Diagnosis of power operation and maintenance records based on pre-training model and prompt learning

Abstract

The operation and maintenance records of power equipment contain abundant historical operation state information of equipment. However, due to the characteristics of multi ambiguity, difficult to segment ambiguity and multi noise, this paper proposes a two-stage model for the text diagnosis of power equipment. First, the large-scale pre-training model is trained based on the massive text, and then the pre-training language model is fine-tuned by the prompt technology for equipment diagnosis. The proposed solution is assessed through experiments and the numerical results demonstrate that the proposed solution can achieve about 20% improvement over the traditional method.