Improvement of Dynamic Range of Laser Positioning System Based on Back Propagation Neural Network

For a pulse laser detection system, the existing peak extraction methods can only detect the unsaturated waveform in the linear region but cannot detect the saturated waveform in the nonlinear region. The methods based on pulse duration analysis can detect the saturated waveform within a certain range but have complicated models and difficult fitting, resulting in the limited detection range of the system. In view of the detection difficulty of the laser positioning system in the nonlinear region, we established an energy response model based on the back propagation neural network algorithm in this paper, which can be used to detect the waveforms in both the linear and nonlinear regions. Finally, the inversion fitting effect of the proposed model on the waveform in the nonlinear region was experimentally verified. The experimental results show that the incident light intensity could be obtained by inversion fitting based on the proposed method and its maximum relative error with the actual light intensity was only 3.79%. Besides, the detection range was expanded to 10.25 times that of the peak extraction methods, and the proposed model was simple and had a small error. In conclusion, the model proposed in this paper can be used to detect the pulse laser in the nonlinear region and applied to improve the dynamic range and detection ability of the pulse laser detection and positioning system based on the four-quadrant detectors. © 2021, Chinese Lasers Press. All right reserved.