Pub Date : 2023-10-04DOI: 10.1080/24725854.2023.2266488
Xin Zan, Jaclyn Hall, Tom Hladish, Xiaochen Xian
AbstractSince 2002 with the SARS outbreak, infectious diseases, including the ongoing COVID-19 pandemic, have continued to be a major global public health threat. It is critical to develop effective data science methods to quickly detect disease outbreaks and contain their rapid globalized spread. However, in practice, limited testing availability, and thus insufficient testing data poses significant challenges in effective analysis and real-time monitoring of infectious diseases, especially during early stages of a novel disease outbreak. To tackle these challenges, this article proposes adaptive testing resource allocation strategies integrated with a physics-informed model to dynamically allocate limited testing resources across different communities. The physics-informed model accounts for transmission dynamics and health disparities, enabling effective health risk assessment despite limited data. By integrating nonstationary Multi-Armed Bandit (MAB) techniques that strike superior balance between exploring the communities with high uncertain risks and exploiting those with high risk levels, the proposed methodology facilitates test allocation to collect high-quality testing data for early outbreak detection. Theoretical analysis is carried out to evaluate the performance of the proposed allocation strategies, ensuring either sublinear or linear dynamic pseudo-regret under regularity assumptions. A comprehensive simulation study is conducted under three transmission scenarios to thoroughly evaluate the proposed methodology.Keywords: data-drivenhealth disparityinfectious diseasesMulti-Armed Bandit (MAB)real-time monitoringresource allocationtransmission dynamicsDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also.
{"title":"Data-driven Adaptive Testing Resource Allocation Strategies for Real-time Monitoring of Infectious Diseases","authors":"Xin Zan, Jaclyn Hall, Tom Hladish, Xiaochen Xian","doi":"10.1080/24725854.2023.2266488","DOIUrl":"https://doi.org/10.1080/24725854.2023.2266488","url":null,"abstract":"AbstractSince 2002 with the SARS outbreak, infectious diseases, including the ongoing COVID-19 pandemic, have continued to be a major global public health threat. It is critical to develop effective data science methods to quickly detect disease outbreaks and contain their rapid globalized spread. However, in practice, limited testing availability, and thus insufficient testing data poses significant challenges in effective analysis and real-time monitoring of infectious diseases, especially during early stages of a novel disease outbreak. To tackle these challenges, this article proposes adaptive testing resource allocation strategies integrated with a physics-informed model to dynamically allocate limited testing resources across different communities. The physics-informed model accounts for transmission dynamics and health disparities, enabling effective health risk assessment despite limited data. By integrating nonstationary Multi-Armed Bandit (MAB) techniques that strike superior balance between exploring the communities with high uncertain risks and exploiting those with high risk levels, the proposed methodology facilitates test allocation to collect high-quality testing data for early outbreak detection. Theoretical analysis is carried out to evaluate the performance of the proposed allocation strategies, ensuring either sublinear or linear dynamic pseudo-regret under regularity assumptions. A comprehensive simulation study is conducted under three transmission scenarios to thoroughly evaluate the proposed methodology.Keywords: data-drivenhealth disparityinfectious diseasesMulti-Armed Bandit (MAB)real-time monitoringresource allocationtransmission dynamicsDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also.","PeriodicalId":56039,"journal":{"name":"IISE Transactions","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135592646","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}
Pub Date : 2023-09-28DOI: 10.1080/24725854.2023.2264889
Adithyaa Karthikeyan, Soham Das, Satish T.S. Bukkapatnam, Ceyhun Eksin
AbstractMany industrial components, especially those realized through 3D printing undergo surface finishing processes, predominantly, in the form of mechanical polishing. The polishing processes for custom components remains manual and iterative. Determination of the polishing endpoints, i.e., when to stop the process to achieve a desired surface finish, remains a major obstacle to process automation and in the cost-effective custom/3D printing process chains. With the motivation to automate the polishing process of 3D printed materials to a desired level of surface smoothness, we propose a dynamic model of surface morphology evolution of 3D printed materials during a polishing process. The dynamic model can account for both material removal and redistribution during the polishing process. In addition, the model accounts for increased material flow due to heat generated during the polishing process. We also provide an initial random surface model that matches the initial surface statistics. We propose an optimization problem for model parameter estimation based on empirical data using KL-divergence and surface roughness as two metrics of the objective. We validate the proposed model using data from polishing of a 3D printed sample. The procedures developed makes the model applicable to other 3D printed materials and polishing processes. We obtain a network formation model as a representation of the surface evolution from the heights and radii of asperities. We use the network connectivity (Fiedler number) as a metric for surface smoothness that can be used to determine whether a desired level of smoothness is reached or not.Keywords: Additive ManufacturingPolishingSurface Morphology EvolutionNetwork FormationDynamic modelsMaterial Removal and Material RedistributionDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Additional informationNotes on contributorsAdithyaa KarthikeyanAdithyaa Karthikeyan is currently a PhD student specializing in Advanced Manufacturing within the Department of Industrial and Systems Engineering, Texas A&M University, USA. He received his B.Tech (Hons) degree in Mechanical Engineering from National Institute of Technology, Tiruchirappalli, India in 2017 and MS degree in Interdisciplinary Engineering from Texas A&M University in 2020. He was a summer intern with Micron Technology Inc. in 2023 with their CMP (Chemical Mechanical Planarization) process development team for semiconductor manufacturing. His research interests include mathematical modelling and data analytics for manufacturing processes and systems.Soham DasSoham Das is a PhD s
