The deformation prediction models of Wuqiangxi concrete gravity dam are developed,including two statistical models and a deep learning model.In the statistical models,the reliable monitoring data are firstly determine...The deformation prediction models of Wuqiangxi concrete gravity dam are developed,including two statistical models and a deep learning model.In the statistical models,the reliable monitoring data are firstly determined with Lahitte criterion;then,the stepwise regression and partial least squares regression models for deformation prediction of concrete gravity dam are constructed in terms of the reliable monitoring data,and the factors of water pressure,temperature and time effect are considered in the models;finally,according to the monitoring data from 2006 to 2020 of five typical measuring points including J23(on dam section 24^(#)),J33(on dam section 4^(#)),J35(on dam section 8^(#)),J37(on dam section 12^(#)),and J39(on dam section 15^(#))located on the crest of Wuqiangxi concrete gravity dam,the settlement curves of the measuring points are obtained with the stepwise regression and partial least squares regression models.A deep learning model is developed based on long short-term memory(LSTM)recurrent neural network.In the LSTM model,two LSTMlayers are used,the rectified linear unit function is adopted as the activation function,the input sequence length is 20,and the random search is adopted.The monitoring data for the five typical measuring points from 2006 to 2017 are selected as the training set,and the monitoring data from 2018 to 2020 are taken as the test set.From the results of case study,we can find that(1)the good fitting results can be obtained with the two statistical models;(2)the partial least squares regression algorithm can solve the model with high correlation factors and reasonably explain the factors;(3)the prediction accuracy of the LSTM model increases with increasing the amount of training data.In the deformation prediction of concrete gravity dam,the LSTM model is suggested when there are sufficient training data,while the partial least squares regression method is suggested when the training data are insufficient.展开更多
由于沅水水系五强溪水库流域面积大,流量控制站少,且洪水进入库区后,洪水波的传播方式变化较大,因此五强溪水库近坝区的洪水预报难度大。为提高五强溪库区洪水预报精度,采用XAJ-DCH模型(Xin′anjiang Digital Channel Model)对近坝区201...由于沅水水系五强溪水库流域面积大,流量控制站少,且洪水进入库区后,洪水波的传播方式变化较大,因此五强溪水库近坝区的洪水预报难度大。为提高五强溪库区洪水预报精度,采用XAJ-DCH模型(Xin′anjiang Digital Channel Model)对近坝区2016~2020年间13场洪水进行模拟,模型河道汇流分别采用了非线性水库法和马斯京根法,根据两种汇流方法的特点制定了两种不同的洪水预报方案。模拟结果表明:XAJ-DCH模型中两种河道演算方法均表现良好且简单实用,13场洪水的确定性系数基本位于0.7以上。非线性水库方法相比于马斯京根法考虑了河段断面情况以及水力特性,能够体现洪水运动的时空变化,且只需要率定河道糙率,其他参数如河道坡降、河宽以及河段长均可根据数字高程模型进行估计;马斯京根法需要率定4个河道参数,但马斯京根法模拟结果相比于非线性水库方法稍好。研究成果可为科学有效开展库区洪水预报、提高预报精度提供参考。展开更多
The Nanhua basin in South China hosts well-preserved middle-late Neoproterozoic sedimentary and volcanic rocks that are critical for studying the basin evolution, the breakup of the supercontinent Rodinia, the nature ...The Nanhua basin in South China hosts well-preserved middle-late Neoproterozoic sedimentary and volcanic rocks that are critical for studying the basin evolution, the breakup of the supercontinent Rodinia, the nature and dynamics of the "snowball" Earth and diversification of metazoans. Establishing a stratigraphic framework is crucial for better understanding the interactions between tectonic, paleoclimatic and biotic events recorded in the Nanhua basin, but existing stratigraphic correlations remain debated, particularly for pre-Ediacaran strata. Here we report new Laser Ablation Inductively Coupled Plasma Mass Spectrometry(LA-ICPMS) U-Pb zircon ages from the middle and topmost Wuqiangxi Formation(the upper stratigraphic unit of the Banxi Group) in Siduping, Hunan Province, South China. Two samples show similar age distribution, with two major peaks at ca. 820 Ma and 780 Ma and one minor peak at ca. 910 Ma, suggesting that the Wuqiangxi sandstone was mainly sourced from Neoproterozoic rocks. Two major age peaks correspond to two phases of magmatic events associated with the rifting of the Nanhua basin, and the minor peak at ca. 910 Ma may correspond to the Shuangxiwu volcanic arc magmatism, which represents pre-collision/amalgamation subduction on the southeastern margin of the Yangtze Block. The youngest zircon group from the topmost Wuqiangxi Formation has a weighted mean age of 714.6±5.2 Ma, which is likely close to the depositional age of the uppermost Banxi Group. This age, along with the ages reported from other sections, constrains that the Banxi Group was deposited between ca. 820 Ma and ca. 715 Ma. The age of 714.6±5.2 Ma from the top of the Wuqiangxi Formation is indistinguishable with the SIMS U-Pb age of 715.9± 2.8 Ma from the upper Gongdong Formation in the Sibao village section of northern Guangxi, South China. It is also, within uncertainties, overlapped with two TIMS U-Pb ages from pre-Sturtian strata in Oman and Canada. These ages indicate that the Jiangkou(Sturtian) glaciation in South China started at ca. 715 Ma instead of ca. 780 Ma and support a globally synchronous initiation of the Sturtian glaciation at ca. 715 Ma.展开更多
