Research On Fault Diagnosis Method Of Reciprocating Compressor Valves Besed On Parameter Recogniton

In recent years machinery fault diagnosis technology has been greatly developed all over the world and the technology is very important in national production. The research on reciprocating compressor fault diagnosis is of great significance owing to the particularity of its application. But gas valve is one of the key parts in reciprocating compressor, which has often broken down with highest ratio and its exhibit non-stationary signals. In order to analysis the feasibility method of fault diagnosis of gas valve, the author uses the 2D12 of Da qing oil field as the object. According to the analysis of the reason of vibration which comes from reciprocating compressor and the non-stationary characteristic of the signal, in this paper, the method of fault diagnosis in this paper is the model parameter of structure identification and the wave packet decompose.In the first, this thesis firstly reviewed the fault characteristics and diagnosis methods of reciprocating machine based on internally and abroad. Then it introduced the background,purpose and significance of fault diagnosis. And according to analysis of the elements of the reciprocating compressor gas valve and the characteristics of the vibration, summarized the characteristic of the signal of the gas valve is non-stationary.In the second, in allusion to non-stationary the characteristic of the signal, the author introduces to the method that using Empirical Mode Decomposition to analysis the vibration signal so that the signal are made up of some Intrinsic Mode Function, after this process, we can use Stochastic Subspace Identification to identification the mode parameter of the structure and find the same work frequency. Since, we can extract the time-domain fault feature parameter in order to fault diagnosis.In the end, according to analysis data of four states of the reciprocating compressor'gas valve in order to approve the feasibility of this method.