| 1. |
- Baxevanidis, Pantelis, et al.
(författare)
-
Group contribution-based LCA models to enable screening for environmentally benign novel chemicals in CAMD applications
- 2022
-
Ingår i: AICHE Journal. - : Wiley. - 1547-5905 .- 0001-1541. ; 68:3
-
Tidskriftsartikel (refereegranskat)abstract
- This study considers the development of suitable models for the estimation of life cycle assessment (LCA) indices of organic chemicals. Unlike state-of-the-art models, the tools developed here correlate LCA indices with the molecular composition according to the well-established group contribution (GC) approach. The LCA indices considered here are global warming potential, cumulative energy demand, and Eco-Indicator 99. The model development uses data from existing LCA databases, where each material is associated with its cradle-to-gate LCA metrics. A variety of regression and nonregression methodologies are recruited to achieve the optimum correlation. GC models can be used to screen for molecules with optimal and/or desirable properties, using appropriate molecular design synthesis algorithms. In this framework, the models developed here are linked to the design algorithm to enable the consideration of LCA features together with other properties, for the design of environmentally benign liquid–liquid extraction solvents.
|
|
| 2. |
- Karka, Paraskevi, 1982, et al.
(författare)
-
Digitizing sustainable process development: From ex-post to ex-ante LCA using machine-learning to evaluate bio-based process technologies ahead of detailed design
- 2022
-
Ingår i: Chemical Engineering Science. - : Elsevier BV. - 0009-2509. ; 250
-
Tidskriftsartikel (refereegranskat)abstract
- Life Cycle Assessment is a data-intensive process holding great promise to benefit from advanced analytics and machine learning technologies. The present research aims at the development of a data-science based framework with capabilities to estimate LCA metrics of bio-based and biorefinery processes in early design phases. Life cycle inventories may combine experimental (pilot and lab scale) data, property and thermodynamic databases, and model-derived data from simulations and design studies. The framework applies advanced analytics such as classification trees and artificial neural networks (ANN) with a scope to produce input–output relationships through predictor variables that refer to the molecular structure of bio-chemical or bio-fuel products of interest, the feedstocks used, and the process technologies characteristics. The combined use of ANNs and trees demonstrates a coordinated level of complementarity between the approaches, while it improves robustness and streamlines LCA estimations in the early-stage design.
|
|
