4.7 Article

Evolutionary neural architecture search for surrogate models to enable optimization of industrial continuous crystallization process

期刊

POWDER TECHNOLOGY
卷 405, 期 -, 页码 -

出版社

ELSEVIER
DOI: 10.1016/j.powtec.2022.117527

关键词

Crystallization; Surrogate assisted optimization; Artificial neural networks; Neural architecture search; Evolutionary algorithms; Multi objective optimization

资金

  1. Depart-ment of Biotechnology, Government of India [BT/PR34209/AI/133/19/2019]
  2. Department of Science and Technology, Government of India [DST/NSM/R&D_HPC_Applications/2021/23]

向作者/读者索取更多资源

This paper proposes an alternative model using Artificial Neural Networks to optimize the crystallization process, achieving a significant speed improvement while maintaining accuracy through a neural architecture search strategy for hyperparameter tuning.
Optimal performance of the crystallization process is of utmost importance for industries handling bulk commodity chemicals to pharmaceuticals. Such an optimization exercise becomes extremely time expensive as the mathematical models mimicking such complex processes involve the solution of Integro-Differential Population Balance Equations using High Resolution Finite Volume Methods. In order to build a fast and robust data based alternative model, a surrogate assisted approach using Artificial Neural Networks has been proposed here. To overcome the heuristics-based estimation of the hyper-parameters in ANNs, we aim to contribute a novel Neural Architecture Search strategy for the auto-tuning of hyper-parameters integrated with sample size determination techniques. While solving a multi-objective optimization of crystallization process ensuring maximum productivity, the results from surrogates are compared with those of a high-fidelity physics driven model, which reports five order of magnitude speed improvement without sacrificing much on accuracy.(c) 2022 Elsevier B.V. All rights reserved.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据