Dynamic modeling and optimization of sustainable algal production with uncertainty using multivariate Gaussian processes
Dynamic modeling and optimization of sustainable algal production with uncertainty using multivariate Gaussian processes
复制标题
DOI：
10.1016/j.compchemeng.2018.07.015
复制
发表时间：
2018-10-04
影响因子：
4.3
通讯作者：
del Rio-Chanona, Ehecatl Antonio
中科院分区：
文献类型：
--
作者：
Bradford, Eric;Schweidtmann, Artur M.;del Rio-Chanona, Ehecatl Antonio
动态建模是更好地理解复杂生物过程和确定过程控制的最佳操作条件的重要工具。目前，两种建模方法已被应用于生物系统：动力学建模，这需要深入的机械知识，和人工神经网络（ANN），在大多数情况下，不能纳入过程的不确定性。本研究的目标是引入一种替代的建模策略，即高斯过程（GP），它包含了不确定性，但不需要复杂的动力学信息。为了测试该策略的性能，基于现有的实验数据集，将GP应用于微藻生长和叶黄素生产的模型，并与以前的ANN的结果进行比较。此外，在不确定性下进行动态优化，避免了模型有效性之外的过度乐观优化。结果表明，GP具有可比的预测能力，人工神经网络的长期动态生物过程建模，同时考虑模型的不确定性。这有力地表明了它们在生物过程系统工程中的潜在应用。(C)2018爱思唯尔有限公司版权所有。
Dynamic modeling is an important tool to gain better understanding of complex bioprocesses and to determine optimal operating conditions for process control. Currently, two modeling methodologies have been applied to biosystems: kinetic modeling, which necessitates deep mechanistic knowledge, and artificial neural networks (ANN), which in most cases cannot incorporate process uncertainty. The goal of this study is to introduce an alternative modeling strategy, namely Gaussian processes (GP), which incorporates uncertainty but does not require complicated kinetic information. To test the performance of this strategy, GPs were applied to model microalgae growth and lutein production based on existing experimental datasets and compared against the results of previous ANNs. Furthermore, a dynamic optimization under uncertainty is performed, avoiding over-optimistic optimization outside of the model's validity. The results show that GPs possess comparable prediction capabilities to ANNs for long-term dynamic bioprocess modeling, while accounting for model uncertainty. This strongly suggests their potential applications in bioprocess systems engineering. (C) 2018 Elsevier Ltd. All rights reserved.