Fault detection technology is an important technology to ensure the safe and stable operation of the electric-hydraulic servo actuator (EHSA). Owing to the electro-hydraulic servo mechanism’s issues with unequal detection time intervals and limited detection times, utilizing such detection data directly in conjunction with the current algorithm to identify EHSA failure may result in decreased detection accuracy and model performance. In order to solve this kind of problem, a fault detection method of an electro-hydraulic servo mechanism based on non-equal interval data was proposed. First, the historical detection data of the equipment was isolated by combining the historical detection data of electro-hydraulic servo mechanisms of various devices in the same batch using the M-H algorithm. Second, the contribution graph approach was utilized to examine the fault-related indicators after statistics were constructed using the kernel principal components analysis (KPCA) method, which analyzed the discrepancies between principal components and served as the basis for fault identification. When the number is limited and the data are not evenly spaced, the suggested approach has a high defect identification rate. The effectiveness of the method is verified by the historical detection data of a certain type of electro-hydraulic servo system.