Abstract: Aiming at the problems of various types of faults, difficult fault diagnosis, low diagnostic efficiency, and high maintenance cost in the hydraulic system of coal mine parts processing lathe, we explored and analyzed the common types of faults in the hydraulic system of CNC lathe, including vibration, noise, crawling and oil temperature abnormality, etc.,and researched the parts of the common faults and the causes of faults, and put forward an intelligent diagnostic method for the faults of the hydraulic system of the CNC lathe, and designed a hardware system and supporting fault identification software control system, realizing the real-time acquisition of processing lathe hydraulic system operation abnormal parameters, intelligent analysis, rapid positioning and identification of hydraulic system failure.After on-site test and debugging on CK6140 CNC lathe in a coal mine in Shanxi, the results show that: the hydraulic system's fault intelligent diagnosis system can quickly identify common vibration and noise faults to show the abnormal characteristics in a visual way, the recognition response time is only 1.69 s, the recognition accuracy is up to 98.6%,and the weak signals are timely collected and intelligently analyzed, which facilitates the timely discovery of potential faults and hidden dangers, and ensures the long-term stable operation of the lathe.