Discharge flow rate under sheet piles, a prediction model
Discharge flow rate under sheet piles, a prediction model
The discharge flow rate beneath water-retaining structures is an important parameter in designing water retaining structures. This paper presents a framework to model and predict discharge flow rate using an evolutionary-based technique. The proposed method is data-driven and searches mathematical structures to representing a complicated system. A comprehensive data set including around a thousand data lines is used to create and test the prediction model. Data divided into training and testing data sets (testing data set not introduced to the model in the training stage) using special statistical approach to ensure relevance, validity and compatibility of the training and testing data sets. The main advantage of the proposed models is to provides an optimum explicit structure for the model directly from the data unlike black box models and the capability of the model is tested by introducing an unseen data set to ensure the model is capable of generalisation. Results revealed the high accuracy of the developed model in predicting flow rates both for seen and unseen data cases. A parametric study on the presented models confirmed consistency of the parameter relationships with the database and expected behaviour of the system based on traditional empirical methods.
A. Ahangar Asr; A. Johari; A. A. Javadi
18th European Conference on Soil Mechanics and Geotechnical Engineering (ECSMGE2024)
B - Geohazards
Contact Information
- Secretary General - Dr A M McNamara
- Email: [email protected]
- Phone: +44 20 7040 8154
- City, University of London
- Northampton Square
- London EC1V 0HB. United Kingdom