<p>This study examines fatigue damage progression in Aluminium 6061 using acoustic emission (AE) analysis combined with continuous wavelet transform (CWT). Despite the widespread use of Aluminium 6061 in the automotive and aerospace industries, existing fatigue monitoring methods lack the precision needed to detect early damage progression under variable loading conditions. Current approaches do not fully utilise the combined potential of AE and wavelet energy analysis to provide real-time insights into fatigue behaviour. AE signals were captured under constant amplitude and block spectrum loading to analyse transient damage events. CWT was employed to decompose the AE signals into time–frequency components, enabling precise identification of the fatigue damage stages. By extracting wavelet coefficients and energy, the study effectively illustrates damage accumulation patterns. The analysis revealed a rate of over 95% accuracy in correlating the AE signals between the time and frequency domains, with power spectral density (PSD) and CWT energy correlations exhibiting a minimum error margin of 5%. These results highlight the capability of CWT to detect fatigue events and accurately predict fatigue life. The findings provide a robust framework for understanding fatigue behaviour under variable loading conditions, offering an advanced approach for predictive maintenance and structural health monitoring.</p> Graphical abstract <p></p>