The invention relates to the technical field of rubber materials, and relates to a rubber multi-stress aging life prediction method based on an Eyring model and a PSO
algorithm, and the method comprises the steps of multi-stress aging experiment data collection, single degradation track curve modeling, reference condition and
acceleration factor definition, Eyring model establishment and parameter identification, and extrapolation of life under natural use conditions. According to the method, the stability of parameter
estimation is remarkably improved by introducing a two-stage parameter identification method, a parameter initial value is obtained through individual
curve fitting, then a shape parameter alpha and a position parameter gamma are fixed, a
rate parameter beta is identified again, and the parameter standard deviation can be reduced; the ratio of the reaction rates is introduced as an
acceleration factor for parameter identification instead of directly identifying the reaction rates, so that the dimensional influence and
experimental system errors are effectively eliminated, data of different batches of materials under different experimental conditions have comparability, and the
engineering applicability of the model is remarkably improved; the PSO
algorithm is adopted to carry out global parameter optimization, so that the prediction precision and the calculation efficiency can be effectively improved.