| 摘要: |
| 针对特高拱坝运行初期温度场的非稳定性和时效的非单调增长性，发展变形监测和预报模型，并提出构建方法。通过主成分上的分层聚类法选取代表性温度测点，将其实测值作为温度变量；引入包含徐变及其恢复项的时效变量表达式，论证其表达谷幅变形的能力。进而考虑库水位、实测温度、组合时效等变量，应用增强回归树方法提出特高拱坝运行初期变形监测和预报模型，并通过后向消减变量建立优化模型。分析各变量对变形的边际效应，得到其相对影响大小；借助部分依赖图，辨识变量间相关关系及其对坝体变形的影响规律，揭示变形机制。将该模型应用于某特高拱坝，验证该模型的可行性和有效性。并将结果与支持向量机、多元回归模型进行对比分析，表明该模型的优越性。 |
| 关键词: 特高拱坝 变形 运行初期 安全监测 增强回归树 主成分分析 支持向量机 |
| DOI： |
| 分类号:TV642 |
| 基金项目:国家重点研发计划(2018YFC0406705)；国家自然科学(51879169; 51779155) |
|
| Deformation forecasting model and its modeling method of super high arch dams during initial operation periods |
|
Hu Jiang
|
|
State Key Laboratory of Hydrology-water Resources and Hydraulic Engineering,Nanjing Hydraulic Research Institute
|
| Abstract: |
| The dam temperature field has not been stabilized, and the time dependent effect does not increase non-monotonously for super high arch dams during initial operation period. Therefore the special deformation monitoring and forecasting model was developed, and its modeling method was proposed in this paper. The key temperature measurement points were chosen by the hierarchical clustering on principal component method, and the corresponding time series were inputted as thermal predictors. The combined time dependent effect, including creep and its restoration, was introduced as time dependent deformation. This time dependent effect was employed to validate its characterization for the valley contraction deformation. Considering the predictor variables such as reservoir water level, adopted measured temperatures, estimated time dependent effect, the simple boosted regression tree (BRT) based dam deformation prediction model was constructed. Through the backward elimination method, a simplified BRT (SBRT) model only including major predictors was obtained. The marginal effects of variables on deformation were analyzed, and the relative influences can be quantitatively analyzed. With the help of partial dependence plot, the correlations among variables and the influences of variables on deformation can be explored, and the deformation mechanism can be revealed. The model was applied to a super high arch dam, and the case study verified the feasibility of the model. The results were compared with the support vector machine model, the traditional multiple regression models, which shows the superiority of the developed model. |
| Key words: super high arch dam deformation initial impoundment period safety monitoring boosted regression tree principal component analysis support vector machine |
