Careful selection and location of sensors are of key importance in the construction and implementation of an effective condition monitoring system. There is a continual call for depletion of maintenance and operational costs of rotating machine elements. Health monitoring of bearings, which is regarded as a crucial component of rotating machinery, is expected to facilitate in the preclusion of machine breakdown and ensure the machine availability by maintenance actions in time. The effectiveness and reliability of measurement approaches for monitoring the condition of the bearing are influenced by both the signal processing techniques and locations of the sensors selected for fault characteristic extraction. This paper proposes a low cost Non-contact optimal sensor placement (NC-OSP) methodology in order to get information of high quality related to the dynamic features of the machines. Experiments were conducted using different bearing conditions under different operating conditions and sensor placement positions. Mathematical models have been proposed based on the response parameters and input variables experimentation using response surface methodology. Results indicate that the most effective input variable to control the response parameters viz. FFT vibration amplitude of characteristic frequency and RMS value of time domain was the shaft speed followed by load and angle of incidence. The responses proposed by the optimal models have been observed at 8° angle of incidence with maximum load and speed. The optimal outcomes have been validated experimentally which proved that the predicted results were in sync with the actual ones. The proposed work has significant potential in industrial environment with complex systems, where the condition monitoring approach with proper placement of sensors can play an important role.