Highlights - 26 April 2020
We are working on a COVID-19 project. Check it out here.
27 June 2020
Hui Tian’s (PhD, ‘20) paper has been published in Computers & Chemical Engineering. Congratulations!
This paper develops a tractable approximation for stochastic model predictive control (SMPC). Under the proposed approach, we solve multiple deterministic MPC (DMPC) problems over individual scenarios of the uncertain variables to obtain a set of control policies and select from this candidate set a control input that yields the best approximation of the SMPC solution (i.e., yields the smallest statistical measure of the objective function (e.g., expected value) and of the constraints). This approach is a scenario decomposition scheme that overcomes tractability issues of SMPC (which solves problems that incorporate multiple scenarios all-at-once). Moreover, the approach enables flexible handling of complex statistical measures (e.g., medians, quantiles, and chance constraints) and enables prioritization of objectives and constraints (this is difficult to do with off-the-shelf optimization solvers). An application to a nonlinear mechanical pulping process demonstrates that the approach provides high quality solutions. We hypothesize that this is because the optimal SMPC policy lives in a space that is spanned by the control policies for the individual scenarios. Moreover, we note that a traditional DMPC policy corresponds to the policy of an individual scenario (the mean scenario is typically chosen). Consequently, the proposed approach can do no worse than DMPC and can be interpreted as an approach that seeks to find a DMPC policy that best approximates the SMPC policy.
14 June 2020
Qiugang Lu (PhD, ‘18), currently postdoc at Zavala Lab, UW-Madison, will begin a tenure track position at Texas Tech University in September 2020. Congratulations!
30 April 2020
Our recent paper on RL, Toward self‐driving processes: A deep reinforcement learning approach to control - Spielberg et al. (2019), has been recognized as “among the top 10% most downloaded papers” in AIChE Journal.
“Among work published between January 2018 and December 2019, yours received some of the most downloads in the 12 months following online publication.”
26 April 2020
COVID-19 has disrupted our lives in unprecedented ways. Our research group is trying to estimate the extent of its prevalence in the society, quantify its infectiousness, model its spread and develop optimal mitigation policies. The focus of our work is primarily on Canadian data.
Visit the website at https://dais.chbe.ubc.ca/covid-19/
17 April 2020
Yiting passed his candidacy exam with flying colors. Congratulations!
16 April 2020
Nathan received the prestigious NSERC CGS D scholarship. He was ranked 5th among 107 applicants in his committee. This is a tremendous achievement. Congratulations, Nathan! We are proud of you.
14 April 2020
Our new paper has been recently accepted in Industrial & Engineering Chemistry Research.
10 March 2020
Hui successfully defended her PhD thesis today on Stochastic multi-objective economic model predictive control of two-stage high consistency mechanical pulping processes. Read more about her work here Congratulations!
27 February 2020
Four of our papers were accepted for presentation at the 2020 IFAC World Congress.
We are also organizing a tutorial on data analytics.
14 February 2020
Prof. Thornhill from Imperial College London visits UBC and delivers a CHBE Distinguished Speaker Seminar on Process Data Analytics. Members of the DAIS lab met Prof. Thornhill to share and discuss their research interests.
After Prof. Thornhill’s talk, Yiting presented at the CHBE department seminar.
01 February 2020
Yi will be going back to the Beijing Institute of Chemical Technology. Best wishes!
02 November 2019
Dr. Gopaluni and Dr. Verrett have been nominated as Applied Science OER champions for the development of open chemical engineering resources. Big thanks to DAIS members and students involved in the TLEF project - Yiting Tsai, Siang Lim, Vasiliy Triandafilidi, Athanasios Kritharis, Eugene Shen, Ngai To Lo, Said Zaid-Alkailani, Victor Chiew and all other contributors.
01 September 2019
Yiting’s paper on bioreactor performance prediction has been published in Processes. Congrats!
01 September 2019
A project in collaboration with Dr. Piret and Dr. Levings on Bioprocess engineering for therapeutic T-cell manufacturing has received federal Collaborative Health Research Projects (CHRP) funding worth over $600k.
15 January 2019
We are looking for a Post Doctoral Fellow to work on an exciting industrial project at the intersection of Control Theory and Machine Learning.
For details see: NewPostDocResearchML.pdf
Applications are invited for a three-year postdoctoral fellowship at the University of British Columbia. The successful candidate will conduct high quality research in machine learning with a focus on deep learning and reinforcement learning to address real world industrial control problems. The principal investigators, based in UBC’s Department of Chemical and Biological Engineering, the Institute of Applied Mathematics, and Honeywell, expect the research to have a significant influence on industrial practice. UBC and Honeywell have extensive experience in collaborating on advanced control technology. Previous projects have resulted in a series of academic innovations and industrial products recognized with awards from IEEE, IFAC, and NSERC.
19 July 2018
DAIS Lab members set to present at ADCHEM 2018. For more information, visit the DAIS ADCHEM page.
See workshop page: https://dais.chbe.ubc.ca/adchem/
05 July 2017
Lee Rippon received the prestigious Killam Doctoral Scholarship. Congratulations!