Vibration-based fault diagnosis of pump using fuzzy technique

Abstract

This paper focuses on a problem of vibration-based condition monitoring and fault diagnosis of pumps used in oil field to recover petroleum. The vibration-based machine condition monitoring and fault diagnosis incorporate a number of machinery fault detection and diagnostic techniques. Many machinery fault diagnostic techniques utilize automatic signal classification in order to increase accuracy and reduce errors caused by subjective human judgment. In this paper, fuzzy logic principle is used as a fault diagnostic technique to describe the uncertain and ambiguous relationship between different fault symptoms and the events, analyze the fuzzy information existing in the different phases of fault diagnosis and condition monitoring of the pumps, and classify frequency spectra representing various pump faults. The diagnostic features are extracted from frequency spectra of the vibration signals of the pump. The frequency spectra representing a number of different fault conditions are then processed using fuzzy membership function, which is established by means of dynamic signal processing based on the condition variables. Correct classification and condition recognition of different pump fault spectra are realized when fuzzy comprehensive discrimination according to the defuzzy diagnosis rules is applied. The work conducted, proposing the new method of the pump fault identification based on fuzzy logic technique, shows the great potentiality and the strong ability to classify and identify machinery faults.