摘要:固定碳是煤层工业组分的重要参数之一,传统的均质理论、线性假设在储层参数预测过程中存在着模型简单、受地层非均质性影响较高等方面的不足,参数预测结果误差较大。为提高对工业组分预测的精度及推广能力,采用非线性关系的BP神经网络方法,通过测井数据预处理、挑选学习样本等工作建立预测原煤固定碳含量的BP神经网络模型。经过学习效果检验及误差分析得出,由BP神经网络预测得到的原煤固定碳含量与实验分析数据之间误差小,预测精度高,具有较好的可推广性。关键词:BP神经网络,煤层,固定碳含量,参数预测
Abstract:Fixed
carbon is one of the important parameters of coal industrial components, some
deficiencies exist during the prediction of reservoir parameters with the
traditional homogeneity theory and linear hypothesis because of the simple
model and the high impact of formation heterogeneity, leading to a big error in
parameter prediction. To improve the prediction precision and generalization
ability for industrial components, the BP neural network method with nonlinear
relationships was taken. A BP neural network model was built to predict the
fixed carbon content of raw coal through the work of data preprocessing,
learning samples selection and so on. After the learning effect test and error
analysis, it shows that the error between predicted content of raw coal fixed
carbon by BP neural network and that by experimental measurement is low, the
prediction accuracy is high and this method has a good generalization.
Key words:BP neural network,
Coal bed, Content of fixed carbon, Parameters prediction
Abstract:Fixed
carbon is one of the important parameters of coal industrial components, some
deficiencies exist during the prediction of reservoir parameters with the
traditional homogeneity theory and linear hypothesis because of the simple
model and the high impact of formation heterogeneity, leading to a big error in
parameter prediction. To improve the prediction precision and generalization
ability for industrial components, the BP neural network method with nonlinear
relationships was taken. A BP neural network model was built to predict the
fixed carbon content of raw coal through the work of data preprocessing,
learning samples selection and so on. After the learning effect test and error
analysis, it shows that the error between predicted content of raw coal fixed
carbon by BP neural network and that by experimental measurement is low, the
prediction accuracy is high and this method has a good generalization.
订阅方式:
①在线订阅(推荐):www.sdchem.net.cn
②邮局订阅:邮发代号24-109
投稿方式:
①在线投稿(推荐):www.sdchem.net.cn
作者只需要简单注册获得用户名和密码后,就可随时进行投稿、查稿,全程跟踪稿件的发表过程,使您的论文发表更加方便、快捷、透明、高效。
②邮箱投稿:sdhgtg@163.com sdhg@sdchem.net
若“在线投稿”不成功,可使用邮箱投稿,投稿邮件主题:第一作者名字/稿件题目。
投稿时请注意以下事项:
①文前应有中英文“题目”、“作者姓名”、“单位”、“邮编”、“摘要”、“关键词”;
②作者简介包括:姓名、出生年、性别、民族、籍贯或出生地、工作单位、职务或职称、学位、研究方向;
③论文末应附“参考文献”,执行国标GB/T7714-2005标准,“参考文献”序号应与论文中出现的顺序相符;
④注明作者的联系方式,包括电话、E-mail、详细的通讯地址、邮编,以便联系并邮寄杂志。
欢迎投稿 答复快捷 发表迅速