Research On State Detection And Fault Diagnosis Of Main Drive Reducer Of Shield Machine

The shield machine is a large piece of equipment dedicated to tunnelling and underground construction.The main drive system which drives the cutter during construction and cuts through the rock is the key system that makes up the shield machine.As the core component of the main drive system,the reducer usually works in harsh environments and under conditions of heavy load at low speed and huge torsional impact,and generally consists of a three-stage planetary wheel system with complex structure,compact parts and high assembly accuracy.As a result,the gears in the planetary wheel system are prone to gear failure due to high loads and meshing shocks.If gear failure is not detected and repaired in time,it will affect the life of the gearbox and the overall construction efficiency.Therefore,it is necessary and urgent to investigate the condition detection and fault diagnosis of the shield machine main drive reducer.In this thesis,the dynamic characteristics of the gears are analysed by constructing a rigid-flexible coupling model of the planetary wheel system of the shield gearbox.The vibration signal is used as the entry point for gear fault extraction and fault diagnosis.A condition detection and fault diagnosis system is developed for shield gearboxes according to the actual engineering requirements.In this thesis,the structure and working principle of mud and water shield machine and reducer are firstly explained;the vibration characteristics of reducer are studied,the failure form of reducer is highlighted,and the vibration characteristics of planetary wheel system of reducer are analysed.Combining the multi-body system dynamics theory and digital twin idea,a rigid-flexible coupling dynamics model of the planetary wheel system of the shield reducer is constructed;the dynamics simulation of the constructed model is carried out,and the simulation results are compared and analysed with the theoretical results to verify the accuracy of the constructed model;and the vibration characteristics of the signals under different health states of the solar wheel are studied from the perspective of time domain characteristics as well as frequency domain characteristics,which provide a basis for It also provides a theoretical basis and data foundation for the condition detection and fault diagnosis of the speed reducer.Secondly,a particle swarm optimisation-based variable modal decomposition algorithm(PSO-VMD)combined with a kurtosis criterion is proposed to address the problem of difficult extraction of gear fault features.The optimal combination of the number of modal components and the quadratic penalty factor of the variational modal decomposition algorithm is determined using the particle swarm algorithm(PSO)with the minimum mean envelope entropy as the fitness function;the original vibration signal is decomposed into several intrinsic modal components by the optimized parameter combination through the variational modal decomposition algorithm,and the components are screened for reconstruction according to the kurtosis criterion to reduce noise interference;the time domain and entropy theoretical features of the reconstructed signal are extracted to form the feature data set.and entropy theoretical features are extracted to form a feature dataset for fault identification and classification using Particle Swarm Optimization Support Vector Machine(PSO-SVM)and Light Gradient Boosting Machine(Light GBM).The results show that the method can effectively extract gear fault features and achieve accurate determination of gear fault types,which verifies the feasibility and effectiveness of the proposed method.Finally,a shield machine gearbox condition detection and fault diagnosis system was developed using Lab VIEW as the development platform,combined with MATLAB for hybrid programming.The system contains modules such as data acquisition,vibration detection,oil detection,temperature detection,vibration intensity diagnosis,PSO-VMD fault diagnosis and information management of the detection objects.In order to verify the stability of the system,the main drive reducers of S-1296 and DZ866 shield machines at a river crossing tunnel construction site in Anhui Province were measured in the field using the system developed in this thesis,and the relevant data of the reducers were collected and analysed.The results show that the developed system has good performance and is useful for condition detection and fault diagnosis of shield machine reducers.