首页> 外文会议>Frontiers on Separation Science and Technology >A NEW REDUCED METHOD FOR THERMAL PROPERTY CALCULATION OF DISTILLATION
【24h】

A NEW REDUCED METHOD FOR THERMAL PROPERTY CALCULATION OF DISTILLATION

机译:一种减少精馏热性能的新方法

获取原文
获取原文并翻译 | 示例

摘要

It is a very time-consuming job to perform rigorous thermodynamics calculation in the dynamic simulation of the distillation, especially when the simulation relates to multi-components, which takes about 70 to 80 percent of the total calculation time of a distillation process. A new reduced method for thermodynamics calculation of distillation based on the artificial neural net (ANN) is developed in the paper. The paper established several reduced models using ANN, such as model of vapor-liquid equilibrium calculation, model of enthalpy calculation and model of temperature calculated from given enthalpy. Examples are used to test the method. The results show that when used the ANN-based thermodynamics model in the dynamic simulation of distillation, much time can be saved with little accuracy lost. According to various multi-components simulations, the calculation performs about 10 times to 20 times faster than using rigorous model and with an error below 2%. It is showed thermodynamic properties reduced model based on ANN is an original, fast, and accurate method.
机译:在蒸馏的动态模拟中执行严格的热力学计算是非常耗时的工作,尤其是在模拟涉及多组分的情况下,这需要花费蒸馏过程总计算时间的70%到80%。本文提出了一种基于人工神经网络(ANN)的精馏热力学简化计算新方法。本文建立了几种基于人工神经网络的简化模型,如汽液平衡计算模型,焓计算模型和根据给定焓计算的温度模型。实例用于测试该方法。结果表明,将基于ANN的热力学模型用于蒸馏的动态模拟时,可以节省很多时间,而损失的精度很少。根据各种多组件模拟,该计算的执行速度比使用严格模型快10到20倍,并且误差低于2%。结果表明,基于人工神经网络的热力学性能降低模型是一种新颖,快速,准确的方法。

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