Research On Signal Acquisition And Fault Diagnosis Of Ball Screw Pair In CNC Machine

Ball screw is a key component of the transmission mechanism of CNC machine tools.The running status of ball screw pair directly affects the machining accuracy and surface quality of the machine tool.In this paper,the main components of the ball screw for CNC machine tools are studied,the load distribution and wear mechanism are analyzed,the signal acquisition system is constructed.The signal processing method is studied,and finally the fault diagnosis of ball screw pair is realized.The main contents of the dissertation are as follows:(1)Based on the Hertz contact theory,the load distribution between the ballscrew and raceway of the ball screw was analyzed.The mechanism of performance degradation and the factors affecting the performance degradation of the ball screw pair under different conditions were studied.The vibration characteristics of the ballscrew And common fault conditions.(2)Analysis of two ball screw signal acquisition methods.The use of OPC technology,acquisition of SIEMENS 840 D ball screw system within the speed of the signal;build sensor-based ball screw vibration signal acquisition system,through the development of LabVIEW-based acquisition software to achieve vibration signal acquisition.(3)The ball screw signal processing method was studied.The EEMD method is used to process the vibration signal to obtain the IMF component eigenvalue of the signal,and a large number of eigenvalues of the signal are obtained by analyzing the eigenvalue of the vibration signal and velocity signal in time-frequency domain.Using the KPCA method to reduce the dimension of the eigenvalue information obtained,a small amount of principal component signal is obtained.The algorithm of BP neural network is analyzed,the main component signal is taken as input and the output of ball screw pair is used as output.The fault diagnosis network of ball screw pair is trained and verified with experiments.(4)The fault diagnosis system of ball screw based on network was designed and developed,which realized the function of storing the sample eigenvalues and diagnosing the status of ball screw.The system uses Apache software as the server system,MySQL as the database system,through the PHP language to build a fault diagnosis system background service program,including sample storage system and BP neural network diagnosis and other parts,combined with front-end technology to build user and server program interaction Interface procedures.