This study proposes a pretraining enhanced multicomponent directed message passing neural network (PEMC D-MPNN) for predicting the solubility of H2S in ionic liquids (ILs). Traditional feature engineering methods often treat ILs as single entities, overlooking the different structural roles of the cations and anions. To address this, we introduce a multicomponent framework that separately encodes cation and anion structures using a D-MPNN, explicitly modeling their interactions. Given the limited experimental H2S solubility data, a pretraining strategy is employed utilizing the CheMeleon foundation model trained on one million molecules from PubChem to learn universal molecular representations, which are then fine-tuned for H2S solubility prediction. The proposed model integrates operational conditions (i.e., temperature and pressure) and leverages interpretability tools, such as SHapley Additive exPlanations (SHAP) and principal component analysis (PCA), to validate feature importance. The evaluation results demonstrate that the proposed PEMC D-MPNN model outperforms existing models (i.e., GPR, RF, XGBoost, SVM, DBN, RNN, DJINN, GP, GMDH), with an R2 of 0.9922, MAE of 0.0080, and RMSE of 0.0136 on 722 data points and an R2 of 0.9964, AAPRE of 5.0506%, and RMSE of 0.0099 on 1516 data points. External validation on unseen ILs, i.e.,1-ethyl-3-methylimidazolium trifluoromethanesulfonate, 1-ethyl-3-methylimidazolium tris(pentafluoroethyl)trifluorophosphate, and 1-butylpyridinium tetrafluoroborate (with 139 data points) confirms strong generalization ability, highlighting the robustness of the proposed model and practical utility for IL screening and design.
This study advances the development of syngas fermentation by presenting the first industrial-scale process design for producing isopropanol (IPA) and acetone from steel mill off-gas, with a total production capacity of 46–50 ktonne per year. The process was rigorously developed in Aspen Plus, with a comprehensive techno-economic assessment and life-cycle analysis performed to evaluate the process performance. The developed process maximizes energy efficiency by utilizing the heat content of steel off-gas and implementing advanced heat pump systems. As a result, the process is thermally self-sufficient and can operate solely on renewable electricity. Efficient utilization of waste gases results in substantial reductions in global warming potential compared with petrochemical-based production (144–160% for IPA and 138–149% for acetone). The unit production cost of 0.58–0.74 $/kgIPA/Ac and potential profit margins of 49–65% testify to the cost-effectiveness of the developed process. These findings demonstrate the environmental and economic sustainability of syngas fermentation from steel mill off-gas, establishing it as a potentially viable alternative to conventional petrochemical processes. This technology may hold great potential in reducing environmental impacts and carbon emissions in industrial chemical production.
The use of carbon-fiber reinforced thermoset polymers (CFRPs) is continuously growing in a wide range of manufacturing sectors, particularly when high performance, lightweight design, and corrosion resistance are required. However, their multimaterial cross-linked structure hinders their recyclability, resulting in the extensive generation of heterogeneous wastes. Nowadays, the correct management of end-of-life (EoL) thermosetting composites remains an open and unsolved issue. In this respect, this work presents a chemical recycling process of a model CFRP from an epoxy-amine network, operated at atmospheric pressure, relatively low temperature (≤200 °C), and mild pH (4–5), allowed by the modification of a Lewis acid catalyst. This process leads to complete liberation of the reinforcing carbon fibers without dimensional alteration, with mechanical characteristics fully comparable to the corresponding virgin fibers, and with the formation of a reusable oligomeric fraction. The recovered components are successfully upcycled by fabricating second-generation CFRPs. Finally, the solvolysis process is validated on real EoL composite parts from aerospace and sports equipment products. This work proposes an economically feasible, safe, and scalable approach to efficiently recycle amine-cured epoxy-based CFRPs, with reusability of all fractions and minimization of any secondary waste generation.

