Heat transfer performance prediction of Taylor–Couette flow with longitudinal slits using artificial neural networks

•The slit structure parameters effect on the heat transfer performance of Taylor–Couette flow are discussed.•The reasons for the differences in the thermal performance of different slit structures are discussed by the field synergy principle.•A GA-BPNN model for thermal performance prediction of Taylor–Couette flow is developed.•The slit structure parameters are optimized according to the PSO algorithm and GA-BPNN model.