Fault Diagnosis Of Self-propelled Artillery Transmission Box Based On Variational Mode Decomposition

Self-propelled artillery is an important equipment of our army.The transmission box is the core component of self-propelled artillery control cartridge box to adjust its launching direction.In the course of its use,due to various problems such as impact,lack of lubrication,inappropriate clearance and so on,it is easy to produce various early faults,which seriously affects the reliability of self-propelled artillery,and even delays the operational opportunity in wartime.Therefore,timely and accurate diagnosis of its abnormal state is of great significance for improving the operational performance of self-propelled artillery.Aiming at the traversing mechanism and elevating mechanism in the transmission box of self-propelled artillery,this paper proposes two different fault diagnosis methods based on the variational mode decomposition,and verified them with the engineering measured signals,all of which have achieved good results.The main research content of this paper is as follows:(1)Variational mode decomposition has a key parameter,that is,the optimal decomposition level is difficult to determine.Therefore,adaptive variational mode decomposition(AVMD)is proposed in this paper.At the same time,a method for screening sensitive IMF components is proposed,using the two methods to improve the traditional Hilbert Huang transform,combining ELM classifier with good generalization ability,a fault diagnosis method for the traversing mechanism of self-propelled artillery transmission box based on improved HHT and ELM is proposed.The experiment is carried out by using the engineering measured signals of the traversing mechanism.The results show that the recognition accuracy rate is 92%,which is higher than the traditional diagnosis method in both recognition rate and recognition speed.The diagnosis results meet the actual engineering requirements.(2)Since the vibration signals of self-propelled artillery elevating mechanism are more complicated,the improved HHT is not suitable for processing such signals,and a single characteristic index can not effectively reveal the state essence of elevating mechanism.Therefore,this paper proposes a fault diagnosis method for self-propelled artillery elevating mechanism based on AVMD and neighborhood rough set.Firstly,this method extracts the time-domain features,singular values,permutation entropy and other features of the elevating mechanism vibration signals to construct the original feature set.Then,the sensitive features are screened out by using neighborhood rough set method.Finally,the state diagnosis is carried out by using ELM.The experiment is carried out by using the engineering measured signals of the elevating mechanism.The results show that the recognition rate is 95%.Compared with the original feature set,the recognition rate is improved by 17.5%,and satisfactory results are obtained.(3)On the basis of the previous two parts,a GUI system for fault diagnosis of self-propelled artillery transmission box is designed by using the GUIDE of MATLAB,which improves the convenience of diagnosis and makes diagnosis more integrated and practical.