| 引用本文: | 王荣涛,赖喜德,陈小明.基于人工神经网络的混流式水轮机转轮多目标优化[J].灌溉排水学报,0,():-. |
| WANG Rong Tao,LAI Xi de,CHEN Xiao ming.基于人工神经网络的混流式水轮机转轮多目标优化[J].灌溉排水学报,0,():-. |
|
| 摘要: |
| 【目的】探究一种同时提升混流式水轮机运行效率、空化性能及运行稳定性的优化方法，为混流式水轮机转轮的多目标优化提供技术途径。【方法】以转轮叶片进出口安放角、安装角为优化变量，通过对叶片几何参数随机离散抽样获取样本数据库，基于CFD数值计算获取各样本的性能参数，进而建立同时考虑混流式水轮机转轮效率、出口旋流数以及空化系数的多目标函数；基于人工神经网络建立优化变量与多目标函数的映射关系，最后采用遗传算法对转轮叶片的18个几何参数进行全局寻优，并对优化前后的转轮叶片性能进行对比分析。【结果】在导叶开度为112°且运行水头分别为160m、175m、180m的3个工况下，优化后的转轮效率相较优化前分别提高了0.22%、0.56%、0.60%；叶片压力分布情况得到有效改善；转轮无叶区与尾水管锥管段处压力脉动幅值显著降低。【结论】叶片进口安放角的优化程度越大，混流式水轮机综合性能的提升幅度越大。 |
| 关键词: 混流式水轮机;转轮;多目标优化设计;人工神经网络;遗传算法 |
| DOI： |
| 分类号:TK730.3 |
| 基金项目: |
|
| Multi-Objective Optimization of Francis Runner Based on Artificial Neural Network Model |
|
WANG Rong Tao, LAI Xi de, CHEN Xiao ming
|
|
School of Energy and Power Engineering, Xihua University
|
| Abstract: |
| 【Background】At present, for technical renovation of turbine equipment in hydropower plant, due to its low investment, quick effect and high economic benefit, it attracts worldwide attention. The main purpose of turbine equipment modification of hydropower station is to increase capacity or improve its operation performance. Generally, it is impossible to make large modification to embedded components during turbine modification. Most of these modifications are aimed at runners or guide vanes of water diversion mechanism. Therefore, it is very important to study an effective multi-objective runner optimization design method to ensure the efficiency, cavitation performance and hydraulic stability of the unit as well as the comprehensive performance of the unit under different operating conditions. 【Purpose】To explore an optimization method which can simultaneously improve the operation efficiency, cavitation performance and operation stability of the Francis turbine, and provide a technical approach for multi-objective optimization of the Francis turbine runner.【Method】Taking the position angle and installation angle of runner blade inlet and outlet as optimization variables, the sample database was obtained by random discrete sampling of blade geometry parameters, and the performance parameters of each sample were obtained based on CFD numerical calculation. Then, a multi-objective function was established considering runner efficiency, swirl number at outlet and cavitation coefficient of Francis turbine at the same time. The mapping relationship between optimization variable and multi-objective function is established based on artificial neural network. Finally, the 18 geometric parameters of runner blades are optimized globally by genetic algorithm, and the performance of runner blades before and after optimization is compared and analyzed.【Result】Under the conditions of 112 degrees guide vane opening and 160m, 175m and 180m running head respectively, the optimized runner efficiency was increased by 0.22%, 0.56% and 0.60% respectively compared with that before optimization. The pressure distribution of blades is effectively improved. The pressure fluctuation amplitude at the vaneless area of the runner and the conical section of the draft tube is significantly reduced.【Conclusion】The greater the optimization of blade inlet placement angle, the greater the improvement of comprehensive performance of Francis turbine. |
| Key words: Francis Turbine; Runner; Multi-Objective Optimization Design; Artificial Neural Network; Genetic Algorithm. |
