The Study of the Performance of Data- Driven Models to Predict the Scour Depth Caused by the Aerated Vertical Jet
Publish Year: 1399
نوع سند: مقاله ژورنالی
زبان: English
View: 83
This Paper With 11 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_JISE-43-4_007
تاریخ نمایه سازی: 12 مهر 1400
Abstract:
High flow discharges coming from the hydraulic structures usually carry a high-velocity jet of flow, which could have different short- and long-term impacts on the river mechanics and the habitat conditions. Scouring is one of the major effects of the incoming flow jet, which, once aerated, has a dynamic behavior and structure. Plunge pools are hydraulic structures to prevent the severe damages of the scouring phenomena. In the present study, due to the high complexity of constructing a physical model, the effect of air entrainment on scoured hole’s depth is assessed using the Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) methods. Each soft computing model’s performance on the scouring is compared to a Nonlinear Regression Method’s result using different statistical measures (RMSE, ME, MAE). The prediction accuracy of ANN, ANFIS, and nonlinear regression using RMSE was calculated as ۰.۰۱۳۷, ۰.۰۱۱, and ۰.۰۲۶۲, respectively. This study presents a novel achievement in measuring and predicting the scoured hole’s depth as one of the most critical phenomena in hydro-environmental science.
Keywords:
Authors
Babak Lashkar-Ara
Associate Professor, Civil Engineering Department, Jundi-Shapur University of Technology, Dezful, Iran
Saman Baharvand
PhD Candidate, Department of Civil Engineering, University of Texas at Arlington, P.O. Box ۱۹۰۱۹, Arlington, TX ۷۶۰۱۹, USA.
Leila Najafi
Instructor in Civil Engineering Department Jundi-Shapur University of Technology
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :