Abstract: To overcome the difficulty of nonlinear correction of pressure sensors and to solve the problem of low accuracy of correction results. A back propagation (BP) neural network model was established based on wavelet function, and the Levenberg-Marquardt algorithm was used to update network parameters to realize the nonlinear correction of pressure sensors. Results show that the traditional BP network reduces the mean square error (MSE) of the pressure sensor from 2.10 to 0.68, and reduces the measurement error by 67.6%. The wavelet BP network is reduced to 0.28, which further reduces the measurement error by 19%. It can better meet the precision requirements of high altitude detection and has good generalization ability, which can be extended to the nonlinear correction of similar sensors.