Research On Fault Diagnosis Of Damaged Hydraulic Cylinder

Hydraulic cylinder,which has a great influence on the working performance of the whole machine,is a key executive element widely used in the hydraulic system of construction machinery.Hydraulic cylinder scuffing is one of the main leading cause of hydraulic cylinder leakage,which is a typical fault of hydraulic cylinder.Due to the tightness of the hydraulic system,the diagnosis of the Hydraulic cylinder scuffing and internal leakage has always been a difficult point in the fault diagnosis of hydraulic system.This article takes the MOB40 * 200 hydraulic cylinder as the research object,and conducts in-depth research on Hydraulic cylinder scuffing and fault diagnosis.The main research contents are as follows: 1.Hydraulic Cylinder Scuffing Simulation Experiment and data acquisition.Based on the YCS-DIII electro-hydraulic servo proportional comprehensive test bench,a test system for the hydraulic cylinder working condition simulation test bench was built to analyze the causes,phenomena,and hazards of cylinder failure.The scuffing of hydraulic cylinder and experimental scheme were designed.The hydraulic cylinder scuffing was artificially simulated,including the test system hardware selection and test system software settings.Based on the above experimental system,the hydraulic cylinder pressure,flow and other signals are collected in the normal state and the cylinder failure state when the hydraulic cylinder is in motion.2.Feature extraction based on EMD for hydraulic cylinder scuffing failure.The pressure signal of the rodless cavity of the hydraulic cylinder was extracted with empirical mode decomposition(EMD).The variation of the three characteristic value with the cylinder scuffing were determined :the energy value of IMF1,the total energy entropy of the intrinsic mode,and the root mean square value of the transient amplitude of IMF1.On this base,a fault feature vector is formed and used as the input vector of the next fault classifier.3.Fault pattern recognition of hydraulic cylinder scuffing based on endocrine neural network.The basic structure and working principle of endocrine BP neural network were summarized,and the regulating function of endocrine strategy on neural network weights was analyzed.The endocrine BP neural network was further introduced into the diagnosis of faults in cylinder barrel scuffing.The network structure of the endocrine neural network classifier was designed,the fault classification for the cylinder scuffing was performed,and the fault classification effect of BP neural network was comparatively analyzed.The research results show that endocrine BP neural network is better than traditional BP neural network.