During disasters, such as floods, it is crucial to get real-time ground information for planning rescue and response operations. With the advent of technology, Unmanned Aerial Vehicles (UAVs) are being deployed for real-time path planning to provide support to evacuation teams. However, their dependency on expert human pilots for command and control limits their operational capacity to the line-of-sight range. In this paper, we utilize a Deep Reinforcement Learning algorithm to autonomously control multiple UAVs for area coverage. The objective is to identify serviceable paths for safe navigation of waterborne evacuation vehicles (WBVs) to reach critical location(s) during floods. The UAVs are tasked to capture the obstacle-related data and identify shallow water regions for unrestricted motion of the WBV(s). The data gathered by UAVs is used by the Minimum expansion A* (MEA*) algorithm for path planning to assist WBV(s). MEA* addresses the node expansion issue with the standard A* algorithm, by pruning the unserviceable nodes/locations based on the captured information, hence expediting the path planning process. The proposed approach, MEA*MADDPG, is compared with other prevalent techniques from the literature over simulated flood environments with moving obstacles. The results highlight the significance of the proposed model as it outperforms other techniques when compared over various performance metrics.
{"title":"Multi-UAV Assisted Flood Navigation of Waterborne Vehicles using Deep Reinforcement Learning","authors":"Armaan Garg, Shashi Shekhar Jha","doi":"10.1115/1.4066025","DOIUrl":"https://doi.org/10.1115/1.4066025","url":null,"abstract":"\u0000 During disasters, such as floods, it is crucial to get real-time ground information for planning rescue and response operations. With the advent of technology, Unmanned Aerial Vehicles (UAVs) are being deployed for real-time path planning to provide support to evacuation teams. However, their dependency on expert human pilots for command and control limits their operational capacity to the line-of-sight range. In this paper, we utilize a Deep Reinforcement Learning algorithm to autonomously control multiple UAVs for area coverage. The objective is to identify serviceable paths for safe navigation of waterborne evacuation vehicles (WBVs) to reach critical location(s) during floods. The UAVs are tasked to capture the obstacle-related data and identify shallow water regions for unrestricted motion of the WBV(s). The data gathered by UAVs is used by the Minimum expansion A* (MEA*) algorithm for path planning to assist WBV(s). MEA* addresses the node expansion issue with the standard A* algorithm, by pruning the unserviceable nodes/locations based on the captured information, hence expediting the path planning process. The proposed approach, MEA*MADDPG, is compared with other prevalent techniques from the literature over simulated flood environments with moving obstacles. The results highlight the significance of the proposed model as it outperforms other techniques when compared over various performance metrics.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141821871","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}
Additive manufacturing fabricates 3D parts via layer-by-layer deposition and solidification of materials. Due to the complexity of this process, advanced sensing is increasingly employed to facilitate system visibility, leading to a large amount of high-dimensional and complex-structured data. While deep learning brings attractive characteristics for data-driven process monitoring and quality prediction, it is currently limited in the ability to assimilate engineering knowledge and offer model interpretability for understanding process-quality relationships. In addition, due to spatiotemporal correlations in AM, a melt-pool anomaly observed during the manufacturing process is not always indicative of abnormal quality characteristics. There is a pressing need to go beyond pointwise analysis of melt pools and consider spatiotemporal effects for quality analysis. In this paper, we propose a novel feature learning framework guided by engineering knowledge for AM quality monitoring. First, engineering knowledge is integrated with deep learning to delineate various sources of process variations and extract melt-pool features that reflect quality-related relationships. Second, a 3D neighborhood model is designed to characterize spatiotemporal variations of melt pools based on their domain-informed features. The resulting 3D neighborhood profiles enable us to go beyond pointwise analysis of melt pools for capturing process-quality relationships. Finally, we built a regression model to predict internal density variations using 3D neighborhood profiles. Our experiments demonstrate that the proposed framework significantly outperforms traditional hand-crafted method and black-box learning in both the ability to provide quality-related features and predict internal density variations.
