Associate Professor Yibo Ai

Keywords：Data Fusion; Nondestructive testing; Intelligence Control; Complex System Modeling; Reliability Analysis

Contact：ybai@ustb.edu.cn

Researches

Yibo Ai received the B.S. degree, M.S. degree and Ph.D. degree in control science and engineering from University of Science and Technology Beijing, Beijing, China, in 2004, 2007 and 2018, respectively. Her research interest includes big data fusion, complex system modeling, nondestructive detection, system reliability analysis and remaining life prediction. She has been engaged in the application on high speed train gear transmission system, high accuracy motorized spindle, biometrics feature recognition and multi-levels system service safety assessment. She has presided over and participated as the main member a number of National Science Foundation China, science and technology support program and other projects in China, and won the second prize of Beijing education teaching achievement award.

l  Main Projects

- Project 1: “Sea Targets Recognition System based on Deep Learning”, Central University Basic Scientific Research Foundation of Ministry of Education, 2019

- Project 2: “Cross-scale, Multi-leve System Service Safety Assessment”, Chinese Natural Science Foundation, 2012-2016

- Project 3: “High-speed gearbox shell damage tolerance and life prediction research”, Central University Basic Scientific Research Foundation of Ministry of Education, 2011-2015

- Project 4: “Research on Engineering Service System Assessment Method”, Beijing Education Commission, 2008-2010

l  Main Contributions

- Complex System Cross-scale Life Prediction and Reliability Analysis: A "material scale—structure scale" cross-scale correlation and decision method for life prediction of gearbox shell has been proposed. The equivalent stress has been used to connect the structure scale finite element and material scale. The fuzzy decision making method has been applied to do the cross-scale decision between simulation result and inspection result of key structure locations in sample bench test.

- Data Fusion for Imbalance Data: An unbalanced data regression method based on Adaboost sample distribution adjustment has been proposed. The fatigue damage process of high speed train gearbox shell is slow, and the key characterization data of the damage state is relatively small. Therefore, the Adaboost classifier algorithm has been used to adjust the distribution of the key characterization data and the non key characterization data in the detection data.

- Video Image Recognition based on Deep Learning: Weld quality recognition has been achieved based on convolutional neural networks (CNN) image classification network. The convolutional neural network (FCN) processing has been used to complete input image, extraction of defect features. Then crack defects in solar energy battery components has been detected and positioning.

l  Publications

1.     Yibo Ai, Hao Cui, Weidong Zhang, “Multi-level Materials Service Safety Assessment System”, Advanced Materials Research, 2012, 572: 410~414.

2.     Weidong Zhang, Xiwen Zhang, Bin Yang, Xianfei Ding, Yibo Ai, “Damage Characterization and Recognition of Aluminum Alloy Based on Acoustic Emission Signal”, Journal of University of Science and Technology Beijing, 2013，35(5): 626~633.

3.     Yibo Ai, Chang Sun, Hongbo Que, Weidong Zhang, “Investigation of Material Performance Degradation for High-Strength Aluminum Alloy Using Acoustic Emission Method”, Metals, 2015, 5(1): 228~238.

4.     Chang Sun, Weidong Zhang, Yibo Ai, Hongbo Que, “Study of the tensile damage of high-strength aluminum alloy by acoustic emission”, Metals, 2015,5(4): 2186~2199.

5.     Yibo Ai, Nan Wang, Hongbo Que, Bin Yang, Weidong Zhang, “Material Casting defect recognition of high-speed train gearbox shell based on industrial CT technology”, Journal of Harbin Institute of Technology | J Harbin Inst Technol, 2015, 40(70): 45~49.

6.     Yibo Ai, Chang Sun, Weidong Zhang, “Fault Diagnosis of High Speed Gear-box Shell Based on Performance Degradation and Material Damage Characterization”, Control and Decision, 2018(7): 1264-1270.

7.     Yibo Ai, Tao Lv and Weidong Zhang, “High strength aluminium alloy fatigue damage alert of high speed train gearbox shell using acoustic emission instrument”, International Journal of Mechatronics and Manufacturing Systems, 2018, 11(1):36-52.

8.     Zhang T, Ai Y, Tian K, Zhou J, Zhang W. “A fast temperature rise identification method based on an adaptive particle filter”. International Journal of Advanced Manufacturing Technology, 2018(1-4):1-19.

9.     Yibo Ai, Chang Sun and Weidong Zhang, “Life prediction of the tensile damage progress for high-speed train gearbox shell based on acoustic emission sensor and an automatic optimization method”, International Journal of Distributed Sensor Networks 2018, 14(6): 1-9.

10.  Kun Tian, Tao Zhang, Yibo Ai, Weidong Zhang, “Induction motors dynamic eccentricity fault diagnosis based on the combined use of WPD and EMD –Simulation study”，Applied Sciences，2018，8(10): 1709.

l  Patents

1.     “An adaptive ultrasonic pulse excitation device and its control method”, patent number: ZL 201410195593.1, authorized;

2.     “An internal defect evolution detection and analysis method for metal casting fatigue process”, patent number: ZL 201510009344.3, authorized;

3.     “A kind of metal material fatigue loading test and fatigue damage analysis of nondestructive testing (NDT) methods”, patent number: ZL 201510059474.8, authorized.

l  Awards and Membership

1.     2018, Beijing Education and Teaching Achievement Award;

2.     Member of INFORMS.