• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International Journal of Heat and Mass Transfer >Prediction of the minimum film boiling temperature using artificial neural network
【24h】

Prediction of the minimum film boiling temperature using artificial neural network

机译：人工神经网络预测最小薄膜沸腾温度

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This work studies the application of artificial neural network (ANN) to predict the minimum film boiling temperature (T_(min)) for various substrate rods quenched in high- and low-pressure distilled water pools. The ANN was trained using 379 experimental data collected from literature. Liquid subcooling temperature (T_(sub)), fluid to the substrate material thermophysical properties (β_f/β_w), system saturated pressure (P_(sat)) and length to diameter ratio (L/D) are utilized as inputs, whereas T_(min) was viewed as the output. The number of neurons and hidden layers were determined based on the precision of results. The trained ANN predicted the experimental data with a mean absolute error (MAE) of approximately 5%, and a determination coefficient (R~2) greater than 0.95 for all data, utilizing an arrangement of 12 neurons inside 2 hidden layers. The estimated results were less than ±10% for 90% of all data, and ±20% for 99% of all data. Among the available correlations for T_(min) in literature, this work shows a success in the first attempt in implementing ANN to predict T_(min) accurately.
机译：该工作研究人工神经网络（ANN）在高压蒸馏水池中淬灭的各种基板杆的最小膜沸腾温度（T_（min））的应用。 ANN使用从文献中收集的379个实验数据进行培训。液体过冷温度（T_（Sub）），流体到底物材料热神族（β_F/β_W），系统饱和压力（P_（饱和））和长度与直径比（L / D）用作输入，而T_（ Min）被视为产出。基于结果的精度确定神经元和隐藏层的数量。训练笼预测了具有大约5％的平均绝对误差（MAE）的实验数据，以及所有数据大于0.95的确定系数（R〜2），利用2个隐藏层内部的12个神经元的布置。估计结果为所有数据的90％少于±10％，均为所有数据的99％±20％。在文献中的T_（min）的可用相关性中，这项工作在第一次尝试中实现了实现ANN以准确地预测T_（min）的成功。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号