增材制造通过逐层沉积和凝固材料制造三维零件。由于这种工艺的复杂性,人们越来越多地采用先进的传感技术来提高系统的可视性,从而产生了大量高维和复杂结构的数据。虽然深度学习为数据驱动的过程监控和质量预测带来了极具吸引力的特性,但它目前在吸收工程知识和为理解过程与质量的关系提供模型可解释性方面能力有限。此外,由于 AM 中的时空相关性,在制造过程中观察到的熔池异常并不总能表明质量特性异常。因此,迫切需要超越熔池点分析,考虑时空效应来进行质量分析。在本文中,我们提出了一种以工程知识为指导的新型特征学习框架,用于 AM 质量监控。首先,将工程知识与深度学习相结合,以划分工艺变化的各种来源,并提取反映质量相关关系的熔池特征。其次,我们设计了一个三维邻域模型,根据领域信息特征来描述熔池的时空变化。由此产生的三维邻域剖面使我们能够超越对熔池的点状分析,捕捉过程与质量之间的关系。最后,我们建立了一个回归模型,利用三维邻域剖面预测内部密度变化。我们的实验证明,所提出的框架在提供质量相关特征和预测内部密度变化的能力方面都明显优于传统的手工方法和黑盒学习。
{"title":"Engineering-guided Deep Feature Learning for Manufacturing Process Monitoring","authors":"Siqi Zhang, Hui Yang, Zhuo Yang, Yan Lu","doi":"10.1115/1.4066026","DOIUrl":"https://doi.org/10.1115/1.4066026","url":null,"abstract":"\u0000 Additive manufacturing fabricates 3D parts via layer-by-layer deposition and solidification of materials. Due to the complexity of this process, advanced sensing is increasingly employed to facilitate system visibility, leading to a large amount of high-dimensional and complex-structured data. While deep learning brings attractive characteristics for data-driven process monitoring and quality prediction, it is currently limited in the ability to assimilate engineering knowledge and offer model interpretability for understanding process-quality relationships. In addition, due to spatiotemporal correlations in AM, a melt-pool anomaly observed during the manufacturing process is not always indicative of abnormal quality characteristics. There is a pressing need to go beyond pointwise analysis of melt pools and consider spatiotemporal effects for quality analysis. In this paper, we propose a novel feature learning framework guided by engineering knowledge for AM quality monitoring. First, engineering knowledge is integrated with deep learning to delineate various sources of process variations and extract melt-pool features that reflect quality-related relationships. Second, a 3D neighborhood model is designed to characterize spatiotemporal variations of melt pools based on their domain-informed features. The resulting 3D neighborhood profiles enable us to go beyond pointwise analysis of melt pools for capturing process-quality relationships. Finally, we built a regression model to predict internal density variations using 3D neighborhood profiles. Our experiments demonstrate that the proposed framework significantly outperforms traditional hand-crafted method and black-box learning in both the ability to provide quality-related features and predict internal density variations.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":2.6,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141822325","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}
We live in an age in which new things are emerging faster that their deep understanding. This statement in particularly applies to doing research and educating university students concerning next generation cyber-physical systems (NG-CPSs). The fast evolution of this system paradigm would have expected a rapid and comprehensive paradigmatic change in research and education concerning this family of systems. However, this has not happened yet. Seeking for a sufficing explanation, this paper reviews the current literature and makes an attempt to cast light on the most significant recent developments in the field of NG-CPSs. The main assumptions of the authors are that research and education should appear in harmony in academic knowledge acquisition and distribution processes, and that academic education of NG-CPSs should be organized and conducted according to a defendable future vision. Combining the results of a broadly-based study of the literature with prognostic critical thinking and personal experiences, this review-based position paper first discusses the current socio-techno-scientific environment, the involved stakeholders, and the demands and two approaches of truly systems-oriented education. Then, it concentrates on the recognized limitations of mono- and interdisciplinary research, and on supradisciplinary approach and transdisciplinary knowledge generation for NG-CPSs. As main contributions, the paper (i) identifies and analyzes the latest theoretical, engineering, and technological developments, (ii) reveals the major trends and their presumably significant implications, (iii) presents a number of thought-provoking findings and makes propositions about the desirable actions.
