Fault diagnosis of high-speed motorized spindles based on lumped parameter model and enhanced transfer learning

Abstract

Condition monitoring of rotating components is crucial for ensuring the reliability and safety of mechanical systems, and artificial intelligence (AI) plays a significant role in achieving the goal. However, the high costs and complexity associated with components like high-speed motorized spindles present significant challenges in collecting complete fault samples. Therefore, we propose a new approach to tackle the challenges. The process commences with establishing a lumped parameter dynamic model for the high-speed motorized spindle. Then, the parameters such as stiffness, eccentricity, and damping in the lumped parameter model were optimized using genetic algorithm. Subsequently, simulated fault samples are acquired by introducing excitation to normal simulated signals. Finally, transfer learning techniques are utilized for intelligent fault diagnosis. The training set consists of simulated fault samples, while the testing set comprises experimental fault samples. Our approach aims to enhance the efficiency and accuracy of fault diagnosis for high-speed motorized spindles while also addressing the challenge of high cost.