Prediction of three-dimensional coordinate measurement of space points based on BP neural network

Abstract

In order to improve the measurement accuracy of three-dimensional coordinate measurement system based on dual-PSD, this paper proposes a three-dimensional coordinate measurement method based on back propagation (BP) neural network considering the high ability of the neural network to deal with the complex nonlinear mapping problem. This method can describe the mapping relationship between three-dimensional coordinates of space points in the world coordinate system and coordinates of light spots on dual-PSD well. Levenberg-Marquardt learning algorithm is used to train the network, and then trained BP neural network model is used to predict three-dimensional coordinates of space points. Experimental results show that the average measurement error of space points obtained by the method is low. It proves that the built BP neural network model can be used to predict three-dimensional coordinates of space points. [Submitted 9 July 2018; Accepted 30 October 2018]