{"title":"What to consider at the development of educational programs and courses about next-generation cyber-physical systems?","authors":"Imre Horvath, Zühal Erden","doi":"10.1115/1.4065735","DOIUrl":"https://doi.org/10.1115/1.4065735","url":null,"abstract":"\u0000 We live in an age in which new things are emerging faster that their deep understanding. This statement in particularly applies to doing research and educating university students concerning next generation cyber-physical systems (NG-CPSs). The fast evolution of this system paradigm would have expected a rapid and comprehensive paradigmatic change in research and education concerning this family of systems. However, this has not happened yet. Seeking for a sufficing explanation, this paper reviews the current literature and makes an attempt to cast light on the most significant recent developments in the field of NG-CPSs. The main assumptions of the authors are that research and education should appear in harmony in academic knowledge acquisition and distribution processes, and that academic education of NG-CPSs should be organized and conducted according to a defendable future vision. Combining the results of a broadly-based study of the literature with prognostic critical thinking and personal experiences, this review-based position paper first discusses the current socio-techno-scientific environment, the involved stakeholders, and the demands and two approaches of truly systems-oriented education. Then, it concentrates on the recognized limitations of mono- and interdisciplinary research, and on supradisciplinary approach and transdisciplinary knowledge generation for NG-CPSs. As main contributions, the paper (i) identifies and analyzes the latest theoretical, engineering, and technological developments, (ii) reveals the major trends and their presumably significant implications, (iii) presents a number of thought-provoking findings and makes propositions about the desirable actions.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141341121","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}
Gaurav Ameta, Satish Bukkapatnam, Dan Li, Wenmeng Tian, Mark Yampolskiy, Fan Zhang
The landscape of cybersecurity in manufacturing exhibits a dynamic interplay between evolving threats and vulnerabilities against innovative defense mechanisms. With the increasing adoption of smart and cloud-controlled technologies, there is a growing emphasis on securing manufacturing systems from cyber-attacks. Future trends indicate a shift toward implementing more advanced technologies such as artificial intelligence and machine learning for threat identification, attack detection, and response. Additionally, the adoption of secure-by-design principles in product development and the integration of blockchain technology for ensuring the integrity of supply chain data are expected to become more prevalent. As manufacturers continue to digitize and connect their operations, collaboration between industry stakeholders, government agencies, and cybersecurity experts will be crucial in developing robust defense strategies against evolving security threats. This Special Issue provided a platform for the research advancing understanding of and addressing these threats.
{"title":"JCISE Special Issue: Cybersecurity in Manufacturing","authors":"Gaurav Ameta, Satish Bukkapatnam, Dan Li, Wenmeng Tian, Mark Yampolskiy, Fan Zhang","doi":"10.1115/1.4065685","DOIUrl":"https://doi.org/10.1115/1.4065685","url":null,"abstract":"\u0000 The landscape of cybersecurity in manufacturing exhibits a dynamic interplay between evolving threats and vulnerabilities against innovative defense mechanisms. With the increasing adoption of smart and cloud-controlled technologies, there is a growing emphasis on securing manufacturing systems from cyber-attacks. Future trends indicate a shift toward implementing more advanced technologies such as artificial intelligence and machine learning for threat identification, attack detection, and response. Additionally, the adoption of secure-by-design principles in product development and the integration of blockchain technology for ensuring the integrity of supply chain data are expected to become more prevalent. As manufacturers continue to digitize and connect their operations, collaboration between industry stakeholders, government agencies, and cybersecurity experts will be crucial in developing robust defense strategies against evolving security threats. This Special Issue provided a platform for the research advancing understanding of and addressing these threats.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141383153","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}
Industry 4.0 drives exponential growth in the amount of operational data collected in factories. These data are commonly distributed and stored in different business units or cooperative companies. Such data-rich environments increase the likelihood of cyber attacks, privacy breaches, and security violations. Also, this poses significant challenges on developing machine learning models on sensitive data that are distributed among different business units. To fill this gap, this paper presents a novel privacy-preserving framework to enable federated learning on siloed and encrypted data for smart manufacturing. Specifically, we leverage fully homomorphic encryption (FHE) to allow for computation on ciphertexts and generate encrypted results which, when decrypted, match the results of mathematical operations performed on the plaintexts. Multi-layer encryption and privacy protection reduce the likelihood of data breaches while maintaining the prediction performance of machine learning models. Experimental results in real-world case studies show that the proposed framework yields superior performance to reduce the risk of cyber attacks and harness siloed data for smart manufacturing.
