Remote Fault Diagnosis System For CNC Machine Tools Based On Internet Of Things

CNC machine tools are important production equipment in modern manufacturing.Once a failure occurs,it may lead to parts scrapping,production stagnation,and enterprise economic loss.With the rapid development of advanced technologies such as the Internet of Things(IoT)and big data,it is possible to realize remote fault diagnosis of machine tools.Remote fault diagnosis system for CNC machine tools based on IoT is established in this paper.The main work are included as follows:(1)Based on the analysis of the functional and performance goals of machine tool fault remote diagnosis,design its functional modules and logical structure,describe the work content and workflow of each module and each layer,and an overall plan of remote fault diagnosis system for CNC machine tools based on NB-IoT is proposed.(2)The OPC client is used to obtain machine operating status data,the external sensor Lab VIEW client is used to obtain temperature,noise,vibration and other data.And the collected data is transmitted to the One NET cloud platform by NB-IoT communication module.(3)Aiming at the problems of low accuracy and stability of traditional neural networks and ELM in fault diagnosis,a model based on KELM was proposed.Aiming at the problem of network structure fluctuation caused by random penalty factors and nuclear parameters in the KELM machine model,a whale algorithm was used to optimize the model.Finally a fault diagnosis model based on the whale optimized kernel extreme learning machine(WOA-KELM)was established.(4)Using the vibration signal of the ball screw pair as the test data of the model,the EEMD and sample entropy are used to extract the signal features,and the extracted features are reduced by the kernel principal component analysis method to obtain the input samples of the model.The comparison between KELM model and WOA-ELM,CBA-KELM,and BA-KELM models shows that WOAKELM has fast convergence speed,high convergence accuracy,and high fault recognition rate.(5)Designed and developed machine tool remote fault diagnosis client software to visually manage the data involved in fault diagnosis,and realized user management,equipment management,fault classification management,fault online diagnosis and other functions.