大坝安全监控的递推PLSR模型  被引量:1

Recursive PLSR Model for Dam Safety Monitoring

在线阅读下载全文

作  者:李波[1] 李大治[2] 张英达 

机构地区:[1]河海大学水利水电工程学院 [2]沈阳市浑蒲灌区管理处,辽宁沈阳110141 [3]中国水利水电第三工程局云南分局,云南保山678300

出  处:《水力发电》2008年第6期101-104,共4页Water Power

基  金:国家自然科学基金项目(50539010,50539110,50579010);雅砻江水电开发联合研究基金项目(50539030-1-3);国家科技支撑计划项目(20006BAC14B03);中国水电工程顾问集团公司科技项目(CHC-KJ-2007-02)

摘  要:在大坝安全监测数据分析中,传统的监控模型大多采用的是静态分析方法,但是,随着数据的积累,静态分析法将会影响计算效率,预测精度也会降低。针对这一问题,对初始样本数据按时间次序分成多个时间块,用偏最小二乘回归法对各时间块建模,在此基础上,对选定的时间块分配权重,以递推的方式,构建了加权块式递推偏最小二乘回归模型。实例表明,与其他静态模型相比,该模型的效率和预测精度较高,在大坝安全监控领域具有一定的推广价值。In the analysis of dam safety monitoring data, static analysis methods are mostly adopted by monitoring model, however, with the accumulation of data, if these methods still are used, calculating rate will be affected, and forecasting accuracy will be reduced. Aiming at the problem, original sample data are separated into many time blocks by time se- quence, which are modeled by partial least squares regression method, on the basis of this, the weights of selected time blocks are allocated, weighted block recursive partial least squares regression model is constructed by means of recursive wise. The result of an example shows that compared with other static models, the efficiency and forecasting performance of weighted block recursive partial least squares regression model are greatly improved, which has certain popularized importance in field of dam safety monitoring.

关 键 词:大坝安全监控 递推PLSR模型 偏最小二乘回归法 

分 类 号:TV698.1[水利工程—水利水电工程]

 

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