The manufacturing industry became a competitive market that requires each manufacturer to pursue operations excellency to maintain profitability and customers satisfaction. With machines and equipment acting as the bloodline for many industries including manufacturing, transportation and services, their efficiency and reliability are essential to ensure the continuity of the industry. With time being of a critical element for the delivery and reliability of any industry, assets breakdowns are incorporated with delays and substantial financial costs. Considering these concerns, predictive maintenance (PdM) emerged as a strategic approach that offers a proactive approach to mitigate the risks of machines’ sudden breakdowns. The current research focuses on the applications of PdM with a focus on a comparative analysis of the existing condition monitoring (CM) tools that support machines’ failure identification. CM is a key component for PdM that involves the continuous assessment of machines’ components health to identify any deviation from normal operating conditions, facilitating the early identification of failures. The efficiency of CM is an impacting key on organisations ability to maintain machines’ reliability, reduce downtime and support maintenance schedule optimization. This paper supports the selection process of CM techniques based on their principles, applications, and limitations, offering a comprehensive overview to support decision making process in the selection of the most suitable techniques for different machines bearings’ failure modes. The research utilises vibration, thermography, and current analysis for various bearing failure modes simulated on an experiment test rig at various speeds. The research offers a comprehensive literature review on maintenance strategies, machines failure modes, CM techniques, their applications and limitations. The research offers a practical insight into bearings failure modes and suggests the optimum CM technique that supports PdM applications for failure prevention.