Simulation of Reservoir Sediment Flushing of the Three Gorges Reservoir Using an Artificial Neural Network

Li, Xueying; Qiu, Jun; Shang, Qi; Li, Fangfang

doi:10.3390/app6050148

Cited by 17 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, machine learning has played an important role in water-related engineering applications, such as reservoir operation [20,21], water management [22,23], turbine operation [24,25], water distribution network [26,27], sediment settling velocity prediction [28], intelligence hydrological model [29,30], rheological prediction model [31,32] etc. Therefore, it is believed that such a method is also applicable for the study of motion characteristics of the single bubbles.…”

Section: Motivationmentioning

confidence: 99%

NewApproach to Predict the Motion Characteristics of Single Bubbles in Still Water

et al. 2019

View full text Add to dashboard Cite

Under the action of gravity, buoyancy, and surface tension, bubbles generated by wave breaking will rupture and polymerize, causing the occurrence of high-speed jets and strong turbulence in nearby water bodies, which in turn affects sea–air exchange, sediment transport, and pollutant movement. These interactions are closely related to the shape and velocity changes in single bubbles. Therefore, understanding the motion characteristics of single bubbles is essential. In this research, a large number of experiments were carried out to serve this purpose. The experimental data were used to develop three machine learning models for the bubble final velocity, bubble drag coefficient, and bubble shape, respectively. The performance of the feed forward back propagation neural network (FBNN) models for the final velocity and drag coefficient were evaluated. The coefficient of determination (R2) and root mean squared error (RMSE) value of final velocity prediction model was recorded at 0.83 and 0.0518, respectively. Meanwhile, for the drag coefficient prediction model, the values are 0.92 for R2 and 0.1534 for RMSE. The models can provide a more accurate output if compared to that from the empirical formulas. K-nearest neighbours (KNN), logistic regression, and random forest were applied as the algorithm while developing the bubble shape classification model. The best performance is achieved by the logistic regression.

show abstract

Section: Motivationmentioning

confidence: 99%

NewApproach to Predict the Motion Characteristics of Single Bubbles in Still Water

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Peng et al (2004) put forth a multi-objective decisionmaking model for reservoir water-sediment joint operation using multi-objective theories and methods. Li et al (2016) used back-propagation error training of artificial neural networks to analyze the relationship between the efficiency of sand flushing of the Three Gorges Reservoir and the factors that affect the efficiency. Bao et al (2007) used the density current total flow differential model to predict the movement of sediment at the dam site of a reservoir and conducted a water-sediment joint operation model to maximize the sediment discharge ratio of the reservoir based on the characteristics of the flood at the dam site.…”

Section: Introductionmentioning

confidence: 99%

A study on sediment avoidance diversion and the coordinated dispatch of water and sediment at an injection-water supply project on a sediment-laden river

Guo

et al. 2021

Engineering Applications of Computational Fluid Mechanics

View full text Add to dashboard Cite

Rivers in the northwestern region of China have a high sediment content, and the construction of reservoirs on these rivers must address the problem of sedimentation that results in a loss of reservoir capacity. In this study, the YZD (Yazidang) reservoir was considered as a typical case, to address the problem of sedimentation in injection-type water supply reservoirs in Northwest China. The temporal and spatial characteristics of the sediment in this water diversion project were analyzed based on available 46-year water and sediment data. The concept of 'sediment avoidance diversion' was proposed, which reduces the entry of sediment into the reservoir. A one-dimensional numerical model for water-sediment coupling was established, and the characteristics of water-sediment erosion and deposition for different operational modes were analyzed. The results show that during a period of high sediment content, large-scale siltation occurs in a water diversion channel. To alleviate sediment deposition in a diversion channel, two control strategies for mitigating siltation were formulated. Considering the pros and cons of these control strategies, a reasonable water-sediment joint operation plan has been proposed to extend the service life of the YZD reservoir. This research provides a theoretical basis for sedimentation treatment and control of similar reservoirs.

show abstract

“…They reported that the ANN and ANFIS models had high predictive accuracy. Li et al (2016) simulated flushing in the reservoir of the Three Gorges Dam, China, using an ANN model. They concluded that the ANN model was significantly capable of relating the prediction of the output sediment to the influential parameters.…”

Section: Introductionmentioning

confidence: 99%

Prediction of longitudinal and transverse profiles of pressure flushing cones using artificial intelligence and data pre-processing

et al. 2021

View full text Add to dashboard Cite

One of the most critical issues in dam reservoir management is the determination of sediment level after flushing operation. Artificial intelligence (AI) methods have recently been considered in this context. The present study adopts four AI approaches, including the Feed-Forward Neural Network (FFNN), Cascade Feed-Forward Neural Network (CFFNN), Gene Expression Programming (GEP), and Bayesian Networks (BNs). Experimental data were exploited to train and test the models. The results revealed that the models were able to estimate the post-flushing sediment level accurately. FFNN outperformed the other models. Furthermore, the importance of model inputs was determined using the τ-Kendall (τ–k), Random Forest (RF), and Shannon Entropy (SE) pre-processing methods. The initial level of sediment was found to be the most important input, while the orifice output flow rate was observed to have the lowest importance in modeling. Finally, inputs of higher weights were introduced to the FFNN model (as the best predictive model), and the analysis of the results indicated that the exclusion of less important input variables would have no significant impact on model performance.

show abstract

Simulation of Reservoir Sediment Flushing of the Three Gorges Reservoir Using an Artificial Neural Network

Cited by 17 publications

References 16 publications

NewApproach to Predict the Motion Characteristics of Single Bubbles in Still Water

NewApproach to Predict the Motion Characteristics of Single Bubbles in Still Water

A study on sediment avoidance diversion and the coordinated dispatch of water and sediment at an injection-water supply project on a sediment-laden river

Prediction of longitudinal and transverse profiles of pressure flushing cones using artificial intelligence and data pre-processing

Contact Info

Product

Resources

About