Self-adaptive fault diagnosis method and equipment for injection-production compressor unit of gas storage

Abstract

The invention provides a method and a device for adaptive fault diagnosis of a gas storage injection-production compressor unit. The method includes acquiring a vibration signal of a compressor and a time-domain characteristic index corresponding to the vibration signal, extracting an energy characteristic value of the vibration signal by the wavelet-packet-decomposition energy characteristic extraction process, constituting a characteristic vector to be diagnosed according to the energy characteristic value and the time-domain characteristic index corresponding to the vibration signal, training a preliminary classification self-organizing competitive network model and a precise classification probabilistic neural network model, substituting the characteristic vector to be diagnosed to the trained preliminary classification self-organizing competitive network model to acquire the preliminary mode, acquiring the correspondingly trained precise classification probabilistic neural network model according to the preliminary mode, and precisely recognizing the preliminarily classified characteristic vector to be diagnosed according to the trained precise classification probabilistic neural network model so as to acquire fault type of the vibration signal. By the method and the device, fault diagnosis precision on variable working conditions of the gas storage injection-production compressor unit is improved effectively.

Description

technical field [0001] The present invention relates to the technical field of natural gas storage equipment, in particular to the technical field of gas storage safety engineering, and specifically to a method and equipment for self-adaptive fault diagnosis of injection-production compressor units of gas storage. Background technique [0002] With the continuous increase in the construction and use of gas storages, more and more experts and scholars have begun to pay attention to the safe operation of gas storages, study the fault diagnosis methods of gas storage injection and production compressor units, and develop some compressor unit status monitoring. And fault diagnosis software and hardware system. Since the pressure inside the gas storage is constantly changing during the gas injection and production process of the gas storage, in addition, depending on the required gas injection and production volume, the incoming gas pressure and flow rate of the gas storage also ...

AI Technical Summary

Problems solved by technology

However, the existing gas storage compressor unit fault diagnosis method models are basically established according to a single working condition. is lower

[0003] In addition, in order to improve the fault identification accuracy of the diagnostic method, a large amount of sample data is often required to train the established diagnostic model, but a large amount of sample data will inevitably increase the training time and reduce the rapidity of the diagnostic method.

Images