In heavy rotating machines and assembly lines, bearing failure in any one of the rotating machines results in shut down of many other machines and affects the overall cost and quality of the product. Condition monitoring of bearing systems avoids breakdown and saves preventive and corrective maintenance time and cost. This research paper proposes advanced strategies in early fault detection of taper rolling bearings. In view of this, a mathematical model based- fault diagnosis and support vector machine (SVM) is proposed in this work. The mathematical model using dimension analysis by matrix method (DAMM) and SVM is developed to predict the vibration characteristic of the rotor bearing system. Various types of defects created using an electric discharge machine (EDM) are analyzed by correlating dependent and independent parameters. Experiments were performed to classify the rotor dynamic characteristic of healthy and unhealthy bearing. Experimental results are used to validate the model obtained by DAMM and SVM. Experimental results showed that vibration characteristics are evaluated by using a theoretical model and SVM. This contribution to the service life extension and efficiency improvement, so as to reduce bearing failure. Thus, the automatic online diagnosis of bearing faults is possible with a developed model-based by DAMM and SVM.