Flow chemistry is a hot topic in today's research. The millimeter scale flow reactor can meet the production requirements of fine chemicals and pharmaceuticals industry.Using inserts in millimeter tubes is an inexpensive, highly machinable reactor design method and offers better pressure resistance than commercial plate flow reactors.In this study, a new multi-blades reactor was designed. CFD method was utilized to study the flow and heat transfer in the reactor, and particle image velocimetry (PIV) was used to visualize the flow field in the reactor.The neural network algorithm was used to process the CFD results, and the relationship between operating conditions, reactor structure and heat transfer capacity was obtained.For the target reaction, the heat transfer capacity requirements of the device were proposed in the reactor design according to the reactor stability criterion, and the optimal structure and operation conditions were achieved by the trained neural network.This design method can shorten the reactor process development time and practice the concept of "intrinsic safety" of the reactor from the initial stage of design.

Neural network-based millimeter reactor design,heat transfer and flow visualization

ACS Spring Meeting 2021

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.