Design Method of TIR Lens Based on CPO-BP Model
YU Luping
LI Huiming
LI Weikang
YE Zhen
Abstract：The structure of the TIR lens has an significant impact on the light intensity and scattering angle of the LED light source passing through it.A BP neural network model optimized by the Crested Porcupine Optimizer CPO is established by taking the structural parameters of the TIR lens as input variables and the light intensity and scattering angle as output variables.The results show that,compared to the BP neutral network,the CPO-optimized BP neural network improved the average absolute percentage error(MAPE)for light intensity and scattering angle prediction by 97.85%and 94.3%,respectively.The CPO-BP model demonstrates good effectiveness,accuracy and scalability.
Keywords：TIR lenscrested porcupine optimizer(CPO)BP neural networklight distribution design
Publication Date：2025-04-30
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 82-87 )