Modeling and prediction of surface roughness for running-in wear using Gauss-Newton algorithm and ANN

- A mathematical model is developed to express evolution of surface roughness as function of time during running-in wear process. No such model is existing in the literature.
- The model is non-linear so a novel technique, Gauss-Newton algorithm, is used to estimate the model parameters.
- Artificial neural network is also used to model the surface roughness in the paper.
- The results of the model are compared with that of the model developed using artificial neural network. Both the models give results which are very close to experimental results.
- Running-in being very important during initial wear of the mechanical components, the model can be used to predict the surface roughness during the wear process, e.g. cylinder liner wear, polishing, honing, etc.