{"title":"Federated Learning on Distributed and Encrypted Data for Smart Manufacturing","authors":"Timothy Kuo, Hui Yang","doi":"10.1115/1.4065571","DOIUrl":"https://doi.org/10.1115/1.4065571","url":null,"abstract":"\u0000 Industry 4.0 drives exponential growth in the amount of operational data collected in factories. These data are commonly distributed and stored in different business units or cooperative companies. Such data-rich environments increase the likelihood of cyber attacks, privacy breaches, and security violations. Also, this poses significant challenges on developing machine learning models on sensitive data that are distributed among different business units. To fill this gap, this paper presents a novel privacy-preserving framework to enable federated learning on siloed and encrypted data for smart manufacturing. Specifically, we leverage fully homomorphic encryption (FHE) to allow for computation on ciphertexts and generate encrypted results which, when decrypted, match the results of mathematical operations performed on the plaintexts. Multi-layer encryption and privacy protection reduce the likelihood of data breaches while maintaining the prediction performance of machine learning models. Experimental results in real-world case studies show that the proposed framework yields superior performance to reduce the risk of cyber attacks and harness siloed data for smart manufacturing.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141117916","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}
Roham Sadeghi Tabar, Samuel Lorin, L. Lindkvist, Kristina Wärmefjord, R. Söderberg
Geometric variation is an inevitable element of any fabrication process. To secure the geometric quality of the assembled products, variation simulation is performed to control compliance with the set geometric requirements. In non-rigid variation simulation, contact modeling is used to avoid the virtual penetration of the components in the adjacent areas, enhancing the simulation accuracy. For frictionless contact models, numerical errors and convergence issues due to the deformation behavior of the interacting surfaces are still limiting the computational efficiency of solving this optimization problem. The optimization problem associated with a contact model is often large-scale, and in practice, fast and robust methods for achieving convergence are required. Previous implementations of contact modeling for non-rigid variation simulation have been prominently based on the Iterative or Penalty Methods. In this paper, a quadratic programming approach has been introduced, based on the Lagrangian multiplier method, for robust contact modeling in non-rigid variation simulation, and the performance of the proposed approach has been compared to the previously applied Iterative and Interior Point Method. The methods have been compared on three industrial reference cases, and the convergence and time-efficiency of each method are compared. The results show that robust optimization of the quadratic program associated with the contact model is highly dependent on the reduced stiffness matrix condition. Furthermore, it has been shown that robust and efficient contact modeling in non-rigid variation simulation is achievable through the proposed quadratic programming method.
{"title":"Robust Contact Computation in Non-Rigid Variation Simulation","authors":"Roham Sadeghi Tabar, Samuel Lorin, L. Lindkvist, Kristina Wärmefjord, R. Söderberg","doi":"10.1115/1.4065570","DOIUrl":"https://doi.org/10.1115/1.4065570","url":null,"abstract":"\u0000 Geometric variation is an inevitable element of any fabrication process. To secure the geometric quality of the assembled products, variation simulation is performed to control compliance with the set geometric requirements. In non-rigid variation simulation, contact modeling is used to avoid the virtual penetration of the components in the adjacent areas, enhancing the simulation accuracy. For frictionless contact models, numerical errors and convergence issues due to the deformation behavior of the interacting surfaces are still limiting the computational efficiency of solving this optimization problem. The optimization problem associated with a contact model is often large-scale, and in practice, fast and robust methods for achieving convergence are required. Previous implementations of contact modeling for non-rigid variation simulation have been prominently based on the Iterative or Penalty Methods. In this paper, a quadratic programming approach has been introduced, based on the Lagrangian multiplier method, for robust contact modeling in non-rigid variation simulation, and the performance of the proposed approach has been compared to the previously applied Iterative and Interior Point Method. The methods have been compared on three industrial reference cases, and the convergence and time-efficiency of each method are compared. The results show that robust optimization of the quadratic program associated with the contact model is highly dependent on the reduced stiffness matrix condition. Furthermore, it has been shown that robust and efficient contact modeling in non-rigid variation simulation is achievable through the proposed quadratic programming method.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141117851","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}
Sean Rescsanski, Vihaan Shah, Jiong Tang, Farhad Imani
Robotic additive manufacturing (RAM) offers significant improvements in maximum build volume compared to conventional bounded designs (e.g., gantry) by leveraging high degree of freedom machines and multi-robot cooperation. However, cooperative RAM suffers from the same defect generation challenges as conventional systems, necessitating improvements in the detection and prevention of flaws within fabricated components. Quality assurance can be further bolstered through the integration of AM models, which utilize sensor feedback to localize defects, vastly reducing false positives. This research explores defect localization through a novel dynamic defect model created from simulated sensing data. In particular, two cooperative robots are simulated to estimate defect parameters, while observing the workspace and accurately classifying different regions of the part, generating a Gaussian mixture map that identifies and assigns appropriate actions based on defect types and characteristics. The experimental result shows that implementation of the dynamic defect model and selective reevaluation achieved an effective defect detection accuracy of 99.9%, an improvement of 9.9% without localization. The proposed framework holds potential for application in domains that utilize high degrees of freedom machines and collaborative agents, offering scalability, improved fabrication speeds, and enhanced mechanical properties.
