Research of Pump-Jack Fault Diagnosis Method Based on the Negative Selection Algorithm

摘要

This paper proposes a fault diagnosis method a based on the biology immune principle, in which fault is regarded as antigen. First initial antibodies are generated using negative selection algorithm, then based on clone, mutation, clone selection, self adjustment and immune memory of the biology immune system, the initial antibodies are evolved to generate memory antibodies which can express and identify the antigen or fault. The method is used to detect the faults of pump-jacks of an oil field. The results show that the effect of fault diagnosis is good and can satisfy the needs