»Full Name：Xiaogang Deng | »Affiliation：Dept. Automation |
|
» Academic degree：PhD | » Title：Associate Prof. | |
» Major：Control Science and Engineering | » Tutor category： Master Supervisor | |
»E-mail：dengxiaogang@upc.edu.cn | ||
» Tel：0532-86983472 | ||
◎Research Areas
Data intelligence methods and their applications to complex system, including: (1) Intelligent process monitoring and fault diagnosis; (2) Machine learning based nonlinear modeling; (3) Deep learning theory and application.
◎Education l 2002-2008, College of Control Science and Engineering, China University of Petroleum (East China), PhD degree l 1998-2002, Department of Automation, University of Petroleum (East China), Bachelor’s Degree
◎Employment l 2019.9-, Associate Prof., College of Control Science and Engineering, China University of Petroleum. l 2015.1-2016.10, Academic visitor, Department of Electronics and Computer Science, University of Southampton. l 2011.1-2019.8, Associate Prof., College of Information and Control Engineering, China University of Petroleum. l 2008.1-2010.12, Lecturer, College of Information and Control Engineering, China University of Petroleum.
◎Courses Offered l Linear system theory l Automatic control theory l System fault diagnosis technology
◎Guiding graduate students l 2013-2016: Ying Xu l 2014-2017: Na Zhong, Chenchen Zhang, Mingsheng Wu l 2015-2018: Lei Wang, Yongping Hu, Baowei Sun l 2016-2019: Jian Ma, Kai Gao, Kaiqi Lu, Jiawei Deng l 2017-2020: Peipei Cai, Lei Yu, Xueying Zheng, Yongxuan Chen, Xinran Wang l 2018-2021: Wenzhi Cui, Zheng Zhang, Yukun Tian l 2019-: Kunyu Du, Jiabing Dai, Fengxuan Zhou, Sen Li, Bao Zhang l 2020-: Xianhui Jiang, Xiaoyue Liu, Shengjie Jing, Rui Sun l 2021-: Yue Zhao, Xuepeng Zhang, Linbo Xiao, Zhiyuan Ping
◎Funding and Projects l Prior knowledge assisted data-driven petrochemical process incipient fault diagnosis method, N Natural Science Foundation of Shandong Province, 2021.1-2023.12，¥10,000, PI. l Fault diagnosis technology of pumping Wells based on deep kernel learning theory, Shandong Provincial Key Research and Development Project, 2018.01-2019.12, ¥ 250, 000, PI l Multi-grade polypropylene process fault diagnosis method based on local information entropy, National Natural Science Foundation of China, 2015.01-2017.12, ¥ 250, 000, PI l Fault diagnosis method for local subspace model of Polypropylene brand Switching process, Natural Science Foundation of Shandong Province, 2014.12-2017.12, ¥ 50,000, PI
◎Awards & Honors l Supervisor of 2014 Excellent Bachelor’s thesis of Shandong Province, l Supervisor of 2020 Excellent Master's thesis of China University of Petroleum
◎Representative Publications [1] Zhang Xiangrui, Deng Xiaogang, Wang Ping. Double-level locally weighted extreme learning machine for soft sensor modeling of complex nonlinear industrial processes. IEEE Sensors Journal. 2021， 21（2）：1897-1905. [2] Deng Xiaogang, Du Kunyu. Efficient batch process monitoring based on random nonlinear feature analysis, Canadian Journal of Chemical Engineering, 2021, in press. [3] Zhang Zheng, Deng Xiaogang. Anomaly detection using improved deep SVDD model with data structure preservation. Pattern Recognition letters, 2021, 148: 1-6. [4] Deng Xiaogang, Wang Shubing, Huang Xianri, Liu Hao, Cui Baochun. Modified Modeling Method of Quartz Crystal Resonator Frequency-Temperature Characteristic With Considering Thermal Hysteresis. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2021, 68(3): 890-898. [5] Cai Peipei, Deng Xiaogang. Incipient fault detection for nonlinear processes based on dynamic multi-block probability related kernel principal component analysis. ISA Transactions. 2020， 105：210-220. [6] Deng Xiaogang, Tian Xuemin, Chen Sheng, Harris C J. Deep principal component analysis based on layerwise feature extraction and its application to nonlinear process monitoring. IEEE Transactions on Control Systems Technology, 2019, 27(6): 2526-2540 [7] Deng Xiaogang, Cai Peipei, Cao Yuping, Wang Ping. Two-Step Localized Kernel Principal Component Analysis Based Incipient Fault Diagnosis for Nonlinear Industrial Processes. Industrial & Engineering Chemistry Research, 2019, 59 (13), 5956-5968. [8] Deng Xiaogang, Deng Jiawei. Incipient fault detection for chemical processes using two-dimensional weighted SLKPCA. Industrial & Engineering Chemistry Research, 2019, 58(6): 2280-2295. [9] Deng Xiaogang, Tian Xuemin, Chen Sheng, Harris C J. Nonlinear process fault diagnosis based on serial principal component analysis, IEEE Transactions on Neural Networks & Learning Systems, 2018, 29(3):560-572. [10] Deng Xiaogang, Wang Lei. Modified kernel principal component analysis using double-weighted local outlier factor and its application to nonlinear process monitoring. ISA Transactions, 2018, 72:218-228 [11] Wang Lei, Deng Xiaogang. Multiblock Principal Component Analysis Based on Variable Weight Information and Its Application to Multivariate Process Monitoring. Canadian Journal of Chemical Engineering, 2018, 96: 1127-1141. [12] Wang Lei, Deng Xiaogang, Cao Yuping. Multimode complex process monitoring using double-level local information based local outlier factor method. Journal of Chemometrics, 2018, 32(10)： 1-21 [13] Deng Xiaogang, Tian Xuemin, Chen Sheng, Harris C J. Fault discriminant enhanced kernel principal component analysis incorporating prior fault information for monitoring nonlinear processes. Chemometrics and Intelligent Laboratory Systems, 2017, 162: 21-34 [14] Zhong Na, Deng Xiaogang. Multimode non‐Gaussian process monitoring based on local entropy independent component analysis. The Canadian Journal of Chemical Engineering, 2017, 95 (2), 319-330 [15] Xu Ying, Deng Xiaogang. Fault detection of multimode non-Gaussian dynamic process using dynamic Bayesian independent component analysis. Neurocomputing, 2016, 200: 70-79.
◎Patent
l 7 national invention patents (China)
| ||