{"title":"Statistical and Dynamic Model of Surface Morphology Evolution during Polishing in Additive Manufacturing","authors":"Adithyaa Karthikeyan, Soham Das, Satish T.S. Bukkapatnam, Ceyhun Eksin","doi":"10.1080/24725854.2023.2264889","DOIUrl":"https://doi.org/10.1080/24725854.2023.2264889","url":null,"abstract":"AbstractMany industrial components, especially those realized through 3D printing undergo surface finishing processes, predominantly, in the form of mechanical polishing. The polishing processes for custom components remains manual and iterative. Determination of the polishing endpoints, i.e., when to stop the process to achieve a desired surface finish, remains a major obstacle to process automation and in the cost-effective custom/3D printing process chains. With the motivation to automate the polishing process of 3D printed materials to a desired level of surface smoothness, we propose a dynamic model of surface morphology evolution of 3D printed materials during a polishing process. The dynamic model can account for both material removal and redistribution during the polishing process. In addition, the model accounts for increased material flow due to heat generated during the polishing process. We also provide an initial random surface model that matches the initial surface statistics. We propose an optimization problem for model parameter estimation based on empirical data using KL-divergence and surface roughness as two metrics of the objective. We validate the proposed model using data from polishing of a 3D printed sample. The procedures developed makes the model applicable to other 3D printed materials and polishing processes. We obtain a network formation model as a representation of the surface evolution from the heights and radii of asperities. We use the network connectivity (Fiedler number) as a metric for surface smoothness that can be used to determine whether a desired level of smoothness is reached or not.Keywords: Additive ManufacturingPolishingSurface Morphology EvolutionNetwork FormationDynamic modelsMaterial Removal and Material RedistributionDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Additional informationNotes on contributorsAdithyaa KarthikeyanAdithyaa Karthikeyan is currently a PhD student specializing in Advanced Manufacturing within the Department of Industrial and Systems Engineering, Texas A&M University, USA. He received his B.Tech (Hons) degree in Mechanical Engineering from National Institute of Technology, Tiruchirappalli, India in 2017 and MS degree in Interdisciplinary Engineering from Texas A&M University in 2020. He was a summer intern with Micron Technology Inc. in 2023 with their CMP (Chemical Mechanical Planarization) process development team for semiconductor manufacturing. His research interests include mathematical modelling and data analytics for manufacturing processes and systems.Soham DasSoham Das is a PhD s","PeriodicalId":56039,"journal":{"name":"IISE Transactions","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135387231","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}
Pub Date : 2023-09-27DOI: 10.1080/24725854.2023.2263786
Tsegai O. Yhdego, Hui Wang, Zhibin Yu, Hongmei Chi
AbstractIdentifying printing defects is vital for process certification, especially with evolving printing technologies. However, this task proves challenging, especially for micro-level defects necessitating microscopy, which presents a scalability barrier for manufacturing. To address this challenge, we propose an attribute learning methodology inspired by human learning, which identifies shared attributes among seen and unseen objects. First, it extracts defect class embeddings from an engineering-guided defect ontology. Then, attribute learning identifies the combination of attributes for defect estimation. This approach enables it to recognize previously unseen defects by identifying shared attributes, even those not included in the training dataset. The research formulates a joint optimization problem for learning and fine-tuning class embedding and ontology and solves it by integrating natural language processing, metaheuristics for exploration and exploitation, and stochastic gradient descent. In a case study involving a direct-ink-writing process for creating nanocomposites, this methodology was used to learn new defects not found in the training data using the optimized ontology. Compared to traditional zero-shot learning, this ontology-based approach significantly improves class embedding, outperforming transfer learning in one-shot and two-shot learning scenarios. This research represents an early effort to learn new defect concepts, potentially reducing the need for extensive measurements in defect identification.Keywords: Additive ManufacturingAttribute learningOntologyDefect identificationProcess certificationDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Additional informationNotes on contributorsTsegai O. YhdegoTsegai O. Yhdego is a researcher in Industrial Engineering pursuing a Ph.D. at Florida A&M University. His academic journey includes a BSc. in Electrical and Electronics Engineering (2015) from Eritrea Institute of Technology and an MSc. in Mechatronic Engineering (2019) from The Pan African University Institute for Basic Sciences, Technology and Innovation. His research focuses on developing small-sample machinelearning algorithms, specializing in ontology-based federated learning, emphasizing data security and collaborative machine learning. He has also contributed to the aviation industry, developing ML models to forecast flight delay and delay impact.Hui WangHui Wang is an associate professor of industrial engineering at the Florida A&M University-Florida State University College of Engineering and a member of the HighPerformance Ma
