摘要
生物质的热值与其组成成分有关,基于此,应用最小二乘支持向量机方法建立了生物质热值预测的有效模型,并利用Biomass Feedstock Composition and Properties Database数据库提供的数据进行了测试。以该数据库的部分生物质的固定碳、挥发分和灰分含量作为输入,以相应的热值作为输出,训练最小二乘支持向量机。训练完成后,用剩余的生物质进行测试。测试结果表明,预测方法准确,速度较快。与神经网络方法相比,基于最小二乘支持向量机的生物质的热值预测方法更有效。
The heat value must have relation with it’s composition. Based on least squares support vector machine, an effective model to predict the heat value of biomass is given. The method is tested on Biomass Feedstock Composition and Properties Database. Using the fixed carbon, volatile and ash of some biomass in the database as input, and corresponding heat value as output to train the least squares support vector machine. Then using the left biomass in the database to test the least squares support vector machine. The result shows the given method is accurate and fast. Compared with the method based on artificial neural network, the method in this paper is more effective.
出处
《可再生能源》
CAS
北大核心
2010年第2期80-82,共3页
Renewable Energy Resources
关键词
最小二乘支持向量机
生物质
热值
heat value
biomass
least squares support vector machine
