Damage state assessment method for remanufacturing blanks based on magnetic and surface texture feature fusion

In order to improve the accuracy and efficiency of damage assessment, a novel method to evaluate the damage state for remanufacturing blanks based on the magnetic and surface texture feature fusion was developed. Through modeling of the magnetic and surface texture features, sample entropy parameters from the magnetic intensity and its gradients were extracted, and energy, entropy, contrast, and correlation parameters from surface texture were obtained. The two-layered feature fusion model comprised of the data layer and the index layer was established. In the data layer, parameters of the magnetic and surface texture features and their nonlinear mapping relationships with damage were obtained. In the index layer, the information fusion between the magnetic and surface texture features was carried out by Dempster-Shafer (D-S) evidence theory. Finally, fatigue test samples were selected to verify the feasibility of the proposed method. Results show that the method can be used to determine the damage states of the remanufacturing blanks, which provides theoretical and technical decision support for remanufacturability of the components.