{"title":"Ontology-guided Attribute Learning to Accelerate Certification for Developing New Printing Processes","authors":"Tsegai O. Yhdego, Hui Wang, Zhibin Yu, Hongmei Chi","doi":"10.1080/24725854.2023.2263786","DOIUrl":"https://doi.org/10.1080/24725854.2023.2263786","url":null,"abstract":"AbstractIdentifying printing defects is vital for process certification, especially with evolving printing technologies. However, this task proves challenging, especially for micro-level defects necessitating microscopy, which presents a scalability barrier for manufacturing. To address this challenge, we propose an attribute learning methodology inspired by human learning, which identifies shared attributes among seen and unseen objects. First, it extracts defect class embeddings from an engineering-guided defect ontology. Then, attribute learning identifies the combination of attributes for defect estimation. This approach enables it to recognize previously unseen defects by identifying shared attributes, even those not included in the training dataset. The research formulates a joint optimization problem for learning and fine-tuning class embedding and ontology and solves it by integrating natural language processing, metaheuristics for exploration and exploitation, and stochastic gradient descent. In a case study involving a direct-ink-writing process for creating nanocomposites, this methodology was used to learn new defects not found in the training data using the optimized ontology. Compared to traditional zero-shot learning, this ontology-based approach significantly improves class embedding, outperforming transfer learning in one-shot and two-shot learning scenarios. This research represents an early effort to learn new defect concepts, potentially reducing the need for extensive measurements in defect identification.Keywords: Additive ManufacturingAttribute learningOntologyDefect identificationProcess certificationDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Additional informationNotes on contributorsTsegai O. YhdegoTsegai O. Yhdego is a researcher in Industrial Engineering pursuing a Ph.D. at Florida A&M University. His academic journey includes a BSc. in Electrical and Electronics Engineering (2015) from Eritrea Institute of Technology and an MSc. in Mechatronic Engineering (2019) from The Pan African University Institute for Basic Sciences, Technology and Innovation. His research focuses on developing small-sample machinelearning algorithms, specializing in ontology-based federated learning, emphasizing data security and collaborative machine learning. He has also contributed to the aviation industry, developing ML models to forecast flight delay and delay impact.Hui WangHui Wang is an associate professor of industrial engineering at the Florida A&M University-Florida State University College of Engineering and a member of the HighPerformance Ma","PeriodicalId":56039,"journal":{"name":"IISE Transactions","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135538456","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}
Pub Date : 2023-09-25DOI: 10.1080/24725854.2023.2261569
Sha Chen, Izak Duenyas, Seyed Iravani
AbstractWe study the routing and admission control problem in a parallel queueing system with heterogeneous servers serving multiple types of customers. The system makes admission decision regarding whether to admit a customer upon arrival as well as routing decision of which queue an admitted customer is assigned to. The objective is to maximize the expected profit, which includes customer-dependent revenues and holding cost and server-dependent cost. We first characterize the structure of the optimal policy for the case with two servers and two types of customers that have the same holding cost. We show that the optimal admission and routing policy has a complex non-monotone structure; however, we show that this non-monotone structure is the result of overlapping of three pairwise dominant policies that have a monotone structure. Utilizing the above structure, we propose three heuristics for the general case of multiple servers and multiple types of customers. Through a numerical study, we demonstrate the effectiveness of our heuristics, and provide conditions under which each heuristic performs well. Lastly, we provide insights on the effect of holding cost on customer rejection and the effect of fixed production cost on capacity allocation.Keywords: Routing controladmission controlMarkov decision processparallel queuesDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Acknowledgement:
{"title":"Admission and Routing Control of Multiple Queues with Multiple Types of Customers","authors":"Sha Chen, Izak Duenyas, Seyed Iravani","doi":"10.1080/24725854.2023.2261569","DOIUrl":"https://doi.org/10.1080/24725854.2023.2261569","url":null,"abstract":"AbstractWe study the routing and admission control problem in a parallel queueing system with heterogeneous servers serving multiple types of customers. The system makes admission decision regarding whether to admit a customer upon arrival as well as routing decision of which queue an admitted customer is assigned to. The objective is to maximize the expected profit, which includes customer-dependent revenues and holding cost and server-dependent cost. We first characterize the structure of the optimal policy for the case with two servers and two types of customers that have the same holding cost. We show that the optimal admission and routing policy has a complex non-monotone structure; however, we show that this non-monotone structure is the result of overlapping of three pairwise dominant policies that have a monotone structure. Utilizing the above structure, we propose three heuristics for the general case of multiple servers and multiple types of customers. Through a numerical study, we demonstrate the effectiveness of our heuristics, and provide conditions under which each heuristic performs well. Lastly, we provide insights on the effect of holding cost on customer rejection and the effect of fixed production cost on capacity allocation.Keywords: Routing controladmission controlMarkov decision processparallel queuesDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Acknowledgement:","PeriodicalId":56039,"journal":{"name":"IISE Transactions","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135770361","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}
