基于机器学习的半圆形迷宫堤排放系数的估计
Akbar Asgharzadeh-Bonab1, Sajad Bijanvand2, Abbas Parsaie3
1Department of Science and Technology Studies, AJA Command and Staff University, Tehran, Iran.
Scientific reports
|September 26, 2025
概括
先进的机器学习模型准确地预测了半圆迷宫护 (SCLW) 中的放电系数. TabNet-MFO模型在测试中表现出卓越的性能,提供了改进的液压设计预测.
科学领域:
- 水力学和流体力学 流体力学
- 计算工程 计算工程
- 人工智能的人工智能
背景情况:
- 准确的排放系数 (Cd) 预测对于液压结构设计至关重要.
- 半圆形迷宫堤 (SCLWs) 需要精确的液压性能估计.
- 传统的Cd估计方法存在一些局限性.
研究的目的:
- 开发和评估先进的机器学习 (ML) 模型来估计SCLW中的Cd.
- 为了比较各种ML模型的性能,包括TabNet-MFO,ELM-JFO,LightGBM和DT.
- 确定影响SCLW中Cd预测的关键因素.
主要方法:
- 机器学习模型的探索:图表神经网络 (TabNet) 与火焰优化 (MFO),极端学习机器 (ELM) 与Jaya和火算法 (JFO),决策树 (DT) 和光梯度增强机器 (LightGBM).
- 使用可解释增强机 (EBM) 和夏普利添加式扩展 (SHAP) 来确定影响性参数的灵敏度分析.
- 使用统计指标进行绩效评估:R2,RMSE,sMAPE,SI,WMAPE,泰勒图和绩效指数 (PI).
主要成果:
- 上游流深与高度 (h/P) 的比率被确定为影响Cd的最重要因素.
- 在培训中,ELM-JFO表现最好 (PI=166,E'=0.0052),紧随其后的是TabNet-MFO (PI=142,E'=0.0068).
- 在测试中,TabNet-MFO获得了最高的精度 (PI=81.92,E'=0.0118),超过了ELM-JFO,LightGBM和DT.
结论:
- 混合和可解释的ML技术,特别是TabNet-MFO,为SCLW中Cd估计提供了可靠的替代方案.
- 与传统方法相比,开发的ML模型显著提高了流量预测的准确性.
- 这项研究支持通过先进的计算方法来增强液压结构设计.
更多相关视频
相关概念视频
01:26Weir: Problem Solving
446
Water flow in open channels is often measured using hydraulic structures such as weirs, which allow precise calculation of discharge. In a rectangular channel, flow rates are measured using three types of weirs: rectangular sharp-crested, triangular sharp-crested, and broad-crested. The weir head is set at a fixed height above the channel bottom, simplifying calculations and enabling the relationship between depth and flow rate to be analyzed.For the rectangular sharp-crested weir, the flow...
446
01:21Design Example: Creating a Hydraulic Model of a Dam Spillway
678
Scaled hydraulic models of dam spillways provide a practical way to replicate and study the intricate flow dynamics of these structures. Often built to a 1:15 ratio, these models allow for observing critical water behavior, such as velocity distribution, flow patterns, and energy dissipation.
678
01:24Weir
460
A weir is a hydraulic structure designed to partially obstruct an open channel, enabling precise control and measurement of water flow. By forcing water to flow over or through it, a weir allows for accurate determination of discharge rates, making it an essential tool in water resource management. These structures are extensively used in regulating river flows, irrigation systems, and flood control channels.Types of Weirs and Their FeaturesWeirs are categorized primarily into sharp-crested and...
460
01:30Typical Model Studies
619
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
619
01:30Underflow Gates
366
Underflow gates are vital for controlling water flow in irrigation canals. The three main types of underflow gates — vertical, radial, and drum gates — serve different purposes while ensuring effective flow management. Vertical gates move up and down, generating a free-flowing water jet; radial gates pivot to regulate the flow; and drum gates rotate for precise adjustments. The flow through these gates is influenced by downstream conditions, resulting in free or drowned outflow.Free and...
366
01:24Rapidly Varying Flow
451
Rapidly varying flow (RVF) in open channels is characterized by abrupt changes in flow depth over a short distance, with the rate of depth change relative to distance often approaching unity. These flows are inherently complex due to their transient and multi-dimensional nature, making exact analysis difficult. However, approximate solutions using simplified models provide valuable insights into their behavior.Key Features of Rapidly Varying FlowRVF is commonly observed in scenarios involving...
451