Data underlying the publication: Dynamic compartment models: Towards a rapid modeling approach for fed-batch fermentations

This data includes the files for developing a workflow to simulate fed-batch fermentations using a hybrid modeling approach based on flow-informed compartment models (CFD-CM) and a machine learning (ML) method. The proposed workflow circumvents the need for re-calibration of the compartment model upon changes in the working volume and stirring rate of the system. This is done using an inferring module based on a neural network. The methods to deploy the framework are described in the publication 'Dynamic compartment models: Towards a rapid modeling approach for fed-batch fermentations'. The dataset includes the case and data files from FLUENT to generate the parameterization of the compartment models (i.e., intercompartmental fluxes - .csv files) used for training and testing of the neural network, which is also included. These files aim to ensure the reproducibility of the results presented in the corresponding publication.

本数据集包含用于开发工作流的相关文件，该工作流可基于流动信息隔室模型（CFD-CM）与机器学习（ML）方法，对补料分批发酵过程进行模拟。所提出的工作流可避免当系统工作体积与搅拌速率发生变化时，需对隔室模型进行重新校准的问题，这一功能可通过基于神经网络的推理模块实现。该框架的部署方法已在论文《动态隔室模型：面向补料分批发酵的快速建模方法》中进行了阐述。本数据集包含来自FLUENT的算例与数据文件，用于生成隔室模型的参数化结果（即隔室间通量——.csv格式文件），这些参数将用于神经网络的训练与测试，相关神经网络文件也一并包含在内。所有文件均旨在确保对应论文中所呈现结果的可复现性。