CAREER: Infrastructure Management under Model Uncertainty: Adaptive Sequential Learning and Decision Making
CAREER: Infrastructure Management under Model Uncertainty: Adaptive Sequential Learning and Decision Making
批准号:
1653716
负责人:
Matteo Pozzi
金额:
$50.0万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2017
资助国家:
美国
项目状态:
已结题
起止时间:
2017-03-15 至 2022-02-28
中文摘要
包括运输和能源系统在内的互联基础设施的维护和运行对于向社会提供足够的安全性和功能性至关重要。对于老化的基础设施,必须在其组件的当前状态、演变和维护行动的结果的高度不确定性下做出关键决策。随着传感器、机器人检查员、通信和计算变得更便宜、更可靠,它们的使用可以集成到基础设施管理中,以改善维护政策,减少不确定性、风险和整体管理成本。充分利用这一潜力需要改变我们如何建模和处理基础设施决策的范式,以及如何在管理基础设施系统的统计推断和顺序优化中采用和扩展新的计算方法。该CAREER奖通过开发先进的模型和算法,利用传感器部署、概率推理和维护和操作决策之间的相互依赖性,最终提高维护和操作目的的决策能力,降低成本。该研究将与管理系统和开发软件的公司合作,在三个案例研究中测试开发的框架,包括风力发电场、天然气管道网络和桥梁网络。支持项目研究的相同框架也形成了基于主动、情境学习活动的基础设施管理教学方法的基础,其中将开发游戏,让K-12和大学生在互动环境中扮演虚拟基础设施管理人员的角色。PI将与卡耐基梅隆大学的女生暑期工程经验项目密切合作,以激发对风险分析和基础设施系统决策的兴趣。该项目的目标是在持续模型不确定性下开发可扩展的长期决策算法。这些算法将不仅针对基础设施系统的操作和维护决策,还将针对进一步信息的收集决策:放置传感器、安排检查、计划测试以及试验新的操作和传感技术。通过学习和行动的连续迭代,管理者可以自适应地优化资源配置。当专注于大型互联系统时,优化变得更加复杂,但回报更高:当许多基础设施组件在统计上相互依赖时,由于空间接近、共同的压力源或共同的动态模型,信息可以在它们之间传播。这使得在一个地方收集的观测结果也可以用于推断其他地方的条件,更重要的是,推断更高层次的系统演化模型。通过确定值得检查的位置和组件,代理可以依次适应系统的探索,避免昂贵的过度仪器,并指导管理层可持续地利用有限的资源。为了开发这些方法,本项目将利用贝叶斯分层建模、随机场建模、预后验和信息值分析、子模块化分析、部分可观察马尔可夫决策过程(POMDP)的近似动态规划、在线优化和网络分析。
英文摘要
Maintenance and operation of interconnected infrastructures, including transportation and energy systems, are critical to provide adequate levels of safety and functionality to society. Critical decisions must be made about aging infrastructures under high uncertainty about the current condition of their components, their evolution, and the results of maintenance actions. As sensors, robotic inspectors, communication and computation become cheaper and more reliable, their use can be integrated into infrastructure management to improve maintenance policies and reduce uncertainty, risk and overall management cost. Full exploitation of this potential requires a change in paradigm in how we model and approach infrastructure decision making, and how novel computational methods may be adopted and extended in statistical inference and sequential optimization for managing infrastructure systems. This CAREER award exploits the interdependency among sensor deployment, probabilistic inference and decision making on maintenance and operation by developing advanced models and algorithms that would ultimately result in enhanced decision making for maintenance and operation purposes and reduced costs. The research will test the developed framework on three case studies including wind farms, networks of gas pipelines, and networks of bridges, in collaboration with companies that manage systems and develop software. The same framework underpinning the project research also forms the basis for a pedagogic approach on infrastructure management based on active, situated-learning activities, in which games will be developed to involve K-12 and college students with assigned roles as virtual infrastructure managers in an interactive environment. The PI will work closely with Carnegie Mellon's SEE (Summer Engineering Experience for Girls) program to inspire interest in risk analysis and infrastructure systems decision making. This project's goal is to develop scalable algorithms for long-term