Research On State Evaluation Method And Monitoring System Of Gear Transmission System

Gear is one of the transmission parts widely applied in mechanical equipment,playing an important role in system movement and power transmission.Due to the harsh working environment of equipment used for production,gear transmission systems are prone to various types of failures,such as pitting,abrasion,fracture,missing teeth,etc.Therefore,it is of great practical significance to monitor and evaluate the operating status of the gear transmission system,which can detecte early failures in time,and plan maintenance programs reasonably,avoiding major losses.This article takes gears as the research object,and conducts research on gear running status assessment and monitoring,as follows:1.Research of feature fusion strategy for gear states diagnosis based on fusion assessment.For the problem of insufficient signal information in a single direction and the difficulty of a single feature analysis method to fully characterize the operating state of the gear transmission system,a feature fusion strategy based on multi-dimensional fusion assessment to obtain optimum feature fusion pattern is proposed,which makes full use of the advantages of vibration signals in different directions and extraction method.First,different analysis methods are employed to extract the features of vibration signal in each direction(X,Y and Z),respectively.Then,the best fusion mode is determined by fusion assessment mechanism based on fuzzy logic in two directions and vibration intensity of signal in three directions.Finally,support vector machine(SVM)and decision tree(DT)are selected as classifiers to verify the validity and universality of the proposed method.2.Research on gear fault diagnosis based on feature fusion optimization and improved two-hidden-layer extreme learning machine(ITELM).To evaluate the operating state of the gear transmission system in rotating machinery,a gear fault diagnosis method based on feature fusion optimization and ITELM is proposed.Firstly,variational mode decomposition(VMD)and wavelet packet(WP)are employed to decompose signal,and statistical parameter features are extracted.Then,Relief F algorithm is adopted to manage the extracted features and obtain the optimal feature subset that can characterize gear running status.Finally,in view of limitation of the existing extreme learning machine in the aspect of network structure and the hidden layer node selection algorithm,combined with the influence of sample size,feature dimension,and classification category number,empirical formula and fuzzy logic inference were constructed to determine the number of nodes in the first and second hidden layers respectively,to improve the classification performance of the network.For the purpose of verifying the effectiveness of the proposed method,an internationally public database is used for verification and analysis.3.Carry out functional planning and build an online monitoring system for gear transmission initially,combining actual application requirements.The system consists of a login module,a data acquisition module,a data processing and analysis module,a data storage and playback module,etc.,which can realize multi-channel signal acquisition,storage,feature extraction,fusion evaluation,pattern recognition and early warning,etc..4.In order to fully verify the effectiveness and universality of the above-mentioned methods,mechanical fault simulation(MFS)is employed as the research object to collect the vibration signals in three directions under different operating conditions of the gear transmission system,applied to verify the method proposed in this article.Experimental research shows that the proposed method can achieve higher accurate for gear transmission system condition assessment.Aiming at the problem of gear fault diagnosis in industrial applications,to achieve effective gear running state characterization and high-precision state identification,relevant innovative methods in feature fusion optimization and classification identification was proposed in this article.The research result of this paper is the expansion of theory and method in the field of gear transmission system condition assessment,which has certain academic value and broad practical application prospects.