Update 19 June 2023: To accommodate additional demand, we have extended the final submission deadline to 31 July 2023.
Control Systems Engineering is the study of dynamical systems within engineering processes and real-world systems. The goal is to develop models and algorithms which direct a system’s inputs towards some desired goal, such as maximising the system’s output, or ensuring the system remains in a steady-state. Control theory is a widely studied area dating back to the late 19th century and has fundamentally revolutionised industrial Engineering and the modern technology era. Real-world applications of control theory include cruise control in cars, autopilot systems in aircraft, industrial automation, packet routing in the internet, heating and cooling ventilation systems and GPS navigation, to name a few. Early research in this area focused on small-scale, linear systems. However, modern Engineering systems are increasingly high-dimensional, strongly nonlinear, and often have multilevel outputs, as seen in air turbulence, neuroscience, finance, epidemiology, autonomous robots, and self-driving cars. In these current and future applications, data-driven modelling and control will be vitally important to ensure safety and trust within autonomous systems.
This special collection is focused on research which explores recent developments in machine learning and artificial intelligence to improve automation within Engineering. Through this special issue we will highlight work which is impactful in areas such as control systems theory, process automation and reinforcement learning for Engineering applications.
Topics
Topics of interest for this special issue include, but are not limited to:
- Deep reinforcement learning in dynamical systems
- Data-driven systems optimisation
- Adaptive multi-agent systems
- Machine learning for nonlinear control systems
- Robust and adaptive AI for process control
Authors are encouraged make code and data that supports the findings openly available in a recognised repository and to link to them in the Data Availability Statement in the article. We recognise this may not be possible in all circumstances. See the DCE Journal’s Transparency and Openness Promotion policy. Open Data and Open Materials badges will be displayed on published articles that link to replication materials, as a recognition of open practices.
We also encourage authors to take consider enhancing their articles with additional materials.
Cambridge’s Open Engage platform is a location for sharing early research outputs and additional materials. It can, for example, be used to host working papers, pre-prints, presentations and posters. Materials uploaded to Open Engage will receive a DOI (and therefore be citable objects), allowing authors to link to them in their submitted article.
We welcome authors to submit manuscripts as soon as they are ready, with a final deadline of 31 July 2023. 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 at a later date.
Please note the following key details, with more information available in the DCE Instructions for Authors:
Templates: DCE provides the following optional templates:
- DCE LaTeX template files
- Use Overleaf (a LaTeX-based collaborative authoring tool; read about benefits of this tool)
- DCE Word template
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: Translational papers, 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)
When submitting your contribution please select the Machine Learning for Control Systems Engineering Special Collection in the drop down menu. Please contact [email protected] with any queries about article preparation.
- Christopher Nemeth (Lancaster University)
- Benjamin Guedj (UCL & Inria)