机器人增材制造(RAM)通过利用高自由度机器和多机器人合作,与传统的有界设计(如龙门)相比,在最大制造体积方面有显著改进。然而,与传统系统一样,合作式 RAM 也面临着缺陷产生的挑战,因此有必要改进对制造部件缺陷的检测和预防。质量保证可以通过集成 AM 模型得到进一步加强,该模型利用传感器反馈定位缺陷,大大减少了误报。这项研究通过模拟传感数据创建的新型动态缺陷模型来探索缺陷定位。具体而言,模拟两个合作机器人估算缺陷参数,同时观察工作空间并对零件的不同区域进行精确分类,生成高斯混合图,根据缺陷类型和特征识别并分配适当的操作。实验结果表明,实施动态缺陷模型和选择性重新评估后,有效缺陷检测准确率达到 99.9%,在没有定位的情况下提高了 9.9%。所提出的框架有望应用于使用高自由度机器和协作代理的领域,提供可扩展性,提高制造速度,并增强机械性能。
{"title":"Stochastic Defect Localization for Cooperative Additive Manufacturing using Gaussian Mixture Maps","authors":"Sean Rescsanski, Vihaan Shah, Jiong Tang, Farhad Imani","doi":"10.1115/1.4065525","DOIUrl":"https://doi.org/10.1115/1.4065525","url":null,"abstract":"\u0000 Robotic additive manufacturing (RAM) offers significant improvements in maximum build volume compared to conventional bounded designs (e.g., gantry) by leveraging high degree of freedom machines and multi-robot cooperation. However, cooperative RAM suffers from the same defect generation challenges as conventional systems, necessitating improvements in the detection and prevention of flaws within fabricated components. Quality assurance can be further bolstered through the integration of AM models, which utilize sensor feedback to localize defects, vastly reducing false positives. This research explores defect localization through a novel dynamic defect model created from simulated sensing data. In particular, two cooperative robots are simulated to estimate defect parameters, while observing the workspace and accurately classifying different regions of the part, generating a Gaussian mixture map that identifies and assigns appropriate actions based on defect types and characteristics. The experimental result shows that implementation of the dynamic defect model and selective reevaluation achieved an effective defect detection accuracy of 99.9%, an improvement of 9.9% without localization. The proposed framework holds potential for application in domains that utilize high degrees of freedom machines and collaborative agents, offering scalability, improved fabrication speeds, and enhanced mechanical properties.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140976637","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}
Hydraulic cylinders with higher stages of extraction are extensively used in earthmoving and heavy machines due to their longer stroke, shorter retracted length and high-end performance. The rigorous and long hours of operations make cylinders prone to internal leakage, which visually remains unnoticeable This manuscript presents the conceptualization and realization of a newly developed 210 bar high-pressure hydraulic test rig actuated by a two-stage hydraulic cylinder. Experiments have been carried out to acquire pressure signals for two different leakage conditions (3 and 5% for moderate and severe leakage respectively) in the ramp wave motion of the cylinder. A decline in the working pressure and the piston velocity by approximately 10 and 45% for these leakage conditions respectively is noted. The time-frequency analysis infers these signals contain low-frequency components. For the automated leakage detection, a new iterative probability-based, transductive semi-supervised Support Vector Machine (TS-SVM) is proposed capable of learning with limited datasets in several iterations. TS-SVM classifies the internal leakage with 100% accuracy in 4 iterations and utilises only 64% of the total training data.
