Application of Improved GMDH Models to Predict Local Scour Depth at Complex Bridge Piers

Abstract

Scour depth prediction is a vital issue in bridge pier design. Recently, good progress has been made in the development of artificial intelligence (AI) to predict scour depth around hydraulic structures base such as bridge piers. In this study, two hybrid intelligence models based on combination of group method of data handling (GMDH) with harmony search algorithm (HS) and shuffled complex evolution (SCE) have been developed to predict local scour depth around complex bridge piers using 82 laboratory data measured by authors and 615 data points from published literature. The results were compared to conventional GMDH models with two kinds of transfer functions called GMDH1 and GMDH2. Based upon the pile cap location, data points were divided into three categories. The performance of all utilized models was evaluated by the statistical criteria of R, RMSE, MAPE, BIAS, and SI. Performances of developed models were evaluated by experimental data points collected in laboratory experiments, together with commonly empirical equations. The results showed that GMDH2SCE was the superior model in terms of all statistical criteria in training when the pile cap was above the initial bed level and completely buried pile cap. For a partially-buried pile cap, GMDH1SCE offered the best performance. Among empirical equations, HEC-18 produced relatively good performances for different types of complex piers. This study recommends hybrid GMDH models, as powerful tools in complex bridge pier scour depth prediction.

Scour Detection with Monitoring Methods and Machine Learning Algorithms—A Critical Review

“…Although the process is time-consuming, Bayesian hyperparameter optimization is a method to set the parameters of a gradient tree boosting model and grid search; while GPU acceleration provided more speed in the selection process [96]. Another algorithm providing successful applications for scour estimation [97,98] is group method of data handling, a procedure which organizes itself through models created step-by-step, based on their performance assessment on a group of multi-input-single-output data couples [99]. Grid search is one of the most common methods to set parameters of group method of data handling models.…”

Numerical investigations of the flow around four non-aligned circular cylinders

“…Although the main attention is on the cylinders themselves, the entire system (the array of cylinders) is affected by the flow. Example of such behavior can be found at Ghodsi and Khanjani [1], where the authors investigated the use of an artificial intelligence method to predict scour depth at complex bridge piers.…”