Collaborative Optimization of Air Compressor Units Based on MSI-BWO Algorithm

To improve the operational efficiency of compressor units and reduce waste, a Multi-Strategy Improved Beluga Whale Optimization (MSI-BWO) algorithm is proposed for the collaborative combination optimization of compressor units in an air compressor plant. Although the original Beluga Whale Optimization (BWO) algorithm, which simulates the social and predatory behaviors of beluga whales, shows certain potential in global optimization problems, there is still room for improvement in convergence speed and accuracy. The MSI-BWO algorithm integrates elite opposition-based learning, dynamic refraction opposition-based learning, and cyclone foraging strategies. Among these, the elite opposition-based learning strategy enhances the diversity and quality of the initial population by constructing an opposition-based search space for elite individuals, thereby accelerating the initial convergence speed of the algorithm. The dynamic refraction opposition-based learning strategy draws on the physical principle of light refraction to dynamically and adaptively adjust the algorithm’s search space, significantly improving its global search capability. The cyclone foraging strategy mimics the unique spiral foraging behavior of manta rays, skillfully balancing the algorithm’s performance between global exploration and local fine-grained search. Through rigorous validation on unit optimization problems, the MSI-BWO algorithm demonstrates superior performance in convergence speed, accuracy, and stability compared to the original algorithm and other popular intelligent optimization algorithms, and the algorithm achieved an energy-saving effect of about 8.31%, while significantly improving the imbalance problem.