{"title":"Semi-supervised approach using Transductive SVM for internal leakage detection in two-stage hydraulic cylinder","authors":"Jatin Prakash, Ankur Miglani, P. K. Kankar","doi":"10.1115/1.4065526","DOIUrl":"https://doi.org/10.1115/1.4065526","url":null,"abstract":"\u0000 Hydraulic cylinders with higher stages of extraction are extensively used in earthmoving and heavy machines due to their longer stroke, shorter retracted length and high-end performance. The rigorous and long hours of operations make cylinders prone to internal leakage, which visually remains unnoticeable This manuscript presents the conceptualization and realization of a newly developed 210 bar high-pressure hydraulic test rig actuated by a two-stage hydraulic cylinder. Experiments have been carried out to acquire pressure signals for two different leakage conditions (3 and 5% for moderate and severe leakage respectively) in the ramp wave motion of the cylinder. A decline in the working pressure and the piston velocity by approximately 10 and 45% for these leakage conditions respectively is noted. The time-frequency analysis infers these signals contain low-frequency components. For the automated leakage detection, a new iterative probability-based, transductive semi-supervised Support Vector Machine (TS-SVM) is proposed capable of learning with limited datasets in several iterations. TS-SVM classifies the internal leakage with 100% accuracy in 4 iterations and utilises only 64% of the total training data.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140972206","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}
Indranil Hazra, Matthew Weiner, Ruochen Yang, Arko Chattejee, Joseph Southgate, Katrina Groth, S. Azarm
With the increasing popularity and deployment of unmanned surface vessels (USVs) all over the world, prognostics and health management (PHM) has become an indispensable tool for health monitoring, fault diagnosis, health prognosis, and maintenance of marine equipment on USVs. USVs are designed to undertake critical and extended missions, often in extreme conditions, without human intervention. This makes the USVs susceptible to equipment malfunction, which increases the probability of system failure during mission execution. In fact, in the absence of any crew onboard, system failure during a mission can create a great inconvenience for the concerned stakeholders, which compels them to design highly reliable USVs that must have integrated intelligent PHM systems onboard. To improve mission reliability and health management of USVs, researchers have been investigating and proposing PHM-based tools or frameworks that are claimed to operate in real time. This paper presents a comprehensive review of the existing literature on recent developments in PHM-related studies in the context of USVs. It covers a broad perspective of PHM on USVs, including system simulation, sensor data, data assimilation, data fusion, advancements in diagnosis and prognosis studies, and health management. After reviewing the literature, this study summarizes the lessons learned, identifies current gaps, and proposes a new system-level framework for developing a hybrid (offline-online) optimization-based PHM system for USVs in order to overcome some of the existing challenges.
{"title":"Prognostics and Health Management of Unmanned Surface Vessels: Past, Present, and Future","authors":"Indranil Hazra, Matthew Weiner, Ruochen Yang, Arko Chattejee, Joseph Southgate, Katrina Groth, S. Azarm","doi":"10.1115/1.4065483","DOIUrl":"https://doi.org/10.1115/1.4065483","url":null,"abstract":"\u0000 With the increasing popularity and deployment of unmanned surface vessels (USVs) all over the world, prognostics and health management (PHM) has become an indispensable tool for health monitoring, fault diagnosis, health prognosis, and maintenance of marine equipment on USVs. USVs are designed to undertake critical and extended missions, often in extreme conditions, without human intervention. This makes the USVs susceptible to equipment malfunction, which increases the probability of system failure during mission execution. In fact, in the absence of any crew onboard, system failure during a mission can create a great inconvenience for the concerned stakeholders, which compels them to design highly reliable USVs that must have integrated intelligent PHM systems onboard. To improve mission reliability and health management of USVs, researchers have been investigating and proposing PHM-based tools or frameworks that are claimed to operate in real time. This paper presents a comprehensive review of the existing literature on recent developments in PHM-related studies in the context of USVs. It covers a broad perspective of PHM on USVs, including system simulation, sensor data, data assimilation, data fusion, advancements in diagnosis and prognosis studies, and health management. After reviewing the literature, this study summarizes the lessons learned, identifies current gaps, and proposes a new system-level framework for developing a hybrid (offline-online) optimization-based PHM system for USVs in order to overcome some of the existing challenges.","PeriodicalId":54856,"journal":{"name":"Journal of Computing and Information Science in Engineering","volume":null,"pages":null},"PeriodicalIF":3.1,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140998279","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}
