Study Of Condition Based Maintenance Technology Application In Typical Petrochemical Equipment

Centrifugal compressor is being widely used in many kinds industries espcially petroleum chemistry industry, if it breaks down during its working process, that would made product line or product machine stop and let company has a big economic loss, even it would threaten worker's life. So, it's important to research the theory of compressor's consition based maintenance and built a fault diagnosis and prediction and prewarning system. In the main, this article researches centrifugal compressor's fault diagnonsis, prediction and prewarning and built a compressor fault diagnosis and prediction and prewarning system. The main analyze methods included in this article as follows:The fuzzy diagnosis model is improved that the new model is given the function of self-learning and quantitative analysis. The set of failure symptom is established through the analyzing of centrifugal compressor's fault. The fuzzy matrix of this self-learning diagnosis model is given by analyzing of the falut character and cases. The failure cause of the compressor can be fought out by the fuzzy algorithm and dealing with the compute result. The self-learning model can be improved by the analyzing of interpretation of result and fault cases. The suitable maintenance is taken when the fault is found out by the diagnosis modle.A new prediction method is built based on the analyzing of susceptivity and measure of dispersion. The running conditions of the compressor are comfirmed by the susceptivity and measure of dispersion. When the susceptivity and measure of dispersion are higher than the permissible value, the running condition of compressor is unsteady. The gray prediction is taken to predict the vibration of the compressor when the running condition of compressor is unsteady. If the running condition of compressor is steady, the fuzzy forecasting model is used to predict the fault. The prewarning is given based on the susceptivity, measure of dispersion and prediction of the compressor. And the suitable maintenance is taken when the running conditions is analyzed by the prediction.The system of condition based maintenance of centrifugal compressor is designed based on the analyzing of fault diagnosis and prediction and prewarning. This system has the functions that are established and analyzed above. The functions are seil-learning diagnosis, prediction model based on the analyzing of susceptivity and measure of dispersion, prewarning based on the susceptivity, measure of dispersion and prediction and fault management.Through the verification of the compressor the result indicate that all parts are researched above states well. It is shown by the results that the condition based maintenance technology is feasible as well as effective.