全英文课程“复杂工业系统的诊断、预测和健康监测”开课通知
发布时间:2019年07月01日 10:02 作者: 点击量:

加拿大康考迪亚大学(Concordia University, Montreal, Canada)电气和计算机工程系K. Khorasani教授,应澳门新萄京网址3522邀请来我校从事教学和研究工作,计划于近期讲授“复杂工业系统的诊断、预测和健康监测课程”全英文课程,欢迎广大研究生和高年级本科生学习。

课程名称

复杂工业系统的诊断、预测和健康监测课程

Lectures on Diagnosis, Prognosis, and Health Monitoring of Complex Industrial Systems

联系人:澳门新萄京网址3522  郭迎清  教授

联系方式:yqguo@nwpu.edu.cn

 

 

课程简介

燃气涡轮机,航空航天系统,运输系统等工业系统日益复杂,制造商和维护人员对降低成本的迫切需求推动了诊断、预测和健康管理(DPHM)系统向着更加智能以及自主能力更强的方向发展。在运营成本中维护成本占比重较大,大多数工业系统当前采用预防性的维护策略,即按制造商建议的时间表实施维护操作。这些维修计划基于历史数据、经验知识以及在设计过程中的测试,而未密切关联系统的实际情况。为了降低维护成本,需要考虑预测和视情维护,即仅在实际需要时实施维护操作。

在本课程中,总结了我们近期在DPHM领域取得的研究成果。研究成果主要分三类:1)基于模型的方法;2)基于数据/计算智能的方法;3)混合方法,即研究方案同时采用基于模型和基于数据/计算智能的方法。

我们的主要研究目标是开发用于自主和智能健康监测,诊断和预测系统的模块化概念,具有以下5方面的功能:1)具有智能自动数据分析能力,2)通过早期检测和监测手段降低维护成本并最大限度地减少灾难性故障发生的可能性;3)显著减少劳动密集型和容易出错的数据分析的服务工程和维护操作;4)解决无法通过常规诊断方法快速或准确地解决的问题;5)提供一个可以运行实际数据的强大、可靠且准确的监控、诊断和验证系统。以燃气涡轮发动机和航空航天系统作为应用实例,验证所提出方法的有效性。

The increasing complexity of industrial systems such as gas turbines, aerospace systems, transportation systems, to name a few, and the cost reduction measures that have affected the manufacturers and maintenance operators are increasingly driving the need for more intelligence and autonomous capabilities and functionalities for diagnosis, prognosis, and health management (DPHM) of these systems. Maintenance cost accounts for a large part of the ownership cost and the current maintenance strategy for most industrial systems is preventive in which maintenance actions are managed along schedules suggested by manufactures. These schedules are based on historical data, empirical knowledge, and tests performed in design processes and have little to do with the actual condition of the system. To reduce the maintenance cost, predictive and condition-based maintenance is desirable in which maintenance actions are performed whenever they are actually needed.

In this talk, we provide a summary of the research outcomes and accomplishments that we have recently achieved and developed in the DPHM domain. The presented results are categorized into three main groups, namely i) model-based approaches, ii) data-driven and computational intelligence-based methods and iii) hybrid methodology, where a hybrid method refers to a scheme that invokes both model-based and data-driven/computational intelligence-based approaches.

Our main objectives have been to develop modularized concepts for autonomous and intelligent health monitoring, diagnosis, and prognosis to: 1) provide intelligent automated data analysis functionalities and capabilities, 2) reduce maintenance costs and minimize the chances of catastrophic failures through early detection and monitoring solutions, 3) provide a significant reduction in service engineering and maintenance operations that are labor intensive and involve error prone data analysis tasks, 4) address difficult to process problems that cannot be solved quickly or accurately with conventional diagnosis methods, and 5) to provide a robust, reliable, and accurate monitoring, diagnosis, and validation system that can operate with actual data. Applications to gas turbine engines and aerospace systems will be provided to demonstrate the capabilities of our proposed technologies.

