With increasing complexity in the heavy duty construction equipment, early fault detection ofcertain components in the machine becomes more and more challenging due to too many faultcodes generated when a failure occurs. The axle is one such component. The axle transfers driv-ing torque from the transmission to the wheels and axle failure may result in costly downtime ofconstruction equipment. To reduce service cost and to improve uptime, adequate condition moni-toring based on sensor data from the axle is considered by for instance measuring vibrations on theaxle. Further, the analysis of the data collected has been has been carried out using adequate sig-nal processing methods. The results indicate that the vibration properties of the axle are relevantfor early fault detection of the axle. Thus, the health of the axle may be continuously monitoredon-board using the vibration information and if the axle health starts to degrade a service and/orrepair may be scheduled well in advance of a potential axle failure and in that way the downtimeof a machine may be reduced and costly replacements and repairs avoided.