<p>Journal bearings play a critical role in supporting high-speed rotors in turbo machinery, making predictive maintenance essential. Vibration monitoring in rotating machinery facilitates the early detection of abnormal patterns, which can be extracted from vibration signals. Identifying deviations from normal operational states is crucial for preventing costly downtimes and enhancing operational efficiency. This paper aims to introduce two precise and computationally cost-effective methods that are efficient for online and offline applications, issuing early warnings by using the RMS (Root Mean Square) of velocity of bearing vibrations in steady-state conditions. The first method complies with the ISO 20816 standard, providing a health indicator for machinery by monitoring changes in the RMS velocity, referred to as the <i>CDI</i>_<i>alarm</i> (Change Detection Index for alarm emission) index. The second method identifies pattern changes in the RMS velocity as a time signal, known as the <i>DSA</i> (Delta Skewness Autocorrelation) index. Finally, the effectiveness of these methods was validated using actual data from a V94.2 gas turbine, demonstrating their accuracy and simplicity. The primary advantage of these two procedures is their utilization of the accelerometer sensor installed on the main bearings of the V94.2 gas turbine.</p>