由Intelligence & Robotics（IR）期刊主導(dǎo)的第四期前沿論壇有幸邀請(qǐng)到了上海交通大學(xué)的陳宏田副教授和上海大學(xué)的張進(jìn)教授作為主講人，將于??2023 年 3 月 28 日 20:00（北京時(shí)間）在 Zoom 平臺(tái)正式召開。本期報(bào)告的主題是?Intelligence, Optimization, and Safety for Complex Systems，將由?IR?副主編上海大學(xué)彭晨教授擔(dān)任主持人，全程采用中文進(jìn)行。IR?編輯部期待您與來(lái)自世界各地的專家學(xué)者分享和交流最前沿的學(xué)術(shù)報(bào)告，促進(jìn)領(lǐng)域的進(jìn)一步發(fā)展，歡迎各位學(xué)者專家積極參會(huì)，交流討論。

參會(huì)信息

報(bào)告題目：Intelligence, Optimization, and Safety for Complex Systems

時(shí)間：2022 年 3 月 28 日 周二 20:00（北京時(shí)間）

地點(diǎn)：Zoom 會(huì)議

ID: 846 2638 7855

會(huì)議主持

IR?副主編 彭晨教授

上海大學(xué)機(jī)電工程與自動(dòng)化學(xué)院副院長(zhǎng)、教授、博士生導(dǎo)師

國(guó)家百千萬(wàn)人才工程、有突出貢獻(xiàn)中青年專家、上海市“東方學(xué)者”、“東方學(xué)者跟蹤計(jì)劃”、“浦江人才計(jì)劃”、2020-2022 年全球高被引科學(xué)家、2014-2022 年 Elsevier 中國(guó)高被引學(xué)者入選者。彭教授主持國(guó)家重點(diǎn)研發(fā)項(xiàng)目 1 項(xiàng)，國(guó)家自然基金項(xiàng)目 6 項(xiàng)（其中 1 項(xiàng)重點(diǎn)），工信部課題 1 項(xiàng)，省部級(jí)項(xiàng)目 20 余項(xiàng)。主要研究領(lǐng)域包括網(wǎng)絡(luò)化控制、安全控制；魯棒控制、模糊系統(tǒng)、時(shí)滯系統(tǒng)分析與綜合；流程供應(yīng)鏈優(yōu)化與調(diào)度；工業(yè)爐窯能效優(yōu)化；流程工業(yè)智能故障診斷與監(jiān)測(cè)等。任 IEEE 高級(jí)會(huì)員、IEEE-PES 智慧物聯(lián)與控制分委會(huì)主席、美國(guó)《數(shù)學(xué)評(píng)論》評(píng)論員、上海市電子電器技術(shù)協(xié)會(huì)副理事長(zhǎng)、上海市自動(dòng)化應(yīng)用專委會(huì)主任，IEEE Transactions on Industrial Informatics、Information Sciences?等國(guó)際期刊的編委。

特邀演講嘉賓

IR?副主編 陳宏田博士上海交通大學(xué)自動(dòng)化系副教授，博士生導(dǎo)師

IEEE 會(huì)員。本碩畢業(yè)于南師大，博士畢業(yè)于南京航空航天大學(xué)。2018 年在德國(guó)先進(jìn)控制與復(fù)雜系統(tǒng)研究所做訪問學(xué)者。主要研究方向?yàn)閿?shù)據(jù)驅(qū)動(dòng)技術(shù)、人工智能、量子計(jì)算、分布式系統(tǒng)等及其在高速列車牽引系統(tǒng)的故障診斷應(yīng)用。目前為止，發(fā)表英文專著 1 部，國(guó)際英文論文 40 余篇（IEEE 匯刊 18 篇）、授權(quán)與受理國(guó)家專利 8 項(xiàng)。主持、參與國(guó)家級(jí)和省部級(jí)項(xiàng)目 6 項(xiàng)。獲得中國(guó)自動(dòng)化學(xué)會(huì)優(yōu)秀博士論文獎(jiǎng)、江蘇省優(yōu)秀博士論文獎(jiǎng)、工信部創(chuàng)新特等獎(jiǎng)（全校第一名），群星創(chuàng)新大獎(jiǎng)、臨近空間杯一等獎(jiǎng)等多項(xiàng)個(gè)人獎(jiǎng)與團(tuán)體獎(jiǎng)。目前為多個(gè)國(guó)際期刊客座編委、青年編委。受邀作為組織主席，舉辦 ICRCA 2022 國(guó)際會(huì)議與 AMEE 2022 國(guó)際會(huì)議；并承擔(dān) DDCLS 22 大會(huì)與 DOCS22 大會(huì)專題主席。

