Genetic Optimization of General Regression Neural Network Applied to Feature Extraction of Brillouin Scattering Spectrum in BOTDA Sensors

摘要：

　　Distributed fiber sensing technology based on Brillouin optical time domain analysis(BOTDA)sensors is widely applied to monitoring the faults of civil engineering.There is a high requirement for the accuracy of Brillouin scattering spectrum feature extraction.Therefore,in order to extract the feature of Brillouin scattering spectrum in BOTDA sensors,a curve fitting method based on genetic algorithm(GA)optimized general regression neural network(GA-GRNN)is proposed in this paper.The stimulation data of different linewidth and signal-to-noise ratio(SNR)are analyzed by using the GA-GRNN algorithm,the results show that the GA-GRNN algorithm does well in extracting the feature of Brillouin scattering spectrum.

关键词： Brillouin scattering spectrum genetic algorithm (GA) general regression neural network (GRNN) curve fitting fiber optics sensors Brillouin optical time domain analysis (BOTDA)

作者: Weixin Kang Hui Li Yue Han

作者单位: College of Information and Communication Engineering Harbin Engineering University Harbin,Heilongjiang Province 150001,China

会议类型: 国际会议

会议名称: The 12th International Symposium Antennas, Propagation, and EM Theory(ISAPE 2018)?(第十二届天线、传播与电磁理论国际学术会议)

会议地点: 杭州

会议语种:英文

页码: 1-4

在线出版日期: 2018-12-03（万方平台首次上网日期，不代表论文的发表时间）