| 地表下沉系数选取的LWPSO-BP方法研究 |
| |
| 引用本文： | 张飞,刘文生,霍志国,方书山.地表下沉系数选取的LWPSO-BP方法研究[J].测绘科学,2011,36(6):128-130. |
| |
| 作者姓名： | 张飞 刘文生 霍志国 方书山 |
| |
| 作者单位： | 1. 辽宁工程技术大学测绘与地理科学学院,辽宁阜新,123000
2. 辽宁工程技术大学土木与交通学院,辽宁阜新,123000 |
| |
| 基金项目： | 辽宁省教育厅创新团队项目(2008T086) |
| |
| 摘 要： | 针对BP神经网络自身收敛速度慢、容易陷入局部极小点的缺点,本文以线性下降惯性权重粒子群优化算法(LLWPSO)为前处理器,优化BP网络的权值和阈值,利用实测资料数据,建立LWPSO-BP的地表下沉系数预计模型,并同普通BP模型预计结果对比结果表明:LWPSO-BP神经网络不仅训练速度快,而且预测精度明显提高,该模型对地...
|
| 关 键 词： | 粒子群 BP神经网络 线性下降惯性权重 地表下沉系数 选取研究 |
LWPSO-BP algorithm for calculation of surface subsidence coefficient |
| |
| ZHANG Fei,LIU Wen-sheng,HUO Zhi-guo,FANG Shu-shan.LWPSO-BP algorithm for calculation of surface subsidence coefficient[J].Science of Surveying and Mapping,2011,36(6):128-130. |
| |
| Authors: | ZHANG Fei LIU Wen-sheng HUO Zhi-guo FANG Shu-shan |
| |
| Institution: | ①(①School of Geomantic,Liaoning Technology University,Liaoning Fuxin 123000,China;②Institute of Civil Engineering and Transportation,Liaoning Technology University,Liaoning Fuxin 123000,China) |
| |
| Abstract: | In view of disadvantages of BP neural network:low convergence rates,easily falling into the partial minimum point and so on,this article saw Particle Swarm Optimization based on linear decrease inertia weight(LWPSO) algorithm as a former processor,optimized weights and thresholds of BP network.It used the actual material data,established the LWPSO-BP estimate model,and contrasted with ordinary BP model estimate result.The result indicated that the LWPSO-BP neural network could not only train in a fast speed,but also forecast in a distinctly enhanced precision,which would have certain application value in selecting the surface submersion coefficient. |
| |
| Keywords: | Particle Swarm Optimization BP neural network linear decrease inertia weight surface submersion coefficient selection research |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
