基于GRA-GASA-SVM的煤层瓦斯含量预测方法研究  被引量:6

Research on Prediction Method of Coal Seam Gas Content Based on GRA-GASA-SVM

在线阅读下载全文

作  者:田水承 任治鹏[1,2] 马磊 TIAN Shuicheng;REN Zhipeng;MA Lei(College of Safety Science and Engineering,Xi'an University of Science and Technology,Xi'an 710054,China;Institute of Safety and Emergency Management,Xi'an University of Science and Technology,Xi'an 710054,China)

机构地区:[1]西安科技大学安全科学与工程学院,西安710054 [2]西安科技大学安全与应急管理研究所,西安710054

出  处:《煤炭技术》2024年第1期114-118,共5页Coal Technology

基  金:国家自然科学基金面上项目(51874237);国家自然科学基金联合基金重点支持项目(U1904210)。

摘  要:为提升煤层瓦斯含量预测精度,提出一种采用遗传模拟退火算法混合优化支持向量机(SVM)参数的瓦斯含量预测模型(GRA-GASA-SVM模型)。该模型将GA和SA整合为遗传模拟退火算法协同优化SVM的参数,以解决传统网格寻优算法取值范围无法确定和单一智能算法优化程度有限等问题。利用灰色关联分析(GRA)压缩数据集维度,建立瓦斯含量预测参数体系并作为GASA-SVM的输入数据集。结果表明:SVM模型、GA-SVM模型和GASA-SVM模型10折交叉验证瓦斯含量预测总平均相对误差分别为15.98%、13.55%和10.58%。相比SVM模型和GA-SVM模型,GASA-SVM模型预测稳定性更优、预测精准度更高且对新样本泛化能力更强。In order to improve the efficiency and effectiveness of coal seam gas content prediction,a gas content prediction model(GRA-GASA-SVM model)using genetic simulated annealing algorithm to hybrid optimize support vector machine(SVM)parameters is proposed.The model integrates GA and SA as a genetic simulated annealing algorithm to collaboratively optimize the parameters of SVM,in order to solve the problems of undetermined value range of traditional grid-seeking algorithm and limited optimization of a single intelligent algorithm.Gray correlation analysis(GRA)is used to compress the dimensionality of the data set,establish the gas content prediction parameter system and serve as the input data set of GASA-SVM.The results showed that the total average relative errors of the SVM model,GA-SVM model and GASA-SVM model were 15.98%,13.55%and 10.58%,respectively,for the 10-fold cross-validation gas content prediction.Compared with the SVM model and the GA-SVM model,the GASA-SVM model has better prediction stability,higher prediction accuracy and better generalization to new samples.

关 键 词:遗传算法(GA) 模拟退火算法(SA) 支持向量机(SVM) 煤层瓦斯含量 灰色关联分析(GRA) 

分 类 号:TD712[矿业工程—矿井通风与安全]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象