Research On Fault Diagnosis Method Of Helicopter Transmission System Based On Rise-dimension Processing

As helicopters play an increasingly important role in the military and civilians,their reliability and safety issues are receiving increasing attention.As the core power transmission component of the helicopter,the transmission system will cause serious consequences in the event of an abnormality.Therefore,the research on the fault diagnosis method of the helicopter transmission system is of great significance to ensure the safety of helicopter flight.The helicopter transmission system has strong background noise,multiple compound failures,and unclear fault mechanism during the actual operation,the accurate diagnosis of the fault is a difficult point.Therefore,this article takes the rotating mechanical components in the transmission system as the research object,on the basis of rising the dimension of the collected one-dimensional vibration signals,the research on fault diagnosis method of helicopter transmission system based on the rise-dimension dimension processing is carried out,aiming at promoting the further development of the fault diagnosis technology of helicopter transmission system in China.The main research work is as follows:(1)The method of rise-dimension based on the rotational speed synchronization signal is given and the preprocessing method of two-dimensional vibration signal based on guided filtering is studied.Firstly,in order to adapt to the situation of rotational speed variation of the rotating machinery of the transmission system,the rotational speed synchronization signal outputted by the coaxial encoder is used as the time scale,converting the one-dimensional vibration signal into a two-dimensional vibration signal by the method of segmenting and rearranging signals.Secondly,the two-dimensional signal gradient information is combined with the guided filtering algorithm,and the two-dimensional vibration signal denoising preprocessing is realized.The pre-processing experiments are carried out by using the simulated signal and the rolling bearing vibration signal.The results show that the proposed method can achieve better pretreatment effect than other methods.(2)The fault diagnosis method of rotating machinery based on rise-dimension processing is studied.Firstly,according to the LBP and GLCM have the characteristics of welling describe two-dimensional signal texture features,the LBP and GLCM feature extraction methods based on two-dimensional vibration signals are studied.Secondly,the fault diagnosis model construction and fault classification process based on SVM algorithm are given.The fault diagnosis experiments of rolling bearing vibration signals with different loads and different scoring conditions are carried out.The results show that the method based on the combination of LBP and GLCM features can obtain better diagnosis results.(3)The vibration signal detection device is designed and developed.On the basis of the hardware and software debugging of the detection device,the vibration signal acquisition is carried out based on the planetary gear vibration table,and relevant experiments are carried out by using the methods of signal rise-dimension processing,preprocessing,feature extraction and fault diagnosis.The results show that the method of this paper can achieve good filtering and fault diagnosis results for vibration data of planetary gears,which further verifies the feasibility of the method.