A Novel Hybrid Intelligent Prediction Model for Valley Deformation: A Case Study in Xiluodu Reservoir Region, China

The narrowing deformation of reservoir valley during the initial operation period threatens the long-term safety of the dam,and an accurate prediction of valley deformation(VD)remains a challenging part of risk mitigation.In order to enhance the accuracy of VD prediction,a novel hybrid model combining Ensemble empirical mode decomposition based interval threshold denoising(EEMD-ITD),Differential evolutions—Shuffled frog leaping algorithm(DE-SFLA)and Least squares support vector machine(LSSVM)is proposed.The non-stationary VD series is firstly decomposed into several stationary subseries by EEMD;then,ITD is applied for redundant information denoising on special sub-series,and the denoised deformation is divided into the trend and periodic deformation components.Meanwhile,several relevant triggering factors affecting the VD are considered,from which the input features are extracted by Grey relational analysis(GRA).After that,DE-SFLA-LSSVM is separately performed to predict the trend and periodic deformation with the optimal inputs.Ultimately,the two individual forecast components are reconstructed to obtain the final predicted values.Two VD series monitored in Xiluodu reservoir region are utilized to verify the proposed model.The results demonstrate that:(1)Compared with Discrete wavelet transform(DWT),better denoising performance can be achieved by EEMD-ITD;(2)Using GRA to screen the optimal input features can effectively quantify the deformation response relationship to the triggering factors,and reduce the model complexity;(3)The proposed hybrid model in this study displays superior performance on some compared models(e.g.,LSSVM,Backward Propagation neural network(BPNN),and DE-SFLA-BPNN)in terms of forecast accuracy.

Response characteristics of plunge pool slabs of Xiaxiluodu Hydropower deformation conditions

The key problem of the energy dissipation scheme of the arch dam body flood discharge and plunge pool below the dam is the stability problem of the plunge pool slab.As the protection structure of the underwater bed,the plunge pool slab bears the continuous impact of high-speed water flow.The hourly average dynamic water pressure on the slab is one of the main loads directly affecting the stability of the slab and is the main factor causing its erosion destruction.After the impoundment of the Xiluodu Hydropower Station,the measuring line of valley width in the plunge pool area has been continuously shrinking.By 2020,the cumulative shrinking value is about 80 mm.In light of the general background condition of valley shrinkage,daily inspection,annual detailed inspection,underwater inspection and drainage inspection of the plunge pool found that the plunge pool has experienced different degrees of damage,which greatly influences the long-term safety stability of the plunge pool.In this paper,the prototype observation data of flood discharge is used as the input load of pulsatingpressure,and the stress and displacement distribution of the plunge pool structure under the vibration load of flood discharge is analyzed under the condition that the stress and strain state of the plunge pool is changed under the influence of valley displacement.The results show that the stress,strain,and displacement distribution of the plunge pool are mainly caused by valley deformation,the vibration caused by flood discharge is little in influence,and the impact effect of deep hole flood discharge tongue on the plunge pool slab is weak.