In modern industry, with the expanding of business level and capacity, the maintenance cost and workplace hazards increase dramatically. Condition-based Monitoring (CM) method is a proving technology that is capable to determine an optimized checking point for maintenance to be carried out prior to the failure occurrence, which results in reduced maintenance cost and improved system performance. This paper proposes a signal analysis technique which evaluates vibration levels with spectrum analysis to discriminate normal random variations from abnormal signatures trends. Firstly, the critical components are determined based on a weighted factor comparison to system failure, failure rate, maintenance cost, the difficulty of acquisition monitoring data. Secondly, vibration data will be collected, classified and stored into database. Thirdly, vibration levels are evaluated by applying FFT spectrum analysis to digitize the running condition of the system. The spectrum patterns are recognized and matched for the frequency grade of defects. The monitoring result will be used to determine an immediate maintenance to be undertaken, or predict time to failure. The proposed CM system has been implemented on various equipments and its successfully application in the local company has been discussed as a case study.