報(bào)告主題：Explainable Fault Diagnosis: A Bridge Between Unsupervised and Supervised Learning-based Fault Diagnosis Approaches

The increased complexity and intelligence of automation systems require the development of intelligent fault diagnosis (IFD) methodologies. By relying on the concept of a suspected space, this study develops explainable data-driven IFD approaches for nonlinear dynamic systems. More in detail, we parameterize nonlinear systems through a generalized kernel representation used for system modeling and the associated fault diagnosis. An important result obtained is a unified form of kernel representations, applicable to both unsupervised and supervised learning. More importantly, through a rigorous theoretical analysis we discover the existence of a bridge (i.e., a bijective mapping) between some supervised and unsupervised learning-based entities. Notably, the designed IFD approaches achieve the same performance by the use of this bridge. In order to have a better understanding of the results obtained, unsupervised and supervised neural networks are chosen as the learning tools to identify generalized kernel representations and design the IFD schemes; an invertible neural network is then employed to build the bridge between them. This report is a perspective talk, whose contribution lies in proposing and detailing the fundamental concepts for explainable intelligent learning methods, contributing to system modeling and data-driven IFD designs for nonlinear dynamic systems.

張進(jìn)博士

上海大學(xué)機(jī)電工程與自動(dòng)化學(xué)院教授、博士生導(dǎo)師

上海海外高層次人才計(jì)劃入選者，現(xiàn)為上海大學(xué)機(jī)電工程與自動(dòng)化學(xué)院教授、博士生導(dǎo)師。先后主持或參與包括國(guó)家自然科學(xué)基金、以色列科學(xué)基金、以色列高等教育委員會(huì)科研專項(xiàng)等在內(nèi)的 8 項(xiàng)科學(xué)研究基金項(xiàng)目，在國(guó)內(nèi)外重要學(xué)術(shù)期刊上發(fā)表論文 30 余篇，并擔(dān)任 20 余種 SCI 學(xué)術(shù)期刊審稿人。

報(bào)告主題：Vibrational control with square wave dithers: A time-delay approach

This talk is concerned with stabilization problem of second-order systems by fast-varying square wave dithers depending on a small parameter. We first employ the known in vibrational control coordinate transformation that allows to cancel the high-gain term due to the introduced controller, and then present a time-delay approach to periodic averaging of the system in new coordinates. The resulting time-delay system is a perturbation of the averaged system in new coordinates which is assumed to be exponentially stable. The stability of the time-delay system guarantees the stability of the original system. We construct an appropriate Lyapunov functional for finding sufficient stability conditions in the form of linear matrix inequalities (LMIs). The upper bound on the small parameter that preserves the exponential stability is found from LMIs. Finally, two numerical examples including vibrational control of suspended pendulum illustrate the efficiency of the method.

歡迎廣大學(xué)者積極參加此次會(huì)議，同時(shí)特刊Intelligence, Optimization, and Safety for Complex Systems開放征稿中，歡迎各位學(xué)者踴躍投稿！

任何問題請(qǐng)聯(lián)系編輯部editorial@intellrobot.com

期刊網(wǎng)站：https://intellrobot.com/