English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Nonlinear model predictive control (NMPC) solves a multivariate optimizationproblem to estimate the system's optimal control inputs in each control cycle.Such optimization is made more difficult by several factors, such asnonlinearities inherited in the system, highly coupled inputs, and variousconstraints related to the system's physical limitations. These factors makethe optimization to be non-convex and hard to solve traditionally. Geneticalgorithm (GA) is typically used extensively to tackle such optimization inseveral application domains because it does not involve differentialcalculation or gradient evaluation in its solution estimation. However, thesize of the search space in which the GA searches for the optimal controlinputs is crucial for the applicability of the GA with systems that requirefast response. This paper proposes an approach to accelerate the geneticoptimization of NMPC by learning optimal search space size. The proposedapproach trains a multivariate regression model to adaptively predict the bestsmallest search space in every control cycle. The estimated best smallest sizeof search space is fed to the GA to allow for searching the optimal controlinputs within this search space. The proposed approach not only reduces theGA's computational time but also improves the chance of obtaining the optimalcontrol inputs in each cycle. The proposed approach was evaluated on twononlinear systems and compared with two other genetic-based NMPC approachesimplemented on the GPU of a Nvidia Jetson TX2 embedded platform in aprocessor-in-the-loop (PIL) fashion. The results show that the proposedapproach provides a 39-53\% reduction in computational time. Additionally, itincreases the convergence percentage to the optimal control inputs within thecycle's time by 48-56\%, resulting in a significant performance enhancement.The source code is available on GitHub.

Accelerating genetic optimization of nonlinear model predictive control by learning optimal search space size