The present research combines machine learning approaches with poly-coherent composite spectrum (pCCS) analysis to propose a vibration-based fault detection solution for rotating machinery. Through a mathematical fusion of vibration measurements obtained from distributed bearing locations, the pCCS technique constructs a unified spectral signature, enabling systematic fault detection. Using pCCS substantially reduces the frequency domain parameters compared to analysing individual spectra from each measurement point. An artificial neural network (ANN) is used and trained on the extracted parameters for fault detection. The methodology is tested on an experimental rotating machine. This research investigates a range of machine states, from healthy conditions to experimentally simulated faults such as bearing defects, misalignment, shaft cracks, and rotor–stator rub. Integrating pCCS analysis with machine learning techniques aims to enhance the robustness, computational efficiency, and real-world application of defect detection in rotating machinery.