State‐of‐the‐Art Artificial Intelligence for Condition Perception of Power Equipment: Applications and Trends

With the advancement of the ‘carbon peaking and carbon neutrality’ targets and the construction of new power systems, the operating environment of power equipment is becoming increasingly complex, rendering traditional operation and maintenance strategies insufficient to meet the demands of safe and stable grid operation. This paper systematically reviews the application status and latest advancements of state‐of‐the‐art artificial intelligence in the field of power equipment condition perception, focussing primarily on two core dimensions: condition assessment and fault diagnosis. First, the evolutionary trajectory of condition assessment and fault diagnosis methods for power equipment is outlined, and the efficacy of various intelligent algorithms in practical engineering applications, such as complex signal feature extraction and small‐sample diagnosis, is deeply analysed. Second, the development and application of large language models (LLMs) in the power sector are summarised, highlighting the immense advantages and potential of LLMs in the intelligent perception of power equipment. Finally, the future development trends and challenges of intelligent perception technologies for power equipment are envisioned. This paper aims to provide a systematic reference for academic research and engineering practice in the intelligent perception of power equipment and related fields.