Research on improving the basis weight measurement accuracy of tissue paper based on PSO-BP neural network

The near-infrared (NIR) sensor can be used for measuring the basis weight and moisture of tissue paper, but measurement accuracy is not ideal this paper grade. range 10~30 g/m2, indicating that it a low gram paper. temperature humidity production environment significantly impact an NIR sensor. This focuses on improving weight. In order to reduce influences humidity, mathematical model based particle swarm optimization back propagation (PSO-BP) neural network proposed. comparison with multiple linear regression models, error PSO-BP within ± 0.5 g/m2. effectively improve has good effect overcoming nonlinear caused by changes in ambient humidity.