has been hindered by the lack of availability of training datasets, limitations on accuracy of out-of-sample predictions, and computational cost. This work presents a physics-informed ML approach and network architecture that addresses these challenges in the context of modeling the behavior of materials with damage. The proposed methodology is a novel Physics-Informed General Convolutional Network (PIGCN) framework that features (1) the fusion of a dense edge network with a convolutional neural network (CNN) for specifying and enforcing boundary conditions and geometry information, (2) a data augmentation approach for learning more information from a static dataset that significantly reduces the necessary data for training, and (3) the use of a CNN for physics-informed ML applications, which is not as well explored as graph networks in the current literature. The PIGCN framework is demonstrated for a simple two-dimensional, rectangular plate with a hole or elliptical defect in a linear elastic material, but the approach is extensible to three dimensions and more complex problems. The results presented in the paper show that the PIGCN framework improves physics-based loss convergence and predictive capability compared to ML-only (physics-uninformed) architectures. A key outcome of this research is the significant reduction in training data requirements compared to ML-only models, which could reduce a considerable hurdle to using data-driven models in materials engineering where material experimental data is often limited.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135569830","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 As Industry 4.0 and digitization continue to advance, the reliance on information technology increases, making the world more vulnerable to cyberattacks, especially cyber-physical attacks that can manipulate physical systems and compromise operational data integrity. Detecting cyberattacks in multistage manufacturing systems (MMS) is crucial due to the growing sophistication of attacks and the complexity of MMS. Attacks can propagate throughout the system, affecting subsequent stages and making detection more challenging than in single-stage systems. Localization is also critical due to the complex interactions in MMS. To address these challenges, a group lasso regression-based framework is proposed to detect and localize attacks in MMS. The proposed algorithm outperforms traditional hypothesis testing-based methods in expected detection delay and localization accuracy, as demonstrated in a simple linear multistage manufacturing system.
{"title":"GLHAD: A Group Lasso-based Hybrid Attack Detection and Localization Framework for Multistage Manufacturing Systems","authors":"Ahmad KoKhahi, Dan Li","doi":"10.1115/1.4063862","DOIUrl":"https://doi.org/10.1115/1.4063862","url":null,"abstract":"Abstract As Industry 4.0 and digitization continue to advance, the reliance on information technology increases, making the world more vulnerable to cyberattacks, especially cyber-physical attacks that can manipulate physical systems and compromise operational data integrity. Detecting cyberattacks in multistage manufacturing systems (MMS) is crucial due to the growing sophistication of attacks and the complexity of MMS. Attacks can propagate throughout the system, affecting subsequent stages and making detection more challenging than in single-stage systems. Localization is also critical due to the complex interactions in MMS. To address these challenges, a group lasso regression-based framework is proposed to detect and localize attacks in MMS. The proposed algorithm outperforms traditional hypothesis testing-based methods in expected detection delay and localization accuracy, as demonstrated in a simple linear multistage manufacturing system.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135569528","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：