- Title
- Research on BP neural network model for stability assessment of loess slopes based on particle swarm optimization and partial least-squares regression
- Creator
- Gong, Bin; Wang, Shanyong; Tang, Chun'an
- Relation
- World Transport Convention (WTC): The Way Connecting China and the World. Proceedings of the inaugural World Transport Convention (Beijing, China 04-06 June, 2017)
- Relation
- http://wtc2017.csp.escience.cn/dct/page/70073
- Publisher
- China Highway & Transportation Society
- Resource Type
- conference paper
- Date
- 2017
- Description
- The assessment of loess slope stability is a highly complex nonlinear problem. There are many factors that influence the stability of loess slopes. Some of them have the characteristic of uncertainty. Meanwhile, the relationship between different factors may be complicated. The existence of multiple correlation will affect the objectivity of stability analysis and prevent the model to make correct judgments. In this paper, the main factors affecting the stability of loess slopes are analysed by means of the partial least-squares regression (PLSR). After that, two new synthesis variables with better interpretation to the dependent variables are extracted. By this way, the multicollinearity among variables is overcome preferably. Moreover, the BP neural network is further used to determine the nonlinear relationship between the new components and the slope safety factor. Then, a new BP model based on the particle swarm optimization and partial least-squares regression, which is initialized by the particle swarm optimization algorithm is developed. The network with global convergence capability is simpler and more efficient. The test results of the model show very good precision, which indicates that the model is feasible and effective for stability evaluation of loess slopes.
- Subject
- slope engineering; stability assessment; BP neural network; particle swarm optimization; partial least-squares regression
- Identifier
- http://hdl.handle.net/1959.13/1390214
- Identifier
- uon:33012
- Language
- eng
- Reviewed
- Hits: 1261
- Visitors: 1221
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|