★ Program Overview
1) Internship in Labs
As a student of the program, you take on a 3-month program where you participate in laboratory research at USTB's state-of-the-art laboratories and benefit from our “Exploring China” course.
Available fields and topics include but not limited to:
1、Day-ahead Forecasting of Photovoltaic Power Production with Convolutional Neural Network
2、Materials Science and Engineering, Physics, familiar with magnetism is favorable.
3、Parameter identification of the photovoltaic cell model with evolutionary computing algorithms
Please refer to the attachment for more details of the topics. You are also advised to contact a supervisor yourself if your preferred research topics are not listed above. Please browse USTB’s homepage to search a USTB faculty.
2) Exploring China (＊Available in July)
Our program offers a series of English-based lectures and field trips that allow you to experience time-honored Chinese history and culture, and explore specific environmental and socio-cultural aspects of China, including visits to historic sites, Chinese language course taught on primary level, Hand-on cultural experience, e.g. Taichi, Tea Art, Calligraphy, Han Chinese costume.
★ Application
1) Who can apply
- Students who are currently registered in a partner university
- English proficiency required to follow lectures
2) Number of Students
- 15 students
3) Program Duration
3 months, starting date as per different topics
4) How to apply
Send the following documents to the International Office, USTB.
- Application Form with photo
- Photocopy of passport
- Certificate of enrollment at home university
- Photocopy of insurance certificate
- Certificate of insurance
Applications should be submitted via the international office of the home university, and individual applications won’t be accepted.
5) Deadline
March 15 (Entry in May) or April 30 (Entry in June)
★ Payment
- Program fee: Exempted
- Accommodation fee: CNY 1500 per month (double-room housing),
charged upon check-in
- Fees for Cultural events and Field trips: Exempted
- Costs for study materials and resources, meals, round-trip air ticket, local transportation,
insurance and medical care not included
★ Accommodation
- Double room in campus dormitory
- Each room furnished with air-conditioner, desk, bed, closet and washroom and
free internet access
- Limited single rooms are available based on a first apply first served principle
on condition that the participant makes up the deficiency.
★ Contact
For more inquiry, please contact the Office of International Affairs, USTB.
Tel.: +86-10-62333799
Fax: +86-10-62327878
Email: ustb_io@163.com
Topic 1:
Day-ahead Forecasting of Photovoltaic Power Production with Convolutional Neural Network
Supervisor:
Dr. Chao Huang
Dr. Chao Huang received the B.Eng. degree in Electrical Engineering from Harbin Institute of Technology, Harbin, China, in 2011, the M.S. degree in Intelligent System for Transport from the University of Technology of Compiegne, Compiegne, France, in 2013, and the Ph.D. degree in Systems Engineering and Engineering Management from City University of Hong Kong, Kowloon, Hong Kong in 2017.
He was appointed as Postdoc Fellow with the Department of Systems Engineering and Engineering Management, City University of Hong Kong. He is currently an Associate Professor with the Department of Computer Science and Technology, University of Science and Technology Beijing, Beijing, China. His research interests include machine learning, computational intelligence, and renewable energy systems.
Duration of the project:
Three months (tentatively from May 2019 to July 2019)
Abstract:
Photovoltaic (PV) modules converts renewable and sustainable solar energy into electricity. However, the uncertainty of PV power productions brings challenges for the grid operation. To facilitate the management and scheduling of PV power plants, forecasting is an essential technique. In this project, convolutional neural network-based data-driven model will be developed for the day-ahead forecasting of hourly PV power productions. The project aims to capture the complex relationship of power productions at different hours in a day and the evolution of power productions at a particular hour over days with a convolutional neural network.
Preferable Candidates:□Undergraduate □Master □Ph.D All
Required Skills/Knowledge:
Proficient in Matlab and/or Python.
Reference Books/Papers:
[1] C. Huang, L Wang*, and L. L. Lai, “Data-driven Short-term Solar Irradiance Forecasting Based on Information of Neighboring Sites”, IEEE Transactions on Industrial Electronics, early access (DOI: 10.1109/TIE.2018.2856199), 2018.
[2] Agoua, Xwégnon Ghislain, Robin Girard, and George Kariniotakis, "Short-term spatio-temporal forecasting of photovoltaic power production." IEEE Transactions on Sustainable Energy 9.2 (2018): 538-546.
[3] Wang, Huai-zhi, Gang-qiang Li, Gui-bin Wang, Jian-chun Peng, Hui Jiang, and Yi-tao Liu. "Deep learning based ensemble approach for probabilistic wind power forecasting." Applied energy 188 (2017): 56-70.