Qihang Fang, Gang Xiong, Weixing Wang, Zhen Shen, Xisong Dong, Fei-Yue Wang
Additive manufacturing (AM) is gaining prominence across numerous fields, which involves the generation of extensive data at each process stage. A relational database is a useful tool to store such AM data in a key-value manner and streamline data retrieval. Users can specify the value of one AM variable or key and retrieve the corresponding record values of another key. This establishes the correlations between AM variables, and supports applications such as process planning. Nonetheless, such an operation is a “hard” query, which lacks reasoning capabilities and fails to provide useful information when required records are missing. It is urgent to develop a more powerful AM database to handle AM data better, which should support “soft” queries, be scalable to high-dimensional data, and maintain flexible query functionality among multiple keys. In this paper, we upgrade an AM database with probabilistic modeling and transformation-invariant feature learning, which is termed as a probabilistic AM database (PAMDB). The PAMDB allows the selection of any key as a query key, or even multiple keys as query keys, to retrieve the values of other keys, which is adapted to unseen, high-dimensional, and multi-modal AM data. Two case studies were conducted for laser powder bed fusion (LPBF) and vat photopolymerization (VP). Compared with existing methods, experimental results underscore the efficacy of the PAMDBs, both qualitatively and quantitatively, in tasks that includes melt pool size prediction and scan parameter estimation in LPBF, and defect detection for the resin deposition process in VP.
快速成型制造(AM)在众多领域日益突出,这涉及在每个流程阶段生成大量数据。关系数据库是以键值方式存储此类 AM 数据并简化数据检索的有用工具。用户可以指定一个 AM 变量或键的值,并检索另一个键的相应记录值。这可以建立 AM 变量之间的相关性,并支持流程规划等应用。然而,这种操作属于 "硬 "查询,缺乏推理能力,在缺少所需记录时无法提供有用信息。当务之急是开发功能更强大的 AM 数据库,以更好地处理 AM 数据,该数据库应支持 "软 "查询,可扩展至高维数据,并在多个键之间保持灵活的查询功能。在本文中,我们升级了一种具有概率建模和变换不变特征学习功能的 AM 数据库,并将其称为概率 AM 数据库(PAMDB)。PAMDB 允许选择任何键作为查询键,甚至多个键作为查询键,以检索其他键的值,这适应于未见、高维和多模态 AM 数据。针对激光粉末床熔融(LPBF)和大桶光聚合(VP)进行了两个案例研究。与现有方法相比,实验结果凸显了 PAMDB 在定性和定量方面的功效,包括 LPBF 中熔池尺寸预测和扫描参数估计,以及 VP 中树脂沉积过程的缺陷检测。
{"title":"A Flexible and Accurate Additive Manufacturing Data Retrieval Method based on Probabilistic Modeling and Transformation-Invariant Feature Learning","authors":"Qihang Fang, Gang Xiong, Weixing Wang, Zhen Shen, Xisong Dong, Fei-Yue Wang","doi":"10.1115/1.4065344","DOIUrl":"https://doi.org/10.1115/1.4065344","url":null,"abstract":"\u0000 Additive manufacturing (AM) is gaining prominence across numerous fields, which involves the generation of extensive data at each process stage. A relational database is a useful tool to store such AM data in a key-value manner and streamline data retrieval. Users can specify the value of one AM variable or key and retrieve the corresponding record values of another key. This establishes the correlations between AM variables, and supports applications such as process planning. Nonetheless, such an operation is a “hard” query, which lacks reasoning capabilities and fails to provide useful information when required records are missing. It is urgent to develop a more powerful AM database to handle AM data better, which should support “soft” queries, be scalable to high-dimensional data, and maintain flexible query functionality among multiple keys. In this paper, we upgrade an AM database with probabilistic modeling and transformation-invariant feature learning, which is termed as a probabilistic AM database (PAMDB). The PAMDB allows the selection of any key as a query key, or even multiple keys as query keys, to retrieve the values of other keys, which is adapted to unseen, high-dimensional, and multi-modal AM data. Two case studies were conducted for laser powder bed fusion (LPBF) and vat photopolymerization (VP). Compared with existing methods, experimental results underscore the efficacy of the PAMDBs, both qualitatively and quantitatively, in tasks that includes melt pool size prediction and scan parameter estimation in LPBF, and defect detection for the resin deposition process in VP.","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":"140694066","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}