激光与光电子学进展, 2020, 57 (15): 153002, 网络出版: 2020-08-04
基于激光诱导击穿光谱与GA-BP神经网络的塑料分类识别 下载: 1143次
Plastic Classification and Recognition by Laser-Induced Breakdown Spectroscopy and GA-BP Neural Network
光谱学 激光诱导击穿光谱 遗传算法 误差反向传播神经网络 塑料识别 主成分分析法 optical spectroscopy laser-induced breakdown spectroscopy genetic algorithm error back propagation neural network plastic recognition principal component analysis method
摘要
利用激光诱导击穿光谱(LIBS)技术与基于遗传算法优化的误差反向传播(GA-BP)神经网络对常见的9种塑料进行分类识别。通过激光诱导击穿塑料表面产生等离子光谱,用光谱仪对每种塑料采集100组光谱数据,以美国国家标准与技术研究院(NIST)的原子光谱数据库为参考,对主要的元素特征谱线进行精确标定。选取15条特征谱线进行分析,通过主成分分析(PAC)法对光谱数据进行降维处理,并建立GA-BP神经网络模型。实验结果表明,通过PCA法对数据进行降维后,GA-BP神经网络的识别效率得到很大提高,平均识别精度为99.72%,可对多种塑料进行快速、精准的识别。
Abstract
Laser-induced breakdown spectroscopy (LIBS) technology and genetic algorithm optimization based error back propagation (GA-BP) neural network are used to classify and recognize 9 common plastics in this paper. Plasma spectra are generated by laser-induced breakdown of the plastic surfaces, and 100 sets of spectral data are collected for each plastic with a spectrometer. The national institute of standards and technology (NIST) atomic spectrum database is used as a reference to accurately calibrate the main element characteristic lines. In the experiment, 15 characteristic spectral lines are selected for analysis, and the dimension of spectral data is reduced by principle component analysis (PAC) method, and GA-BP neural network model is established. Experimental results show that the GA-BP neural network recognition efficiency is greatly improved after dimensionality reduction by PCA method, and the average recognition accuracy is 99.72%, which can identify a variety of plastics quickly and accurately.
宋海声, 麻林召, 朱恩功, 王一帆, 刘宇平, 孙文健, 彭鹏, 李承飞. 基于激光诱导击穿光谱与GA-BP神经网络的塑料分类识别[J]. 激光与光电子学进展, 2020, 57(15): 153002. Haisheng Song, Linzhao Ma, Engong Zhu, Yifan Wang, Yuping Liu, Wenjian Sun, Peng Peng, Chengfei Li. Plastic Classification and Recognition by Laser-Induced Breakdown Spectroscopy and GA-BP Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(15): 153002.