Ph.D. Student , James COOK University (JCU)
Hydraulic Water Retaining Structures (HWRS), such as dams, weirs and regulators are important infrastructures and necessary for water management. Seepage analysis under HWRS has a substantial consequence of the design of HWRS. One of the biggest challenging in design of HWRS is to determine the accurate seepage characteristics with complex flow conditions, and simultaneously to find the optimum design considering safety and cost. Therefore, this study concentrates on developing a linked simulation-optimization (S-O) model for non-homogenous anisotropic soil properties. This is achieved via linking the numerical seepage simulation (Geo-Studio/SEEPW) with the evolutionary optimization solver using Genetic Algorithm (GA). Since, a direct linking of numerical model with optimization model is computationally expensive and time consuming, an accurate surrogate model is integrated in the S-O instead a numerical model. A Support vector machine regression (SVM) surrogate model is linked with the optimization model to achieve the optimum hydraulic design of HWRS. The seepage characteristics of optimum design resulted in by S-O are evaluated by comparing with the numerical seepage modeling (SEEPW) solutions. The comparison, in general, shows good agreement. Accordingly, the S-O methodology is potentially applicable for providing safe, efficient and economical design of HWRS constructed on a complex seepage flow domain.