Performance optimisation of a normalised operational assessment system using hybrid population intelligence algorithm

Aiming at the dynamic constraints and MOPs faced by the normalised operation appraisal system in industrial environments, this paper proposes a hybrid swarm intelligence framework that integrates PSO, GA and ACO. By constructing a hierarchical optimisation architecture - based on the synergistic mechanism of discrete decision-making layer, continuous parameter optimisation layer and variable operation layer a multimodal information fusion strategy and an adaptive parameter adjustment method are innovatively introduced. Experiments based on real industrial operation data show that compared with the traditional optimisation algorithms, the proposed method demonstrates improvements in response time and resource utilisation, with balanced multi-objective performance under dynamic constraints, especially in the dynamic constraint scenarios with stable convergence characteristics and robustness. The engineering deployment verifies the practical value of the framework in complex industrial systems and provides a new technical path for intelligent operation assessment.