To address the issue of low accuracy in traditional rotor fault diagnosis during the helicopter rotor fault diagnosis process, this paper presents a fault diagnosis method based on the Improved Particle Swarm Optimization (IPSO) algorithm for Relevance Vector Machine (RVM). The fitness function of the IPSO algorithm is defined as the mean squared error between the predicted classification results obtained through cross-validation and the actual classification. The IPSO algorithm is used to search for the optimal width factor of the RVM kernel function and establish the fault diagnosis model. Through simulation experiments and comparisons with Particle Swarm Optimization (PSO) algorithm-based RVM and Improved Particle Swarm Optimization-based Support Vector Machine (SVM), it is demonstrated that this approach, compared to traditional rotor fault diagnosis methods, effectively improves the accuracy of fault recognition.