Zobrazeno 1 - 10
of 184
pro vyhledávání: '"Hector Budman"'
Publikováno v:
Bioprocess and Biosystems Engineering. 46:789-802
Autor:
Dylan Hematillake, Daniele Freethy, Jacob McGivern, Chris McCready, Piyush Agarwal, Hector Budman
Publikováno v:
Industrial & Engineering Chemistry Research. 61:4625-4637
Publikováno v:
Biotechnology Progress.
Publikováno v:
Processes; Volume 10; Issue 12; Pages: 2557
A hierarchical structure based on a Deep LSTM Supervised Autoencoder Neural Network (Deep LSTM-SAE NN) is presented for the detection and classification of faults in industrial plants. The proposed methodology has the ability to classify incipient fa
Autor:
Kaveh, Ohadi, Hengameh, Aghamohseni, Johannes, Gädke, Murray, Moo-Young, Raymond, Legge L., Jeno, Scharer, Hector, Budman M.
Publikováno v:
In IFAC Proceedings Volumes 2013 46(31):30-35
Publikováno v:
Bioprocess and Biosystems Engineering. 44:453-472
The paper discusses modelling and optimization of multi-component cell culture medium. The specific productivity (Qp) was considered a function of the medium components and possible interactions described by linear factors, two-way interactions and s
Autor:
Hector Budman, Xin Shen
Publikováno v:
Processes
Volume 9
Issue 10
Processes, Vol 9, Iss 1762, p 1762 (2021)
Volume 9
Issue 10
Processes, Vol 9, Iss 1762, p 1762 (2021)
Dynamic flux balance models (DFBM) are used in this study to infer metabolite concentrations that are difficult to measure online. The concentrations are estimated based on few available measurements. To account for uncertainty in initial conditions
Publikováno v:
Industrial & Engineering Chemistry Research. 59:2378-2395
A classification approach is proposed for finding ranges of process inputs that result in corresponding ranges of a process profit function using deep learning. Two deep learning tools are used to ...
Autor:
Hector Budman, Rubin Hille
Publikováno v:
Industrial & Engineering Chemistry Research. 58:13599-13610
Model errors in model-based optimization procedures can result in suboptimal policies. In that regard, structural mismatch is of particular concern since it results in inaccurate model predictions even when a large amount of data is available for mod