Process synthesis experiences a disruptive transformation accelerated by artificial intelligence. We propose reinforcement learning algorithm for chemical process design based on state-of-the-art actor-critic logic. Our proposed represents processes as graphs and uses graph convolutional neural networks to learn from graphs. In particular, the are implemented within agent architecture states ma...

Unsaturated, nitrogenated and sulfured compounds may reach undesirable levels in lubricant base oils, requiring hydrotreatment (HDT) at high temperatures and pressures. HDT processes are well known for their high capital and operational costs due to the use of hydrogen, compressors and multistage heterogeneous reactors. Process costs are thus highly dependent on the applied conditions. An overs...

Reuse of process water in the flotation sulfide ores has crucial importance for environmental sustainability and improved economy. However, chemistry may be a critical subject efficiency as dissolved ion concentration increases with reuse. In this study, effects reuse on Cu-Zn ore were investigated. The flowsheet consists pre-flotation section to remove naturally floatable talc particles, seque...

Increase in CO2 emissions from fossil fuels has threatened the future security of human race. The addition a renewable and environment friendly energy source to present mix is essentially required. Hydrogen economy one potential solutions for clean sustainable energy. However, economical safe storage hydrogen biggest hurdle success on commercial scale. form an organic hydride such as methylcycl...

Catalytic hydrothermal decarboxylation of biomass-derived butyric acid can produce renewable biopropane as a direct drop-in replacement fuel for liquefied petroleum gases. In this present study, experimental results from batch reactor have been used to develop hypothetical continuous process deliver 20,000 tonnes/year biopropane, base-case capacity, 10 wt% aqueous acid. A combination synthesis ...

Previous studies on process integration have generally considered reaction and separation as processes that occur sequentially in a flowsheet In this paper, a unified formalism is presented for the synthesis of reaction-separation systems, while ensuring "optimal" energy management The synthesis model stems from a target-based approach for reactor networks due to an earlier study. It is shown t...