decision-making under persistent model uncertainty. These algorithms will target decisions about not only operation and maintenance of infrastructure systems, but also about the gathering of further information: placing sensors, scheduling inspections, planning tests and experimenting with new technologies for operation and sensing. By sequential iterations of learning and acting, managers can adaptively optimize resource allocation. Optimization becomes more complex, but with higher pay-off, when focusing on large interconnected systems: when numerous infrastructure components are statistically interdependent, because of spatial proximity, common stressors, or common dynamic models, information can propagate across them. This allows observations collected in one location to also be useful for inferring the conditions of others and, more importantly, the higher-level system evolution model. By identifying locations and components that deserve inspections, the agent can sequentially adapt the exploration of the system, avoid costly over-instrumentation, and guide management towards a sustainable use of the limited resources. To develop these approaches, this project will make use of Bayesian hierarchical modeling, random field modeling, pre-posterior and value-of-information analysis, sub-modularity analysis, approximate dynamic programming for Partially Observable Markov Decision Processes (POMDP), on-line optimization and network analysis.
期刊论文(7)
专著(0)
科研奖励(0)
会议论文
登录
查看更多内容
DOI:
10.1177/1748006x211020151
发表时间:
2021
期刊:
Part O: Journal of Risk and Reliability
影响因子:
--
作者:
[Lin, Chaochao, Pozzi, Matteo]
通讯作者:
Pozzi, Matteo
Submodularity issues in value-of-information-based sensor placement
基于信息值的传感器放置中的子模块化问题
DOI:
10.1016/j.ress.2018.11.010
发表时间:
2019
期刊:
Reliability Engineering & System Safety
影响因子:
8.1
作者:
[Malings, C., Pozzi, M.]
通讯作者:
Pozzi, M.
Optimal inspection of binary systems via value of information analysis
通过信息分析的价值对二元系统进行优化检查
DOI:
10.1016/j.ress.2021.107944
发表时间:
2021
期刊:
Reliability engineering systems safety
影响因子:
--
作者:
[Chaochao Lin, Junho Song]
通讯作者:
Chaochao Lin, Junho Song
DOI:
10.1002/stc.2329
发表时间:
2019
期刊:
Structural Control and Health Monitoring
影响因子:
5.4
作者:
[Li, Shuo, Pozzi, Matteo]
通讯作者:
Pozzi, Matteo
DOI:
10.1007/s12205-018-0014-x
发表时间:
2018-03
期刊:
KSCE Journal of Civil Engineering
影响因子:
2.2
作者:
[M. Pozzi;Qiaochu Wang]
通讯作者:
M. Pozzi;Qiaochu Wang
共 7 条
Attitude towards information in multi-agent settings: Understanding and mitigating Avoidance and Over-Evaluation
-
批准号:1919453
-
项目类别:Continuing Grant
-
资助金额:$50.0万
-
财政年份:2019
-
负责人:Matteo Pozzi
-
依托单位:
From Future Learning To Current Action: Long-Term Sequential Infrastructure Planning Under Uncertainty
-
批准号:1663479
-
项目类别:Standard Grant
-
资助金额:$55.0万
-
财政年份:2017
-
负责人:Matteo Pozzi
-
依托单位:
PREEVENTS Track 2: Collaborative Research: SHADE: Surface Heat Assessment for Developed Environments
-
批准号:1664091
-
项目类别:Continuing Grant
-
资助金额:$51.5万
-
财政年份:2017
-
负责人:Matteo Pozzi
-
依托单位:
CRISP Type 1/Collaborative Research: A Computational Approach for Integrated Network Resilience Analysis Under Extreme Events for Financial and Physical Infrastructures
-
批准号:1638327
-
项目类别:Standard Grant
-
资助金额:$35.0万
-
财政年份:2016
-
负责人:Matteo Pozzi
-
依托单位:
海外基金