Comfort Study of General Aviation Pilot Seats Based on Improved Particle Swam Algorithm (IPSO) and Support Vector Machine Regression (SVR)

Little work has been carried out to predict the comfort of aircraft seats, a component in close contact with human body during travel. In order more accurately nonlinear and complex relationship between subjective objective evaluations comfort, this paper proposes prediction method based on Improved Particle Swarm Algorithm (IPSO) optimized Support Vector Machine Regression (SVR). Focusing problems too-fast convergence low accuracy traditional particle swarm algorithm (PSO), improved is obtained by linearly decreasing dynamic adjustments inertia weight ω, self-learning factor c1, social c2; then, penalty parameter C kernel function σ SVR are IPSO algorithm, IPSO-SVR established. The was 94.00%, root mean square error RMSE 0.37, absolute value MAE 0.32, goodness fit R2 0.92. results show that model can seat under different angles backrest tilt provide reference research for related industries. higher accuracy, its feasible generalizable, meaning it reliable basis inclinations, as well providing