Pub Date : 2023-09-25DOI: 10.1080/24725854.2023.2261507
Majid Akhgar, Juan S. Borrero
AbstractWe introduce the Influence Coverage Optimization Problem (ICOP), which is an influence maximization problem where the activation of nodes also depends on their location on the plane. Specifically, the ICOP assumes that there is a network where nodes become active (i.e., influenced) either by the influence they receive from interactions with active in-neighbors or by entering the coverage area of a physical ad or a Geo-fence. The objective is to locate a fixed number of ads or Geo-fences and modify the network influence rates to minimize the network activation time. Assuming a Markovian influence model, we prove that the ICOP is NP-hard, and then we present MIP formulations for three different types of coverage modes. A reformulation of the non-linear ‘big-M’ constraints, two types of valid cuts, and a fast heuristic based on the k-means algorithm are used as enhancements that facilitate solving the ICOP via an Iterative Decomposition Branch-and-Cut (IDBC) algorithm. In addition, we present an alternative discrete formulation of the ICOP using critical intersection points. Several experiments under various parameter configurations across instances with more than a hundred nodes and thousand arcs are conducted, showing the IDBC’s capability to provide optimal solutions within seconds or minutes for most instances. Moreover, the experiments reveal that the ICOP can significantly outperform a Geo-fence coverage model that does not consider network interactions to make location decisions.Keywords: Influence maximizationsocial networksmaximum coveragecritical intersection pointsbranch-and-cutDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. AcknowledgementsThis research is partially funded by the National Science Foundation (NSF) (Award ENG/CMMI # 2145553), by the Air Force Office of Scientific Research (AFORS) (Award # FA9550-22-1-0236), and the Office of Naval Research (ONR) (Award # N00014-19-1-2329).
{"title":"The Influence Coverage Optimization Problem","authors":"Majid Akhgar, Juan S. Borrero","doi":"10.1080/24725854.2023.2261507","DOIUrl":"https://doi.org/10.1080/24725854.2023.2261507","url":null,"abstract":"AbstractWe introduce the Influence Coverage Optimization Problem (ICOP), which is an influence maximization problem where the activation of nodes also depends on their location on the plane. Specifically, the ICOP assumes that there is a network where nodes become active (i.e., influenced) either by the influence they receive from interactions with active in-neighbors or by entering the coverage area of a physical ad or a Geo-fence. The objective is to locate a fixed number of ads or Geo-fences and modify the network influence rates to minimize the network activation time. Assuming a Markovian influence model, we prove that the ICOP is NP-hard, and then we present MIP formulations for three different types of coverage modes. A reformulation of the non-linear ‘big-M’ constraints, two types of valid cuts, and a fast heuristic based on the k-means algorithm are used as enhancements that facilitate solving the ICOP via an Iterative Decomposition Branch-and-Cut (IDBC) algorithm. In addition, we present an alternative discrete formulation of the ICOP using critical intersection points. Several experiments under various parameter configurations across instances with more than a hundred nodes and thousand arcs are conducted, showing the IDBC’s capability to provide optimal solutions within seconds or minutes for most instances. Moreover, the experiments reveal that the ICOP can significantly outperform a Geo-fence coverage model that does not consider network interactions to make location decisions.Keywords: Influence maximizationsocial networksmaximum coveragecritical intersection pointsbranch-and-cutDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. AcknowledgementsThis research is partially funded by the National Science Foundation (NSF) (Award ENG/CMMI # 2145553), by the Air Force Office of Scientific Research (AFORS) (Award # FA9550-22-1-0236), and the Office of Naval Research (ONR) (Award # N00014-19-1-2329).","PeriodicalId":56039,"journal":{"name":"IISE Transactions","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135816546","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}
Pub Date : 2023-09-19DOI: 10.1080/24725854.2023.2261028
Barry L. Nelson
AbstractComputer simulation has been in the toolkit of industrial engineers for over fifty years and its value has been enhanced by advances in research, including both modeling and analysis, and in application software, both commercial and open source. However, “advances” are different from paradigm shifts. Motivated by big data, big computing and the big consequences of model-based decisions, it is time to reboot simulation for industrial engineering.Keywords: Systems simulationbig datahigh-performance computingsystem of systemsDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Additional informationNotes on contributorsBarry L. NelsonBarry L. Nelson is the Walter P. Murphy Professor Emeritus of the Department of Industrial Engineering and Management Sciences at Northwestern. His research focus is the design and analysis of computer simulation experiments on models of discrete-event, stochastic systems, including methodology for simulation optimization, quantifying and reducing model risk, variance reduction, output analysis, metamodeling and multivariate input modeling. He has published numerous papers and three books, including Foundations and Methods of Stochastic Simulation: A First Course (second edition, Springer, 2021). Nelson is a Fellow of INFORMS and IISE. Further information can be found at www.iems.northwestern.edu/∼nelsonb/.Barry L. Nelson is the Walter P. Murphy Professor