文摘The deformation prediction models of Wuqiangxi concrete gravity dam are developed,including two statistical models and a deep learning model.In the statistical models,the reliable monitoring data are firstly determined with Lahitte criterion;then,the stepwise regression and partial least squares regression models for deformation prediction of concrete gravity dam are constructed in terms of the reliable monitoring data,and the factors of water pressure,temperature and time effect are considered in the models;finally,according to the monitoring data from 2006 to 2020 of five typical measuring points including J23(on dam section 24^(#)),J33(on dam section 4^(#)),J35(on dam section 8^(#)),J37(on dam section 12^(#)),and J39(on dam section 15^(#))located on the crest of Wuqiangxi concrete gravity dam,the settlement curves of the measuring points are obtained with the stepwise regression and partial least squares regression models.A deep learning model is developed based on long short-term memory(LSTM)recurrent neural network.In the LSTM model,two LSTMlayers are used,the rectified linear unit function is adopted as the activation function,the input sequence length is 20,and the random search is adopted.The monitoring data for the five typical measuring points from 2006 to 2017 are selected as the training set,and the monitoring data from 2018 to 2020 are taken as the test set.From the results of case study,we can find that(1)the good fitting results can be obtained with the two statistical models;(2)the partial least squares regression algorithm can solve the model with high correlation factors and reasonably explain the factors;(3)the prediction accuracy of the LSTM model increases with increasing the amount of training data.In the deformation prediction of concrete gravity dam,the LSTM model is suggested when there are sufficient training data,while the partial least squares regression method is suggested when the training data are insufficient.
文摘由于沅水水系五强溪水库流域面积大,流量控制站少,且洪水进入库区后,洪水波的传播方式变化较大,因此五强溪水库近坝区的洪水预报难度大。为提高五强溪库区洪水预报精度,采用XAJ-DCH模型(Xin′anjiang Digital Channel Model)对近坝区2016~2020年间13场洪水进行模拟,模型河道汇流分别采用了非线性水库法和马斯京根法,根据两种汇流方法的特点制定了两种不同的洪水预报方案。模拟结果表明:XAJ-DCH模型中两种河道演算方法均表现良好且简单实用,13场洪水的确定性系数基本位于0.7以上。非线性水库方法相比于马斯京根法考虑了河段断面情况以及水力特性,能够体现洪水运动的时空变化,且只需要率定河道糙率,其他参数如河道坡降、河宽以及河段长均可根据数字高程模型进行估计;马斯京根法需要率定4个河道参数,但马斯京根法模拟结果相比于非线性水库方法稍好。研究成果可为科学有效开展库区洪水预报、提高预报精度提供参考。
基金supported by the Ministry of Science and Technology(No.2011CB808806)the National Natural Science Foundation of China (No. 41402026)
文摘The Nanhua basin in South China hosts well-preserved middle-late Neoproterozoic sedimentary and volcanic rocks that are critical for studying the basin evolution, the breakup of the supercontinent Rodinia, the nature and dynamics of the "snowball" Earth and diversification of metazoans. Establishing a stratigraphic framework is crucial for better understanding the interactions between tectonic, paleoclimatic and biotic events recorded in the Nanhua basin, but existing stratigraphic correlations remain debated, particularly for pre-Ediacaran strata. Here we report new Laser Ablation Inductively Coupled Plasma Mass Spectrometry(LA-ICPMS) U-Pb zircon ages from the middle and topmost Wuqiangxi Formation(the upper stratigraphic unit of the Banxi Group) in Siduping, Hunan Province, South China. Two samples show similar age distribution, with two major peaks at ca. 820 Ma and 780 Ma and one minor peak at ca. 910 Ma, suggesting that the Wuqiangxi sandstone was mainly sourced from Neoproterozoic rocks. Two major age peaks correspond to two phases of magmatic events associated with the rifting of the Nanhua basin, and the minor peak at ca. 910 Ma may correspond to the Shuangxiwu volcanic arc magmatism, which represents pre-collision/amalgamation subduction on the southeastern margin of the Yangtze Block. The youngest zircon group from the topmost Wuqiangxi Formation has a weighted mean age of 714.6±5.2 Ma, which is likely close to the depositional age of the uppermost Banxi Group. This age, along with the ages reported from other sections, constrains that the Banxi Group was deposited between ca. 820 Ma and ca. 715 Ma. The age of 714.6±5.2 Ma from the top of the Wuqiangxi Formation is indistinguishable with the SIMS U-Pb age of 715.9± 2.8 Ma from the upper Gongdong Formation in the Sibao village section of northern Guangxi, South China. It is also, within uncertainties, overlapped with two TIMS U-Pb ages from pre-Sturtian strata in Oman and Canada. These ages indicate that the Jiangkou(Sturtian) glaciation in South China started at ca. 715 Ma instead of ca. 780 Ma and support a globally synchronous initiation of the Sturtian glaciation at ca. 715 Ma.