课程基础

本次课程受众广泛,但考虑到课程内容的准备情况,对以下学生帮助更大:(1)控制理论专业的本科生或研究生,研究方向为故障诊断、预测与健康管理(DPHM);(2)从事系统理论研究,准备将当前所研究的理论应用于DPHM和容错控制(FTC)方法中。课程尽量不涉及太多交叉学科的内容,若有一些线性控制理论方面的基础知识对听课会很有帮助。

These lectures can be useful for a variety of audiences. However, the presentations are prepared considering two main target audiences, (a) An undergraduate/graduate student specialized in control theory, who is beginning a research on fault diagnosis and PHM (DPHM), and (b) A system theorist who is interested in applying his/her knowledge/ideas to the DPHM and FTC methodologies. We assume audiences are familiar with basic concepts of linear control theory. However, we try to be self-contained.

 

时间地点

授课内容

时间

地点

Module 1: Introduction   (1):

? General overview of DPHM   and FTC concepts.

? Introduction to various   issues in DPHM and FTC.

78

8:00-12:00

教东JC104(长安校区)

Module 2: Introduction   (2):

? Introduction to the main   challenges.

? Summary of available   results.

79

8:00-12:00

教东JC104(长安校区)

Module 3: Model-based   Fault Diagnosis Approaches

? Introduction to   model-based fault diagnosis (fault detection, isolation, and identification)   approaches.

? Introduction to key   features of various techniques.

? Applications and   summary.

710

8:00-12:00

教东JC104(长安校区)

Module 4: Data-Driven   and Hybrid Approaches

? Introduction to   data-driven and hybrid approaches.

? Applications to an   aircraft gas turbine engine and summary.

711

8:00-12:00

教东JC104(长安校区)

Module 5: Fault   Recovery and Reconfiguration, Passive and Active FTC

? Introduction to main   methodologies in PFTC and AFTC and the challenges.

? Applications and   summary.

712

8:00-12:00

教东JC104(长安校区)

 

外教简介

Dr. K. Khorasani

Department of Electrical and Computer Engineering

Concordia Institute of Aerospace and Design for Innovation

Concordia University, Montreal, Canada

K. Khorasani教授分别于1981年,1982年和1985年在伊利诺伊大学厄巴纳香槟分校获得电气与计算机工程专业的学士、硕士和博士学位。1985年至1988年期间,在密歇根大学迪尔伯恩分校担任助理教授。1988至今,在加拿大蒙特利尔的康考迪亚大学工作,目前是该大学电气和计算机工程系教授,并担任康考迪亚航空航天设计与创新研究所(CIADI)主席。

K. Khorasani教授的主要研究领域有: 非线性系统自适应控制,网络化无人系统的智能和自主控制,故障诊断、隔离和恢复(FDIR),诊断、预测和健康管理(DPHM),网络物理系统(CPS)和网络安全,卫星,无人机,UUV,神经网络和自适应结构机器学习。

在以上研究领域中,K. Khorasani教授撰写了超过450多篇学术著作,并担任IEEE航空航天和电子系统副主编。在过去的34年期间,培养了超过125位硕士和博士研究生,并撰写和合著了450多篇会议和期刊论文。从1988年至今的统计显示,他的谷歌学术论文的被引用次数超过10,000,其中包括52篇高索引论文以及220篇影响因子大于10的学术论文。

K. Khorasani received the B.S., M.S., and Ph.D. degrees in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign in 1981, 1982 and 1985, respectively. From 1985 to 1988 he was an Assistant Professor at the University of Michigan at Dearborn and since 1988, he has been at Concordia University, Montreal, Canada, where he is currently a Professor and University Tier I Research Chair in the Department of Electrical and Computer Engineering and Concordia Institute for Aerospace Design and Innovation (CIADI). His main areas of research are in nonlinear and adaptive control, intelligent and autonomous control of networked unmanned systems, fault diagnosis, isolation and recovery (FDIR), diagnosis, prognosis, and health management (DPHM), cyber-physical systems (CPS) and cybersecurity, satellites, UAVs, UUVs, neural networks, and adaptive structure machine learning. He has authored/co-authored over 450 publications in these areas. He has served as an Associate Editor of the IEEE Transactions on Aerospace and Electronic Systems. Over the past 34 years, he has graduated more than 125 Master of Applied Science (Thesis), Ph.D., and PDFs and has authored and co-authored over 450 refereed conference and journal publications. His Google Scholar citation index is over 10,000 (Since 1988) and his Google Scholar h-index is 52 and i10-index is 220 (Since 1988).

 

XML 地图 | Sitemap 地图