Supervisor’s Contacts
Email: chaohuang@ustb.edu.cn
Tel.: +86-18802030467
Fax: +86-10-62332931
Topic 2:
Magnetic refrigeration based on rotating magnetocaloric effects
Supervisor:
Dr. Hu Zhang
Duration of the project:
2019. 5 -2019. 8
Abstract:
As the new field of magnetic refrigeration research, the “rotating magetocaloric effect (RMCE)” will not only be much helpful to our theoretical understanding on magnetocaloric effect, but also provide new thoughts for the design of magnetic refrigeration materials and machines. However, since the research on RMCE has just started, the physical mechanism is still unclear and most studies are focused on the single crystals, which hinder the development and application of this novel technology. In our upfront work, we found for the first time that the textured polycrystalline DyNiSi and LaMn2Si2 compounds exhibit RMCE. Based on that, this project is proposed to study the RMCE based on magnetic anisotropy in oriented polycrystalline materials. The regulation mechanism on orientation will be investigated by different methods such as directional solidification and magnetic heat treatment. The physical mechanism of RMCE will be studied by combining theoretical and experimental methods. The RMCE will be enhanced by optimizing the composition and processing technique. Consequently, we expect to fully understand the physical and optimization mechanisms of RMCE, and obtain a material design method which could guide us to explore room temperature RMCE materials.
Preferable Candidates:□Undergraduate □Master □Ph.D ■All
Required Skills/Knowledge:
Materials Science and Engineering, Physics, familiar with magnetism is favorable.
Reference Books/Papers:
[1] Tishin A M and Spichkin Y I 2003 in The Magnetocaloric Effect and its Applications, edited by Coey J M D, Tilley D R and Vij D R (Bristol: IOP Publishing).
[2] Tishin A M, Handbook of Magnetic Materials Vol.12, Amsterdam: North Holland, 1999.
[3] Gschneidner K A Jr, Pecharsky V K and Tsokol A O 2005 Rep. Prog. Phys. 68 1479.
Supervisor’s Contacts
Email: zhanghu@ustb.edu.cn
Tel.: 86-15210637268
Fax:
Topic 3:
Parameter identification of the photovoltaic cell model with evolutionary computing algorithms
Supervisor:
Dr. Long Wang
Dr. Long Wang received the MSc degree in computer science with distinction from University College London, London, U.K. in 2014, and the Ph.D. degree in systems engineering and engineering management from City University of Hong Kong, Kowloon, Hong Kong in 2017.
He is currently an Associate Professor with the Department of Computer Science and Technology, University of Science and Technology Beijing, Beijing, China. He serves as an associate editor for IEEE Access and an academic editor for PLOS ONE. His research interests include machine learning, computational intelligence, and computer vision. He was an awardee of the Hong Kong PhD Fellowship (success rate: around 1/30) in 2014.
Duration of the project:
Three months (tentatively from May 2019 to July 2019)
Abstract:
Solar energy has attracted growing interest from both of the academia and industry. To better monitor and control photovoltaic (PV) systems, accurate modelling of PV cells is highly desired. Two main phases are typically considered in modelling PV cells. In the first phase, a parametric model is formulated to describe the dynamic behaviors of PV cells. Next, parameters of the parametric model are identified based on collected experimental data. In this project, the parameters of the PV cell model will be estimated via evolutionary computing algorithms, including but not limited to Genetic Algorithm, Particle Swarm Optimization algorithm, and Jaya algorithm. The performance of different algorithms will be compared, and the sensitivity analysis of algorithm-specific parameters will be conducted.
Preferable Candidates:□Undergraduate □Master □Ph.D All
Required Skills/Knowledge:
Good knowledge of at least one main computer language such as Matlab, Python and Java.
Reference Books/Papers:
[1] Wang, Long, and Chao Huang. "A novel Elite Opposition-based Jaya algorithm for parameter estimation of photovoltaic cell models." Optik-International Journal for Light and Electron Optics 155 (2018): 351-356.
[2] Luo, Xiong, et al. "Parameter identification of the photovoltaic cell model with a hybrid Jaya-NM algorithm." Optik 171 (2018): 200-203.
[3] Wang, Long, Huang, Chao and Huang, Lingmiao. "Parameter estimation of the soil water retention curve model with Jaya algorithm." Computers and Electronics in Agriculture 151 (2018): 349-353.
Supervisor’s Contacts
Email: long.wang@ieee.org
Tel.: +86-17611490612
Fax: +86-10-62332931
