Mechanical systems under periodic loading due to rotary operation usually respond in measurements with a superposition of sinusoids whose frequencies were integer or fractional integer multiples of the reference shaft speed. When the rotary machines are running, acousto-mechanical signals acquired from the machines enable to reveal their operation status and machine conditions. The study proposed a DSP-based adaptive angular-velocity Vold-Kalman filtering order tracking (AV2KF-OT) algorithm with online real-time nature for signal interpretation and machine condition monitoring. Theoretical derivation and numerical implementation of the computation scheme was briefly introduced. An online real-time condition monitoring system based on the AV2KF-OT algorithm, which was implemented through both a digital signal processor (DSP) and a man-machine interface coded by using LabVIEW®, was developed. An experimental task, the startup detection on the fluid-induced whirl performed through a journal-bearing rotor rig, was used to justify the proposed technique.