Patent Operation Platform

Patent

[CN 202010430430.2] Forging hydraulic press pump source fault prediction method and system


[CN 202010430430.2] A Forging Hydraulic Machine Pump Source Fault Prediction Method and System Title: A Forging Hydraulic Machine Pump Source Fault Prediction Method and System Application Number: CN 202010430430.2 Applicant: Tianjin Tianforging Press Co., Ltd.; Wuxi Xuelang Digital System Technology Co., Ltd. Application Date: 2020-5-20 Patent Type: Invention Application The present invention relates to a forging hydraulic machine pump source fault prediction method and system, belonging to the technical field of forging hydraulic machines, including: s1, select the pump source system of a forging hydraulic machine as the object of fault prediction evaluation, S2, through long-life test, obtain the test data of the whole life cycle of multiple pumps, S3, use the test data to train the appropriate neural network model, S4, obtain the characteristic parameters of each pump running the equipment pump source system at the current moment; s5, input the characteristic parameters of each pump to be predicted into the trained neural network model to obtain the prediction of the remaining fault interval time of each pump at the current moment; S6, determine the average maintenance interval of each pump and calculate the repair rate of the faulty pump; S7, draw the state transition diagram of Markov chain of pump source system; S8, realize the prediction of failure; s9, when the time point of the fault probability update calculation is reached, the fault probability starts the update calculation.