Emeritus of the Department of Industrial Engineering and Management Sciences at Northwestern. His research focus is the design and analysis of computer simulation experiments on models of discrete-event, stochastic systems, including methodology for simulation optimization, quantifying and reducing model risk, variance reduction, output analysis, metamodeling and multivariate input modeling. His application areas are manufacturing, services, financial engineering, renewable energy generation and transportation. He has published numerous papers and three books, including Foundations and Methods of Stochastic Simulation: A First Course (second edition Springer, 2021). Nelson is a Fellow of INFORMS and IISE. In 2006, 2013 and 2015 he received the Outstanding Simulation Publication Award from the INFORMS Simulation Society; in 2009, 2011 and 2015 he was awarded the Best Paper–Operations Award from IIE Transactions; in 2019 he received the David F. Baker Distinguished Research Award from IISE; and in 2022 he received the Lifetime Professional Achievement Award from the INFORMS Simulation Society. His teaching has been acknowledged by a Northwestern University Alumni Association Excelle
50多年来，计算机仿真一直是工业工程师的工具包，其价值随着研究的进步而得到提高，包括建模和分析，以及商业和开源的应用软件。然而，“进步”不同于范式转换。在大数据、大计算和基于模型的决策的巨大影响的推动下，是时候重新启动工业工程的仿真了。关键词:系统仿真大数据高性能计算系统免责声明作为对作者和研究人员的服务，我们提供此版本的接受稿件(AM)在最终出版版本记录(VoR)之前，将对该手稿进行编辑、排版和审查。在制作和印前，可能会发现可能影响内容的错误，所有适用于期刊的法律免责声明也与这些版本有关。barry L. Nelson是西北大学工业工程与管理科学系的Walter P. Murphy名誉教授。他的研究重点是设计和分析离散事件随机系统模型的计算机模拟实验，包括模拟优化方法、量化和降低模型风险、方差减少、输出分析、元建模和多变量输入建模。他发表了许多论文和三本书，包括随机模拟的基础和方法:第一课程(第二版，施普林格，2021年)。尼尔森是INFORMS和IISE的研究员。欲了解更多信息，请访问www.iems.northwestern.edu/∼nelsonb/。barry L. Nelson是西北大学工业工程与管理科学系Walter P. Murphy名誉教授。他的研究重点是设计和分析离散事件随机系统模型的计算机模拟实验，包括模拟优化方法、量化和降低模型风险、方差减少、输出分析、元建模和多变量输入建模。他的应用领域包括制造业、服务业、金融工程、可再生能源发电和交通运输。他发表了许多论文和三本书，包括随机模拟的基础和方法:第一课程(第二版施普林格，2021年)。尼尔森是INFORMS和IISE的研究员。2006年、2013年和2015年，他获得了INFORMS仿真学会颁发的杰出仿真出版物奖;2009年、2011年和2015年，他被IIE Transactions授予最佳纸张操作奖;2019年，他获得了IISE颁发的David F. Baker杰出研究奖;2022年，他获得了INFORMS仿真学会颁发的终身专业成就奖。他的教学获得了西北大学校友会卓越教学奖、麦考密克工程与应用科学学院年度教师奖(两次)、IISE运筹学部和IISE仿真与建模部的卓越教学奖。更多信息请访问:www.iems.northwestern.edu/∼nelsonb/。
{"title":"Rebooting Simulation","authors":"Barry L. Nelson","doi":"10.1080/24725854.2023.2261028","DOIUrl":"https://doi.org/10.1080/24725854.2023.2261028","url":null,"abstract":"AbstractComputer simulation has been in the toolkit of industrial engineers for over fifty years and its value has been enhanced by advances in research, including both modeling and analysis, and in application software, both commercial and open source. However, “advances” are different from paradigm shifts. Motivated by big data, big computing and the big consequences of model-based decisions, it is time to reboot simulation for industrial engineering.Keywords: Systems simulationbig datahigh-performance computingsystem of systemsDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Additional informationNotes on contributorsBarry L. NelsonBarry L. Nelson is the Walter P. Murphy Professor Emeritus of the Department of Industrial Engineering and Management Sciences at Northwestern. His research focus is the design and analysis of computer simulation experiments on models of discrete-event, stochastic systems, including methodology for simulation optimization, quantifying and reducing model risk, variance reduction, output analysis, metamodeling and multivariate input modeling. He has published numerous papers and three books, including Foundations and Methods of Stochastic Simulation: A First Course (second edition, Springer, 2021). Nelson is a Fellow of INFORMS and IISE. Further information can be found at www.iems.northwestern.edu/∼nelsonb/.Barry L. Nelson is the Walter P. Murphy Professor Emeritus of the Department of Industrial Engineering and Management Sciences at Northwestern. His research focus is the design and analysis of computer simulation experiments on models of discrete-event, stochastic systems, including methodology for simulation optimization, quantifying and reducing model risk, variance reduction, output analysis, metamodeling and multivariate input modeling. His application areas are manufacturing, services, financial engineering, renewable energy generation and transportation. He has published numerous papers and three books, including Foundations and Methods of Stochastic Simulation: A First Course (second edition Springer, 2021). Nelson is a Fellow of INFORMS and IISE. In 2006, 2013 and 2015 he received the Outstanding Simulation Publication Award from the INFORMS Simulation Society; in 2009, 2011 and 2015 he was awarded the Best Paper–Operations Award from IIE Transactions; in 2019 he received the David F. Baker Distinguished Research Award from IISE; and in 2022 he received the Lifetime Professional Achievement Award from the INFORMS Simulation Society. His teaching has been acknowledged by a Northwestern University Alumni Association Excelle","PeriodicalId":56039,"journal":{"name":"IISE Transactions","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135059674","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}
Pub Date : 2023-09-15DOI: 10.1080/24725854.2023.2259949
Yiming Chen, Yu Liu, Tangfan Xiahou
AbstractInspection and maintenance activities are effective ways to reveal and restore the health conditions of many industrial systems, respectively. Most extant works on inspection and maintenance optimization problems assumed that systems operate under a time-invariant demand. Such a simplified assumption is oftentimes violated by a changeable market environment, seasonal factors, and even unexpected emergencies. In this article, with the aim of minimizing the expected total cost associated with inspections, maintenance, and unsupplied demand, a dynamic inspection and maintenance scheduling model is put forth for multi-state systems (MSSs) under a time-varying demand. Non-periodic inspections are performed on the components of an MSS and imperfect maintenance actions are dynamically scheduled based on the inspection results. By introducing the concept of decision epochs, the resulting inspection and maintenance scheduling problem is formulated as a Markov decision process (MDP). The