李 佳,刘振宇.SVM与BP神经网络在石煤提钒行业清洁生产评价中的对比研究[J].中南民族大学学报自然科学版,2018,(4):18-21
SVM与BP神经网络在石煤提钒行业清洁生产评价中的对比研究
Clean Production Evaluation of Vanadium Extraction from StoneCoal by SVM and BP Neural Network: A Comparative Study
  
DOI:10.12130/znmdzk.20180404
中文关键词: 清洁生产  石煤提钒  支持向量机  BP 神经网络  评价方法
英文关键词: cleaner production  extraction vanadium from stone coal  SVM  BP-ANN  assessment methods
基金项目:湖北省自然科学基金资助项目(2016CFC772)
作者单位
李 佳,刘振宇 中南民族大学 资源与环境学院学院武汉 430074 
摘要点击次数: 128
全文下载次数: 106
中文摘要:
      为比较 BP 神经网络(ANN) 和支持向量机方法(SVM) 两种机器学习方法对清洁生产的评价能力, 以理论原理为基础,比较了两种机器学习算法在应用原理方面的差异.并以石煤提钒生产工艺中水浸工艺为对象, 对 BP 神经网络和支持向量机在清洁生产水平评价上进行了对比研究.结果表明: 支持向量机方法分类精度为 100%; BP神经网络为 90%但易陷入局部最优,因此支持向量机方法在解决小样本评价问题时具有较高的实用价值.
英文摘要:
      In order to investigate the clean production evaluation performance of two machine learning methods, BP artificial neural net (ANN) and support vector machine (SVM) , the differences between the two machine learning algorithms in application principle were compared and analyzed based on the theoretical principles. According to the water leaching process in vanadium extraction from stone coal, the performances of BP-ANN and SVM were comparatively analyzed in terms of clean production assessment. The results demonstrated that the classification accuracy of SVM reached 100%; while BP-ANN could reach 90% but was easy to fall into local optimum. So SVM method is more practical for the assessment of small samples
查看全文   查看/发表评论  下载PDF阅读器
关闭