Machinery prognosis is the forecast of the remaining operational life, future condition, or probability of reliable operation of equipment based on the acquired condition monitoring data. The full process of prediction that is based on the condition of the equipment and the failure physics may be separated into two steps. The first step is diagnostics. It includes characterization of the defect in terms of location (in what component and where in the component), type, and extent. The second step is prognostics. It includes using the characterization of the defect with the estimated load in order to estimate the propagation of the defect as a function of time. Models for defect propagation can be statistical models or physical models (mathematical description of the physics of the failure growth), such as crack propagation. Physical models attempt to combine system-specific mechanical knowledge, defect growth formulas, and vibration data to provide knowledge-rich prognosis output. The goal of this research is to enable the estimation of the remaining useful life of rolling element bearings. One of the common reasons for rolling element bearings failure is the rolling contact fatigue (RCF). RCF occurs when two bodies roll/slide with respect to each other, producing alternating stresses over a very small volume beneath the contact surface. Complete understanding of the fatigue process is critical for estimation of the bearing remaining useful life and allows planning maintenance actions. In the current work, it is assumed that the spall generation, on the surface of the raceway, is a result of RCF. This process is modeled based on continuum damage mechanics and later implemented using ABAQUS Finite Element software. Different meshes were constructed for simulation purposes. An ideal line contact, representing the cylindrical roller bearing, is used to simulate rolling contact conditions. The geometry and initiation time of the simulated spalls are in good agreement with published simulated and experimental data.