报告讲座 > 正文

Tien-I Liu教授学术报告二则
发布日期:2018-06-14  字号:   【打印

  Professor Tien-I Liu (ASME Fellow)

工作单位Department of Mechanical Engineering College of Engineering and Computer Science California State University

举办单位:仪器科学与光电工程学院

报告人简介

Tien-I Liu(刘天一), 美国机械工程师学会院士 (ASME Fellow),现在为美国加州州立大学机械工程学系副系主任。美国威斯康辛大学(麦迪逊) 机械工程博士(1987),台湾中央大学机械工程学系主任兼机械工程研究所所长和多家台湾、美国公司工作经历,担任过台湾大学、新加坡南洋理工大学、新加坡国立大学、清华大学、上海交通大学、华中科技大学等知名高校的客座教授。曾荣获CSUS 卓越学术成就奖,IEA/JOSE 2003-05最佳论文奖等八个不同奖章. 超过100篇技术论文、20本书、手册和报告、12项软件版权和一项专利。

目前之研究领域:人工智能应用、传感器技术、线上量测,包括预测性的监侦、诊断和维护、先进的机电仪一体化、并行设计、绿色设计和制造、智能产品设计和制造、自动化系统、精密工程、先进的制造、质量和可靠性等等。

学术报告信息(一)

    报告题目:USING ARTIFICIAL INTELLIGENCE AND SENSOR TECHNOLOGY FORPRECISION BORING(使用人工智能及传感器技术进行精密镗孔)

    报告时间2018年6月25日(星期一)9:00

    报告地点:仪器学院学术报告厅(科技楼236)

   报告简介

Cutting tool conditions significantly influence the quality and precision of the machined parts.   With the ability to monitor the cutting tool condition, machining quality can be maintained and catastrophic failure can be eliminated.  In this manner, production automation can be achieved.  Therefore, tool condition monitoring (TCM) is extremely important to achieve high quality and automation of boring processes.  

Neural network, which is a branch of Artificial Intelligence, has been widely used in condition monitoring.  Counterpropagation Neural Networks (CPNs), which are based on competitive learning, have been utilized in TCM in this research for high quality and automated boring.  The inputs of the CPNs were the indexes acquired from 3-axis cutting force measurements.  The output was either the tool state or the value of tool wear.  Seventy CPN network structures have been utilized for both real time recognition and real time measurements.  The performance of the CPNs for TCM depends on the network structures.  

The results of this research are exceedingly successful.  Real time recognition of tool states showed excellent results, using a 2x30x1 CPN, of being able to predict tool states real time with 100% accuracy.  Real time measurements can achieve a minimum error of 8.46% using a 3x69x1 CPN, which is sufficient for continuous assessment of the tool degradation.  Control actions can be taken to stop the boring process in order to avoid catastrophic failure and to enhance quality and automation of the boring process.

学术报告信息(二)

    报告题目:ON STREAM INSPECTION FOR PITTING CORROSION DEFECT OF PRESSURE VESSELS USING ARTIFICIAL INTELLIGENCE AND SENSOR TECHNOLOGY(使用人工智能及传感器技术实现压力容器的孔蚀缺陷的在线检测)

    报告时间:2018年6月26日(星期二)9:00

    报告地点:仪器学院学术报告厅(科技楼236)

    报告简介

The objective of this research is to develop an intelligent on-line pitting corrosion defect detection system, which is on stream inspection (OSI).  During the tests of two pressure vessels, acoustic emission (AE) was utilized for on-line detection in order to assess internal integrity of pressure vessels. 

Feature acquisition was utilized to obtain essential features from the AE measurements.  In order to obtain the optimal features effectively, Euclidean Distance Measure and Sequential Forward Search Algorithm (SFS)were utilized for feature choice. The chosen three features were AE time domain kurtosis, AE duration, and AE frequency domain average.   Adaptive Neuro-Fuzzy Inference Systems (ANFIS), which is a branch of Artificial Intelligence, were utilized. The chosen three features were the inputs to a 3*(3*3*3) ANFIS.  Whether there is pitting corrosion defect or not was the output of this system. This approach can most quickly and most reliably determine whether there is a pitting corrosion defect or not for pressure vessels.  The developed intelligent on-line system has very high reliability and safety.  This OSI system can reduce shut down inspection (SDI), increase efficiency, and reduce cost.

(张勇/文)  
编辑:徐小红
0