Abstract With changes to aircraft usage due to expanded roles, operators need to monitor the usage of the aircraft and component loads to ensure safe operation of the components within their fatigue lives. Accurate load monitoring of aircraft component loads during flight is a challenge that has inspired the implementation of computational intelligence and machine learning techniques to replace the need for costly sensor systems. Much research has been carried out to develop a methodology for load signal and fatigue life estimation using only data from standard flight state and control system parameters. The National Research Council’s approach to load and usage monitoring is centered on leveraging the data recorded by existing instrumentation using machine learning models and data mining techniques. This flexible approach has been demonstrated on several helicopter platforms manufactured by different original equipment manufacturers. Results from the Australian S-70A-9 Black Hawk and Canadian Forces CH-146 Griffon (Bell 412) are provided to demonstrate the analysis and outputs enabled by accurate load monitoring. These outputs include load signal estimates, fatigue damage accumulation, and load exceedance plots and comparisons. For many operators, access to component material information that supported initial design analysis is very limited, so the provided outputs do not assume that this type of information is readily available. Using this analysis, valuable insights can still be obtained, particularly through load exceedance comparisons. Accurate load and usage monitoring is a universal goal that is not easily achieved on older aircraft without the sophisticated and powerful health and usage monitoring systems that are available today. This research targets these smaller legacy fleets to help satisfy their usage monitoring requirements and ensuring structural integrity.