| With the accelerated progress of urbanization in China,the number of elevators is increasing due to the increase of the number of high-rise buildings.As an important transportation tool for high-rise buildings,the safety and reliability of the operation of elevators are closely related to people’s life safety.As an important part of elevator,the bearings of the traction system bear the load of car and counterweight.When the bearing of traction system fails,it will generate abnormal vibration and transmit to the car through the steel wire rope,which will cause passengers to panic and even cause major safety accidents.Therefore,it is of great significance to carry out fault diagnosis research for the bearing of traction system.When a traction system bearing malfunctions,its vibration signal is frequently impacted by the operating circumstances and interference signals,making it challenging to extract the fault features from the signal and influencing the accuracy of traction system bearing fault diagnosis.Thus,the difficulty of traction system bearing fault diagnosis is to accurately extract the fault characteristics of the traction system bearing and accurately identify the fault mode of the traction system bearing.This paper explores the fault characteristics of the traction system bearing by establishing the dynamics model of the vertical direction of the traction system,extracting the fault characteristics of the traction system bearing according to the operating conditions and fault characteristics of the traction system bearing,constructing a fault identification model of the traction system bearing with faster diagnosis speed and higher recognition accuracy,and finally carrying out a fault injection test for verification.The details are as follows:Firstly,it introduces the research background and significance of the fault diagnosis method for elevator traction system bearings,reviews the status of domestic and foreign research based on signal processing and machine learning fault diagnosis methods,analyzes the shortcomings of existing fault diagnosis methods for elevator mechanical components,and finally puts forward the main research contents and general technical route of this paper.Secondly,the structural composition and working principle of the elevator and traction system are introduced,the dynamics model of the vertical direction of the traction system is established,the vertical vibration response of the car and the failure response of the bearings when different bearings of the traction system fail are investigated,and the main bearing parts affecting the safe operation of the car and their failure characteristics are determined.Thirdly,based on the variable speed operating characteristics and fault response characteristics of the traction system bearing,a feature extraction method based on the combination of angular resampling and adaptive variational modal decomposition is proposed to solve the problem that the fault characteristics of the traction system bearing are affected by the variable speed operating conditions and disturbance signals.Then,according to the correlation and impact characteristics of the fault components,the correlation cliff index is constructed to select and reconstruct the fault components,the changes of the index before and after the fault of the traction system bearing are investigated,and then the effective feature indexes to characterize the bearing state of the traction system are selected.Fourthly,for the problem that the recognition effect of the kernel extreme learning machine is affected by the kernel function,a linear weighted multicore basis function is proposed,and an improved sparrow search algorithm is introduced for parameter seeking,and a fault recognition model based on the improved sparrow search algorithm optimized multicore extreme learning machine is constructed to improve the accuracy of bearing fault recognition of the traction system.Finally,a fault injection test was carried out and the proposed method was used to carry out fault diagnosis on the bearings of the elevator traction system. |
