This study proposes a hybrid model that utilizes a physical model and Artificial Neural Networks (ANN) approach to predict surface roughness during cylinder bore honing with an improved prediction efficiency of 90% compared to the standalone physical model. As a critical component of internal combustion engine technology, improvement in the surface roughness of cylinder bore can significantly reduce friction, wear and oil consumption, resulting in improved engine performance. Desired surface roughness in cylinder bore is imparted by honing, which serves as the terminal process in cylinder bore manufacturing. The cylinder bore honing process consists of rough honing, fine honing, and plateau honing stage. Each stage further involves variables such as honing stone geometry, grain size, grain concentration, honing speed, pressure, feed, over travel, number of strokes, etc. In literature, different approaches have been proposed to determine the influence of process parameters on the surface roughness of the honed cylinder bore. However, these approaches have their limitations. Experimental based studies are limited by the number of parameters that can be considered, analytical analysis methods involve extensive calculations resulting in reduced computational efficiency and accuracy, while machine learning approaches require a large amount of data. To overcome these limitations, this study employs a hybrid model to investigate the evolution of roughness at the rough and fine stage of the honing process. A two-phase approach is employed; first, a physical model is used to determine the surface roughness using various parameters. Secondly, these results are applied to train the ANN that can predict surface roughness for new parameters with a difference of less than 10% from the physical model.