Method And Experimental Research On Health Monitoring Of Intelligent Equipment Based On Internet Of Things

With the revolutionary progress of modern industrial intelligent manufacturing and artificial intelligence technology,industrial production equipment is rapidly developing towards unmanned,integrated,and intelligent directions,which has promoted a significant increase in production efficiency.Generally,intelligent equipment is more expensive and the system is complex.Due to the changing working environment,the complex mechanism of the equipment itself,and high requirements for stability and reliability,there are higher requirements for maintenance.Existing ex-post maintenance strategies will seriously affect production efficiency,and bring huge economic losses and hidden safety hazards.Real-time online diagnosis and prediction of remote monitoring equipment operation status and health using Io T technology and intelligent sensing technology.It has received extensive attention from the scientific and industrial circles.Through real-time monitoring of the health status of intelligent equipment,faults can be found and repaired in time,which improves the safety,stability and reliability of industrial production.Therefore,it is of great practical significance to conduct in-depth research on the health status of intelligent equipment.The research on the health monitoring of intelligent equipment in this subject mainly includes three aspects: the research on fault detection methods,the research on fault prediction methods,and the construction of the Internet of Things platform.1.In terms of research on fault detection methods,this paper proposes improved fault feature extraction methods based on CEEMDAN and TEO based on the shock characteristics of vibration signals.This method first establishes a comprehensive evaluation model of SDEA,uses the kurtosis criterion and correlation coefficients to filter the characteristic modal signals;then uses SDEA to evaluate the denoising effect,selects the signal with the highest comprehensive evaluation coefficient and reconstructs it using energy indicators;finally,it uses TEO For the high sensitivity of the impulse signal,perform envelope demodulation on the reconstructed signal to extract the fault characteristic signal.2.In terms of fault prediction method research,this paper proposes a prediction model based on GA-optimized BP neural network in view of the characteristics of large-scale changes and non-linear signals in fault prediction.The ability of using the genetic algorithm to find the global optimal solution optimizes the initial value of the BP network,avoids the fitting error problem caused by the improper selection of the initial value of the neural network,and greatly improves the prediction accuracy.This method first establishes a BP neural network prediction model for the predicted object;then determines the parameters in the network through the optimized search ability of the GA algorithm,and uses the original data for network training;finally,it performs rolling extrapolation prediction based on the data collected in real time.3.With regard to the construction of the Internet of Things platform,this article addresses the needs of the manufacturing industry for intelligent management of equipment,and proposes a solution using industrial Io T technology as a carrier,combining traditional methods and machine learning technology to solve the problem of industrial intelligent equipment health monitoring.The data required for intelligent equipment monitoring is collected,transmitted,stored,and analyzed by building an Io T platform.This article builds a hardware platform for the Internet of Things platform,including a sensor acquisition system with a sensor as the core,a signal processing system with an AD acquisition module and a main control module as the core,and a signal transmission system with 4G communication as the core.Then the software design is carried out,which mainly includes the software design of the hardware platform and the interface design of the upper computer display part.Finally,the overall platform test was performed.The test results show that the system basically meets the design requirements and the overall operation is good.