Multiscale optimization of formic acid dehydrogenation process via linear model decision tree surrogates
Multiscale optimization problems require the interconnection of several models of distinct phenomena which occur at different scales in length or time. However, the best model for any particular phenomenon may not be amenable to rigorous optimization techniques. For instance, molecular interactions are often modeled by computational chemistry software packages that cannot be easily converted into optimization constraints. Data-driven surrogate models can overcome this problem. By choosing surrogates with functional forms that are convertible to a mixed-integer linear model, one can connect and optimize these surrogates instead of the underlying models. We demonstrate the interconnection of linear model decision trees to optimize across three scales of a formic acid dehydrogenation process. We show that optimizing across all three scales simultaneously leads to a 40% cost savings compared to optimizing each model independently. Furthermore, the surrogates retain some relevant physical behaviors and provide insights into the optimal design of this process.
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE; USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)
- Grant/Contract Number:
- AC52-07NA27344
- OSTI ID:
- 2479664
- Report Number(s):
- LLNL--JRNL-865282; 1099378
- Journal Information:
- Computers and Chemical Engineering, Journal Name: Computers and Chemical Engineering Vol. 194; ISSN 0098-1354
- Publisher:
- ElsevierCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
MISO - Mixed Integer Surrogate Optimization
Cross-Scale Catalyst Modeling Applied to H2 Storage and Release via Formic Acid