Research on Deep Learning Based Dispatching Fault Disposal Robot Technology

Abstract

The current rapid development of artificial intelligence technology represented by deep learning has attracted much attention in all walks of life. The real-time regulation and operation of large-scale power grids is a typical combination of knowledge experience-based and online analysis. In particular, the fault disposal of power grids mainly depends on the pre-compiled texts of failure scenarios, which is actually the induction of prior knowledge and summary of dispatchers. Based on the above scenarios, this paper proposes a deep learning based dispatching fault disposal robot technology. Firstly, the natural language processing technology is used to learn, understand and extract the key information of the fault preplan text, and then a fault disposal knowledge map is built on this basis. Through the reasoning and analysis of knowledge, automatic/semi-automatic disposal of faults can be achieved.