Jump to:

• Introduction
• Topics
• Timetable
• Submission Guidelines
• Editors

Introduction

Many optimization problems in process engineering can be formulated as expensive black box problems whose solutions are limited by the number of ‘evaluations’ (e.g. experiments, expensive simulations, process setpoint changes). Recently, there has been exciting progress in artificial intelligence and the development of machine learning models, which enable accurate surrogate models for optimization in process systems engineering. Furthermore, the increase in data availability, computational power and storage has revealed numerous applications for such technologies in this field. Typically, the derived models are data-driven, in that they describe statistical relationships and correlations between data. This special collection is dedicated to the coupling of machine learning models with optimization algorithms for advancing engineering applications. We aim to highlight research efforts that incorporate machine learning techniques into computational optimization methods for model development and its usage in process design, operation and optimization of the next generation of physicochemical and biochemical processes.

Topics

The topics of interest for this special collection include, but are not limited to:

• Surrogate models in mixed-integer (non)linear programming (MINLP)
• Optimization with deep learning surrogates
• Expensive black-box optimization for optimal design and/or operation of processes
• Supply chain optimization via surrogate modelling
• Dynamic optimization via machine learning
• Data-driven solution of dynamic systems
• Bayesian optimization for uncertainty quantification
• Global optimization with surrogates
• Stochastic and robust optimization surrogates
• Real-time optimization with machine learning

Timetable

Authors welcome to submit manuscripts as soon as they are ready, with a final deadline of June 1st, 2022. Articles will be published as soon as possible after acceptance, in the interest of allowing authors to disseminate their work without unnecessary delay, and added to a curated page for the collection of articles. An editorial reflecting on the insights of the articles will be published later in 2022.

Submission Guidelines

Please note the following key details, with more information available in the DCE Instructions for Authors:

• Templates: DCE LaTeX and Word templates are available. For initial submission, authors are able to provide a single manuscript file, if this is easier, but we will need source files for the manuscript and all figures on revision. 
• Article types: We anticipate that most articles will be research articles, but the journal also publishes translational papers, reviews, position papers and perspectives.
• Abstract and Impact Statement: Authors should provide both an abstract that summarises the paper (250 words or less) and beneath it an impact statement (120 words describing the significance of the findings in language that can be understood by a wide audience).
• Disclosure statements: At the end of the article text – ahead of the references – authors should provide the following statements:
• Competing interests: detail any financial, professional, contractual or personal situations that could be perceived to exert an undue influence on an authors’ presentation of their work, or state “None”. 
• Funding: provide details of any grant or other direct financial support the authors received to produce the work, or a statement that “This work received no specific grant from any funding agency, commercial or not-for-profit sectors.” 
• Data availability: authors are encouraged but not required to make replication materials available via a public repository. A data availability statement should be included in the article that describes where replication materials can be accessed (including the DOI from the repository), or if they cannot be made publicly available the reason for this. For more details and example data availability statements, see the journal’s policy on Transparency and Openness Promotion. Published articles that link to replication materials will receive Open Data and Open Materials badges to highlight these resources to readers.



When submitting your contribution please select the "Data-driven Optimization in Process Engineering" Special Collection in the drop down menu. Please contact dce@cambridge.org with any queries about article preparation.

Editors

Antonio del Rio Chanona, Imperial College London, UK (DCE Associate Editor)
Chrysoula D Kappatou, Imperial College London, UK (DCE Guest Editor)