deep reinforcement learning (DRL) method with a proximal policy optimization (PPO) algorithm is customized to cope with the “curse of dimensionality” of the resulting sequential decision problem. As an extra input feature for the agent, the category of decision epochs is formulated to improve the effectiveness of the customized DRL method. A six-component MSS, along with a multi-state coal transportation system, is given to demonstrate the effectiveness of the proposed method.Keywords: multi-state systemdeep reinforcement learningdynamic inspection and maintenance schedulingproximal policy optimizationtime-varying demandDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Additional informationNotes on contributorsYiming ChenYiming Chen received the Ph.D. degrees in mechanical engineering from the University of Electronic Science and Technology of China in 2022. He is currently a Lecturer with the College of Marine Equipment and Mechanical Engineering, Jimei University. His research interests include maintenance decisions, stochastic dynamic programming, and deep reinforcement learning.Yu LiuYu Liu is a professor of industrial engineering with the School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China. He received a PhD degree from the University of Electronic Science and Technology of China in 2010. He was a Visiting Predoctoral Fellow with the Department of Mechanical Engineering, Northwestern University, USA, from 2008 to 2010 and a Postdoctoral Research Fellow with the Department of Mechanical Engineering, University of Alberta, C
{"title":"Dynamic Inspection and Maintenance Scheduling for Multi-State Systems Under Time-Varying Demand: Proximal Policy Optimization","authors":"Yiming Chen, Yu Liu, Tangfan Xiahou","doi":"10.1080/24725854.2023.2259949","DOIUrl":"https://doi.org/10.1080/24725854.2023.2259949","url":null,"abstract":"AbstractInspection and maintenance activities are effective ways to reveal and restore the health conditions of many industrial systems, respectively. Most extant works on inspection and maintenance optimization problems assumed that systems operate under a time-invariant demand. Such a simplified assumption is oftentimes violated by a changeable market environment, seasonal factors, and even unexpected emergencies. In this article, with the aim of minimizing the expected total cost associated with inspections, maintenance, and unsupplied demand, a dynamic inspection and maintenance scheduling model is put forth for multi-state systems (MSSs) under a time-varying demand. Non-periodic inspections are performed on the components of an MSS and imperfect maintenance actions are dynamically scheduled based on the inspection results. By introducing the concept of decision epochs, the resulting inspection and maintenance scheduling problem is formulated as a Markov decision process (MDP). The deep reinforcement learning (DRL) method with a proximal policy optimization (PPO) algorithm is customized to cope with the “curse of dimensionality” of the resulting sequential decision problem. As an extra input feature for the agent, the category of decision epochs is formulated to improve the effectiveness of the customized DRL method. A six-component MSS, along with a multi-state coal transportation system, is given to demonstrate the effectiveness of the proposed method.Keywords: multi-state systemdeep reinforcement learningdynamic inspection and maintenance schedulingproximal policy optimizationtime-varying demandDisclaimerAs a service to authors and researchers we are providing this version of an accepted manuscript (AM). Copyediting, typesetting, and review of the resulting proofs will be undertaken on this manuscript before final publication of the Version of Record (VoR). During production and pre-press, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal relate to these versions also. Additional informationNotes on contributorsYiming ChenYiming Chen received the Ph.D. degrees in mechanical engineering from the University of Electronic Science and Technology of China in 2022. He is currently a Lecturer with the College of Marine Equipment and Mechanical Engineering, Jimei University. His research interests include maintenance decisions, stochastic dynamic programming, and deep reinforcement learning.Yu LiuYu Liu is a professor of industrial engineering with the School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China. He received a PhD degree from the University of Electronic Science and Technology of China in 2010. He was a Visiting Predoctoral Fellow with the Department of Mechanical Engineering, Northwestern University, USA, from 2008 to 2010 and a Postdoctoral Research Fellow with the Department of Mechanical Engineering, University of Alberta, C","PeriodicalId":56039,"journal":{"name":"IISE Transactions","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135397256","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}
Pub Date : 2023-09-11DOI: 10.1080/24725854.2023.2257245
Ragnar Eggertsson, Rob Basten, Geert-Jan van Houtum
–We study the problem of inspection and maintenance planning of capital goods based on observations of the capital good’s degradation state. However, the observations are imprecise, and their quality depends on the environment. For example, when performing maintenance for heating, ventilation, and air-conditioning units (HVACs) in trains, the health of the cooling component of an HVAC can be assessed from temperature readouts of the car in which the HVAC is mounted. Temperature information is useful in the summer when high car temperatures can indicate a failed cooling component, but this information has limited value during the winter. We model the problem as a partially observable Markov decision process with a fully observed environment. We analytically show that an environment-dependent monotonic at-most-4-region policy is optimal. Furthermore, we numerically analyze an example motivated by HVAC maintenance at Dutch Railways. This analysis shows that, in many cases, including the environment in the model can lead to cost savings of more than 10%. In a broad numerical experiment, we show that a simple policy cannot always substitute an optimal policy.
