Multi-objective fractional-order particle swarm optimization algorithms for data processing of multi-wavelength pyrometer

This paper focuses the algorithm of the true temperature inversion for high temperature targets with unknown emissivity by transforming multi-spectral true temperature inversion into multi-objective minimum optimization. Two improved fractional-order particle swarm optimizations (IFOPSO), high-order nonlinear time-varying inertia weight (Hntiw) IFOPSO and global-local best values (Glbest) IFOPSO, are proposed to obtain the true temperature by solving the multi-objective minimum optimization. Combining the inherent advantages of fractional-order calculus to jump out of the local extreme value, the Hntiw IFOPSO algorithm is proposed by replacing the linear time-varying inertia weights with nonlinear functions related to the total number of iterations and the current number of iterations. The Glbest IFOPSO algorithm is designed by using the global local optimal inertia weight and acceleration constant to update the particle velocity and position values, which improves the multi-objective optimization ability and the accuracy of the true temperature inversion. The effectiveness of the proposed methods is verified by the simulation with typical spectral emissivity models and the measured data from rocket tail flame.