Global Optimization of the Hydraulic-Electromagnetic Energy-Harvesting Shock Absorber for Road Vehicles With Human-Knowledge-Integrated Particle Swarm Optimization Scheme

This article proposes a human-knowledge-integrated particle swarm optimization (Hi-PSO) scheme to globally optimize the design of hydraulic-electromagnetic energy-harvesting shock absorber (HESA) for road vehicles. A newly developed k-fold learning framework is key Hi-PSO scheme, which runs k groups (folds) individual local (using selected cycle), and validation other k-1 testing cycles) with concept digital twin introduced into HESA. It aims achieve optimum energy recovery efficiency in both cycles cycles. Within framework, nearest-neighborhood algorithm incorporate human knowledge (e.g., ISO standards) so that computational load can be reduced through downsizing spaces. Experiments have been conducted evaluate damping performance under conditions (duty used learning) global (six duty covering main equivalent amplitudes frequencies suspension's operation). Compared conventional PSO algorithm, shown more robust by achieving 5.17% higher mean value 10 trials while same maximum efficiency. The result obtained 20 mm/1.5 Hz condition achieves an average 59.07%.