{"title":"Maintenance optimization for capital goods when information is incomplete and environment-dependent","authors":"Ragnar Eggertsson, Rob Basten, Geert-Jan van Houtum","doi":"10.1080/24725854.2023.2257245","DOIUrl":"https://doi.org/10.1080/24725854.2023.2257245","url":null,"abstract":"–We study the problem of inspection and maintenance planning of capital goods based on observations of the capital good’s degradation state. However, the observations are imprecise, and their quality depends on the environment. For example, when performing maintenance for heating, ventilation, and air-conditioning units (HVACs) in trains, the health of the cooling component of an HVAC can be assessed from temperature readouts of the car in which the HVAC is mounted. Temperature information is useful in the summer when high car temperatures can indicate a failed cooling component, but this information has limited value during the winter. We model the problem as a partially observable Markov decision process with a fully observed environment. We analytically show that an environment-dependent monotonic at-most-4-region policy is optimal. Furthermore, we numerically analyze an example motivated by HVAC maintenance at Dutch Railways. This analysis shows that, in many cases, including the environment in the model can lead to cost savings of more than 10%. In a broad numerical experiment, we show that a simple policy cannot always substitute an optimal policy.","PeriodicalId":56039,"journal":{"name":"IISE Transactions","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135938019","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}
Pub Date : 2023-09-11DOI: 10.1080/24725854.2023.2257255
Fabio Caltanissetta, Luisa Bertoli, Bianca Maria Colosimo
AbstractThe amount of attention paid to in-situ monitoring in Additive Manufacturing (AM) has significantly increased over the last few years, paving the way to a paradigm shift for quality monitoring and control via big data analysis of signals, images, and videos. In-situ quality monitoring represents an opportunity for waste reduction and first-time-right production via inline detection of process flaws, which allows early identification of scraps and the possibility of correcting actions for first-time-right production. This article presents a solution for in-situ monitoring of images taken layerwise in material extrusion AM. Compared with the existing solutions, mainly focusing on monitoring the shape deviation observed at each layer with respect to the nominal shape, this article focuses on monitoring the internal surface texture with the aim of detecting over- and under-extrusion flaws. Inspired by an approach reported in the literature that was developed for textile image monitoring, we propose a solution for in-situ monitoring of textured surfaces which is based on combining Random Forests with clustering to automatically identify defective locations layerwise. A real case study based on Fused Filament Fabrication is used to compare the performance of the novel proposed solution with the original one and identify an appropriate direction for future research.Keywords: Statistical quality monitoringin-situ monitoringimagerandom forestsclusteringadditive manufacturing Data availabilityThe data that support the findings of this study are openly available in figshare at https://doi.org/10.6084/m9.figshare.24042891.v1.Additional informationFundingThe present research was partially funded by ACCORDO Quadro ASI-POLIMI “Attività di Ricerca e Innovazione” n. 2018-5-HH.0, collaboration agreement between the Italian Space Agency and Politecnico di Milano.Notes on contributorsFabio CaltanissettaFabio Caltanissetta received his doctoral degree in industrial engineering from Politecnico di Milano (while completing this research work), after completing an MSc in industrial engineering at the same university. He is currently a Process R&D Specialist at Caracol AM.Luisa BertoliLaura Bertoli completed a Master of Science in industrial engineering at Politecnico di Milano, Italy (while completing this research work). She is currently a business data product specialist at UniCredit.Bianca Maria ColosimoBianca Maria Colosimo is a professor in the Department of Mechanical Engineering of Politecnico di Milano. Her research interest is mainly in the area of big data mining for Industry 4.0, with special focus on advanced manufacturing. She is currently a department editor of IISE Transactions, senior editor of Informs Journal of Data Science, associate editor of Progress in Additive Manufacturing and Additive Manufacturing Letters. She has been editor-in-chief of the Journal of Quality Technology (2018-2021). She is included among the top 100 Italian woman scien
