作者: Tang Hongsheng , Sheng Liwen , Liang Long , Wang Kang , Li Jiguang
DOI:
关键词: Classifier (UML) 、 Random forest 、 Laser-induced breakdown spectroscopy 、 Multiple classification 、 Artificial intelligence 、 Test set 、 Computer science 、 Pattern recognition
摘要: The invention discloses a method for recognizing steel grade by combining random forest algorithm with laser-induced breakdown spectroscopy. comprises the following steps of firstly detecting samples different grades utilizing an LIBS (Laser-induced Breakdown Spectroscopy) system, and acquiring data matrix; then establishing disaggregated models algorithm, wherein combined classifier which is strong plurality weak classifiers used in modeling process; forming through multiple classification trees after to-be-detected sample input model; distinguishing classifying test set forest, determining category final voting classifier. According to method, classifiers, accuracy improved, influences useless information on prediction process are reduced, calculation cost lowered.