Colour formulation prediction for opaque plastics based on an improved particle swarm algorithm

Abstract This study introduces a method for predicting colour formulations for opaque plastics based on an improved particle swarm algorithm. This approach utilises the Kubelka–Munk double‐constant theory to predict the reflectivity of the opaque plastic formulation. Furthermore, the absorption coefficients and scattering coefficients of the substrate and pigments are calculated using the least squares method. The CIELab colour difference is employed as the standard to evaluate the quality of the formulation. Building on these foundations, an improved particle swarm algorithm is proposed for colour formulation prediction. This algorithm employs logic mapping for population initialisation, inertia weights and learning factors related to colour difference. The accuracy and stability of the algorithm is demonstrated in comparison with other algorithms and in prediction of real target formulations.