摘要
采用激光诱导击穿光谱技术(LIBS)与机器学习算法相结合,研究建立了煤矿样标的分类方法。首先对煤矿样标光谱数据进行预处理,然后建立极限学习机(ELM)、支持向量机(SVM)、随机森林(RF)机器学习模型,最后通过对选定的特征光谱进行分类训练及测试。结果表明:ELM、SVM、RF三种机器学习模型的分类准确度分别为96.52%、96.55%、97.02%。从分类准确度可以看出,构建的激光诱导击穿光谱结合机器学习算法模型,能够实现对煤矿标样LIBS数据的快速、准确分类。
The classification method of coal mine sample is established by combining laser induced breakdown spectroscopy(LIBS) with machine learning algorithm. First, preprocess the spectral data of coal mine sample, and then establish the machine learning models of extreme learning machine(ELM), support vector machine(SVM), and random forest(RF). Finally, train and test the selected characteristic spectra by classification.The results show that the classification accuracy of ELM, SVM and RF machine learning models is 96.52%, 96.55% and 97.02% respectively. From the classification accuracy, it can be seen that the combination of laser induced breakdown spectroscopy and machine learning can achieve fast and accurate classification of coal mine samples.
作者
汪浩
Wang Hao(School of Chemistry and Chemical Engineering,Xi'an Shiyou University,Shaanxi,710065)
出处
《当代化工研究》
2023年第4期28-31,共4页
Modern Chemical Research
关键词
激光诱导击穿光谱
极限学习机
支持向量机
随机森林
机器学习
laser induced breakdown spectroscopy
extreme learning machine
support vector machines
random forest
machine learning