摘要在过去几年中，对增材制造(AM)现场监测的关注程度显著增加，为通过信号、图像和视频的大数据分析进行质量监测和控制的范式转变铺平了道路。通过在线检测工艺缺陷，现场质量监测为减少浪费和第一次正确生产提供了机会，这可以早期识别废料，并为第一次正确生产提供纠正措施的可能性。本文提出了一种材料挤压增材制造分层图像的现场监测方案。与现有的解决方案主要关注于监测每层观察到的形状相对于标称形状的偏差相比，本文主要关注于监测内部表面纹理，目的是检测过度和欠挤压缺陷。受文献报道的纺织品图像监测方法的启发，我们提出了一种基于随机森林和聚类相结合的纹理表面原位监测解决方案，以分层自动识别缺陷位置。通过一个基于熔丝制造的实际案例研究，比较了新提出的解决方案与原始解决方案的性能，并确定了未来研究的合适方向。关键词:统计质量监测原位监测图像随机森林聚类增材制造数据可用性支持本研究结果的数据可公开获取，共享网址:https://doi.org/10.6084/m9.figshare.24042891.v1.Additional information资助本研究部分由ACCORDO Quadro ASI-POLIMI“atitivitondi Ricerca e Innovazione”资助，2018-5-HH。意大利航天局与米兰理工大学之间的合作协议。fabio Caltanissetta在米兰理工大学获得工业工程硕士学位后，获得了工业工程博士学位(同时完成了这项研究工作)。他目前是Caracol AM的工艺研发专家。Luisa BertoliLaura Bertoli在意大利米兰理工大学(Politecnico di Milano)获得工业工程硕士学位(同时完成了这项研究工作)。她目前是UniCredit的商业数据产品专家。Bianca Maria Colosimo是米兰理工大学机械工程系的教授。主要研究方向为面向工业4.0的大数据挖掘，重点关注先进制造业。她目前是IISE Transactions的部门编辑，Informs Journal of Data Science的高级编辑，《增材制造进展》和《增材制造快报》的副主编。她曾担任Journal of Quality Technology(2018-2021)主编。她被列入意大利STEM领域前100名女科学家之一
{"title":"In-situ monitoring of image texturing via random forests and clustering with applications to additive manufacturing","authors":"Fabio Caltanissetta, Luisa Bertoli, Bianca Maria Colosimo","doi":"10.1080/24725854.2023.2257255","DOIUrl":"https://doi.org/10.1080/24725854.2023.2257255","url":null,"abstract":"AbstractThe amount of attention paid to in-situ monitoring in Additive Manufacturing (AM) has significantly increased over the last few years, paving the way to a paradigm shift for quality monitoring and control via big data analysis of signals, images, and videos. In-situ quality monitoring represents an opportunity for waste reduction and first-time-right production via inline detection of process flaws, which allows early identification of scraps and the possibility of correcting actions for first-time-right production. This article presents a solution for in-situ monitoring of images taken layerwise in material extrusion AM. Compared with the existing solutions, mainly focusing on monitoring the shape deviation observed at each layer with respect to the nominal shape, this article focuses on monitoring the internal surface texture with the aim of detecting over- and under-extrusion flaws. Inspired by an approach reported in the literature that was developed for textile image monitoring, we propose a solution for in-situ monitoring of textured surfaces which is based on combining Random Forests with clustering to automatically identify defective locations layerwise. A real case study based on Fused Filament Fabrication is used to compare the performance of the novel proposed solution with the original one and identify an appropriate direction for future research.Keywords: Statistical quality monitoringin-situ monitoringimagerandom forestsclusteringadditive manufacturing Data availabilityThe data that support the findings of this study are openly available in figshare at https://doi.org/10.6084/m9.figshare.24042891.v1.Additional informationFundingThe present research was partially funded by ACCORDO Quadro ASI-POLIMI “Attività di Ricerca e Innovazione” n. 2018-5-HH.0, collaboration agreement between the Italian Space Agency and Politecnico di Milano.Notes on contributorsFabio CaltanissettaFabio Caltanissetta received his doctoral degree in industrial engineering from Politecnico di Milano (while completing this research work), after completing an MSc in industrial engineering at the same university. He is currently a Process R&D Specialist at Caracol AM.Luisa BertoliLaura Bertoli completed a Master of Science in industrial engineering at Politecnico di Milano, Italy (while completing this research work). She is currently a business data product specialist at UniCredit.Bianca Maria ColosimoBianca Maria Colosimo is a professor in the Department of Mechanical Engineering of Politecnico di Milano. Her research interest is mainly in the area of big data mining for Industry 4.0, with special focus on advanced manufacturing. She is currently a department editor of IISE Transactions, senior editor of Informs Journal of Data Science, associate editor of Progress in Additive Manufacturing and Additive Manufacturing Letters. She has been editor-in-chief of the Journal of Quality Technology (2018-2021). She is included among the top 100 Italian woman scien","PeriodicalId":56039,"journal":{"name":"IISE Transactions","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135983331","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：