Model Predictive Evolutionary Temperature Control via Neural-Network-Based Digital Twins

Created by W.Langdon from gp-bibliography.bib Revision:1.8120

@Article{ates:2023:Algorithms,

• author = "Cihan Ates and Dogan Bicat and Radoslav Yankov and Joel Arweiler and Rainer Koch and Hans-Jorg Bauer",
• title = "Model Predictive Evolutionary Temperature Control via {Neural-Network-Based} Digital Twins",
• journal = "Algorithms",
• year = "2023",
• volume = "16",
• number = "8",
• pages = "Article No. 387",
• keywords = "genetic algorithms, genetic programming",
• ISSN = "1999-4893",
• URL = "https://www.mdpi.com/1999-4893/16/8/387",
• DOI = "doi:10.3390/a16080387",
• abstract = "In this study, we propose a population-based, data-driven intelligent controller that leverages neural-network-based digital twins for hypothesis testing. Initially, a diverse set of control laws is generated using genetic programming with the digital twin of the system, facilitating a robust response to unknown disturbances. During inference, the trained digital twin is used to virtually test alternative control actions for a multi-objective optimisation task associated with each control action. Subsequently, the best policy is applied to the system. To evaluate the proposed model predictive control pipeline, experiments are conducted on a multi-mode heat transfer test rig. The objective is to achieve homogeneous cooling over the surface, minimizing the occurrence of hot spots and energy consumption. The measured variable vector comprises high dimensional infrared camera measurements arranged as a sequence (655,360 inputs), while the control variable includes power settings for fans responsible for convective cooling (3 outputs). Disturbances are induced by randomly altering the local heat loads. The findings reveal that by using an evolutionary algorithm on measured data, a population of control laws can be effectively learnt in the virtual space. This empowers the system to deliver robust performance. Significantly, the digital twin-assisted, population-based model predictive control (MPC) pipeline emerges as a superior approach compared to individual control models, especially when facing sudden and random changes in local heat loads. Leveraging the digital twin to virtually test alternative control policies leads to substantial improvements in the controller's performance, even with limited training data.",
• notes = "also known as \cite{a16080387}",

}

Genetic Programming entries for Cihan Ates Dogan Bicat Radoslav Yankov Joel Arweiler Rainer Koch Hans-Jorg Bauer

Citations