Neural-network-based control of discrete-phase concentration in a gas-particle corner flow with optimal energy consumption.

This paper presents a machine learning based model for control of local bioaerosol concentration via a forced corner flow with optimal energy efficiency in an indoor environment. A recirculation zone determined by the inlet flow rate traps particles partially with one or more vortices around the corner. The profile of the recirculation zone is then determined mathematically by the minimum net mass flux principle with a grid search technique. Subsequently, the variation of the recirculation zone profile is then learned through a neural network (NN), in which data is collected from the simulation by the Eulerian–Lagrangian scheme. Moreover, a model predictive control (MPC) algorithm is implemented to achieve an optimal profile of the recirculation zone with optimal energy consumption, based on the linearized NN model. Finally, the proposed NN-MPC is implemented for simulation of removing the local bioaerosol from an indoor corner through a flow-rate-controllable airflow from ventilation outlet located on the ceiling. • A recirculation zone trapping particles is defined by minimum net mass flux law. • Relationship between recirculation zone and inlet flow rate is trained by NN. • Energy consumption of input is optimized to fit long-term continuous process. • The proposed NN-MPC reduces particle concentration with energy efficiency. [ABSTRACT FROM AUTHOR]