Three-dimensional coordinate measurement algorithm by optimizing BP neural network based on GA. Issue 6 (8th July 2019)

• Record Type: Journal Article
• Authors: Lu, Xiaohong; Wang, Yongquan; Li, Jie; Zhou, Yang; Ren, Zongjin; Liang, Steven Y.
• Is Part Of: Engineering computations. Volume 36:Issue 6(2019)
• Page Start: 2066
• Page End: 2083
• Publication Date: 2019-07-08
• Subjects: Measurement -- Genetic algorithm -- BP neural network -- PSD; Computer-aided engineering -- Periodicals; Computer graphics -- Periodicals; 620.00285
• DOI: 10.1108/EC-09-2018-0410
• Languages: English
• ISSNs: 0264-4401

Abstract

Abstract : Purpose: The purpose of this paper is to solve the problem that the analytic solution model of spatial three-dimensional coordinate measuring system based on dual-position sensitive detector (PSD) is complex and its precision is not high. Design/methodology/approach: A new three-dimensional coordinate measurement algorithm by optimizing back propagation (BP) neural network based on genetic algorithm (GA) is proposed. The mapping relation between three-dimensional coordinates of space points in the world coordinate system and light spot coordinates formed on dual-PSD has been built and applied to the prediction of three-dimensional coordinates of space points. Findings: The average measurement error of three-dimensional coordinates of space points at three-dimensional coordinate measuring system based on dual-PSD based on GA-BP neural network is relatively small. This method does not require considering the lens distortion and the non-linearity of PSD. It has simple structure and high precision and is suitable for three-dimensional coordinate measurement of space points. Originality/value: A new three-dimensional coordinate measurement algorithm by optimizing BP neural network based on GA is proposed to predict three-dimensional coordinates of space points formed on three-dimensional coordinate measuring system based on dual-PSD.