Research On Health Evaluation System Of Gantry Crane Reducing Mechanism

With the more and more extensive application of bridge gantry cranes in production and logistics,the reduction mechanism,as one of the important components,often affects the performance of the whole machine due to the internal gear pitting corrosion,gluing,wear and other forms of damage,and also brings potential safety hazards.Therefore,the research on the integration and application of multi-sensor information collection,key component fault diagnosis,and health status detection system of the bridge gantry crane reduction mechanism is of far-reaching significance for timely detection of the failure of the reduction mechanism,greatly reducing the incidence of safety accidents,and ensuring the safe and reliable operation of the equipment.This thesis takes the bridge gantry crane reduction mechanism as the research object,comprehensively applies data acquisition,multi-sensor data fusion technology,signal processing technology,deep learning technology,knowledge graph and other technologies to study the fault diagnosis method of the reduction mechanism in the industrial site,and combines the industrial Internet of Things technology to realize the integration of the health state detection system and improve the real-time and practicality of the health status detection system.The main research contents are as follows:In this thesis,the bridge gantry crane reducer is modeled in 3D by Solid Works,and the assembly is imported into ADAMS for dynamic simulation,and Hyper Mesh is used to flex some parts to construct a rigid-flex coupling model of the reducer,which verifies the correctness of the model from the two aspects of shaft speed and gear meshing force,and simulates the gear wear fault.By analyzing the failure mode and failure mechanism of crane reducer gears,combined with attention mechanism and multi-source information fusion theory,a multi-source information fusion and fault diagnosis model based on attention mechanism convolutional neural network(SE+MC+1DCNN)is proposed.The attention mechanism is added to the CNN to screen out important fault features,and the optimal network model is obtained after training with the sample data of the open source dataset,and this is applied to the real-time operation state fault diagnosis of the crane reducer,and the results show that the model can accurately classify different fault types of gears and have high accuracy.The health status detection system architecture of the deceleration mechanism based on cloud and fog collaborative computing is constructed,the data collection is realized at the edge,the monitoring data of the equipment is uploaded to the fog node through the wireless transmission module,and the data is preprocessed in the fog layer.A cloud database is built in the cloud layer to realize data storage,and the model training and update module and the health detection of the deceleration mechanism are deployed to the cloud,and Lab VIEW is used as the software development platform of the system to realize the functions of real-time monitoring,data management,fault diagnosis,and status detection of the system.Finally,the system is tested with engineering examples to verify the effectiveness and practicality of the system.