Bed load prediction in gravel-bed rivers using wavelet kernel extreme learning machine and meta-heuristic methods

Roushangar, Kiyoumars; Shahnazi, Saman

doi:10.1007/s13762-019-02287-6

Cited by 23 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In SVM, model behavior is largely dependent on the RBF kernel parameter (γ), which can lead to under-fitting and overfitting in the prediction process (Roushangar & Shahnazi 2019). Figure 8 illustrates the statistical indices via gamma values of the SVM model (fed with model (V)).…”

Section: Resultsmentioning

confidence: 99%

Insights into the prediction capability of roughness coefficient in current ripple bedforms under varied hydraulic conditions

Roushangar

Shahnazi

2021

Journal of Hydroinformatics

View full text Add to dashboard Cite

Ubiquitous flow bedforms such as ripples in rivers and coastal environments can affect the transport conditions as they constitute the bed roughness elements. The roughness coefficient needs to be adequately quantified owing to its significant influence on the performance of hydraulic structures and river management. This work intended to evaluate the sensitivity and robustness of three machine learning (ML) methods, namely, Gaussian process regression (GPR), artificial neural network (ANN), and support vector machine (SVM) for the prediction of the Manning roughness coefficient of channels with ripple bedforms. To this purpose, 840 experimental data points considering various hydraulic conditions were prepared. According to the obtained results, GPR was found to accurately predict the Manning's coefficient with input parameters of Reynolds number (Re), depth to width ratio (y/b), the ratio of the hydraulic radius to the median grain diameter (R/D50), and grain Froude number (). Moreover, sensitivity analysis was implemented with proposed ML approaches which indicated that the ratio of the hydraulic radius to the median grain diameter has a considerable role in modeling the Manning's coefficient in channels with ripple bedforms.

show abstract

Section: Resultsmentioning

confidence: 99%

Insights into the prediction capability of roughness coefficient in current ripple bedforms under varied hydraulic conditions

Roushangar

Shahnazi

2021

Journal of Hydroinformatics

View full text Add to dashboard Cite

show abstract

“…where constant C is the penalty coefficient, C > 0. The Lagrange function of the optimization problem described in equation (4) can be constructed as 38…”

Section: Svr Control Principlementioning

confidence: 99%

Roadheader horizontal swing movement based on VP technology and SVR algorithm

Liu

Zhao

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

In tunnel construction, over-excavation and under-excavation by the roadheader often occur, which can lead to rough excavation cross-sections that require subsequent treatment resulting in additional time and cost. With a view to improving the quality of excavated tunnels, increasing the speed of the roadheader in tunneling applications, and accurately controlling the excavation process, a virtual prototype (VP) of the roadheader is built using Pro/Engineer, ADAMS, ANSYS, and EASY5. A mechanical model of the system is established and relationships between hydraulic piston expansion length, speed, and boom swing angle are determined. Then, a support vector regression (SVR) internal model controller is introduced into the roadheader swing system. An electromechanical fluid coupling automatic control system model is also established. Combining VP technology with the SVR algorithm, an internal model and inverse model of the roadheader horizontal swing system are obtained. Multi-domain co-simulations are performed. When the SVR internal model controller is incorporated, the gyration platform is more reliable, and the target position can be quickly tracked by the system. The cutting test bench of roadheader was built, and the cutting experiments were carried out by using SVR and PID control methods. Although the PID control system has a faster response, it is only 1.61 s faster than SVR, and the PID control method has a much higher over-excavation amount than SVR control method, and the maximum over-excavation amount is 3.22 times of SVR controller. Therefore, the SVR controller has better control over the over-excavation phenomenon and higher control accuracy. So the proposed method can be used to effectively solve the over-excavation and under-excavation problem.

show abstract

“…However, the sediment transport process often changes rapidly with strong temporal variation and features complex non-linear characteristics (Li et al, 2010); Thus, the traditional artificial intelligence model may yield results with relatively unsatisfying accuracy and robustness if the time-history of flow and sediment transport processes is ignored. In fact, in the process of determining the discharge, water level and suspended sediment concentrations (SSC) at a specific point of the river highly depend on upstream and past conditions (Roushangar, K., and Shahnazi, S., 2019). What's more, the relationships of S-Z and Q-Z in a river of an increasing discharge are thoroughly different from those at a decreasing discharge, which is a typical feature of river dynamics.…”

Section: Introductionmentioning

confidence: 99%

Variation of dominant discharge along the riverbed based on numerical and deep-learning models: A case study in the Middle Huaihe River, China

Zhang

Wang

et al. 2022

Journal of Hydrology

View full text Add to dashboard Cite

Bed load prediction in gravel-bed rivers using wavelet kernel extreme learning machine and meta-heuristic methods

Cited by 23 publications

References 32 publications

Insights into the prediction capability of roughness coefficient in current ripple bedforms under varied hydraulic conditions

Insights into the prediction capability of roughness coefficient in current ripple bedforms under varied hydraulic conditions

Roadheader horizontal swing movement based on VP technology and SVR algorithm

Variation of dominant discharge along the riverbed based on numerical and deep-learning models: A case study in the Middle Huaihe River, China

Contact Info

Product

Resources

About