首页> 外文会议>Italian Conference on Chemical and Process Engineering(ICheaP-6) vol.2; 20030608-11; Pisa(IT) >Use of Deterministic Model and Artificial Neural Networks in the Dextran Production System Simulation
【24h】

Use of Deterministic Model and Artificial Neural Networks in the Dextran Production System Simulation

机译:确定性模型和人工神经网络在葡聚糖生产系统仿真中的应用

获取原文
获取原文并翻译 | 示例

摘要

Dextran is a biopolymer, with great potential of utilization in cosmetic industry and in the medical area. This work is focused on development of hybrid model for description of the dynamic behavior for a dextran reactor. This model is developed by coupling Artificial Neural Networks (ANN) and deterministic model. The hybrid model will be used as mathematical representation of the process, for applications in real time control and optimization and mainly as soft-sensors. Mathematical models were based on mass balances involving enzyme and substrate distributions between solid and liquid phases; energy balances were not considered because the thermal effects are negligible. For the construction of the hybrid model ("Gray Box" model) it was accomplished the training of a ANN that predicts the dextran system kinetic. After adjustment of the ANN, it is coupled to the deterministic model supplying the dynamic profiles of the process variables: Substract concentration, in two stages , efficiency and productivity.
机译:葡聚糖是一种生物聚合物,在化妆品工业和医疗领域具有巨大的利用潜力。这项工作的重点是开发混合模型,以描述葡聚糖反应器的动态行为。该模型是通过结合人工神经网络(ANN)和确定性模型开发的。混合模型将用作过程的数学表示,用于实时控制和优化中的应用,并且主要用作软传感器。数学模型基于涉及酶和底物在固液相之间的分布的质量平衡;没有考虑能量平衡,因为热效应可以忽略不计。对于混合模型(“灰箱”模型)的构建,完成了对预测葡聚糖系统动力学的ANN的训练。调整人工神经网络后,将其与提供过程变量动态配置文件的确定性模型耦合:在两个阶段,即效率和生产率中减去浓度。

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