Cable multi-state variable evaluation model design method and device based on zero-order learning method

The invention proposes a cable multi-state variable evaluation model design method and device based on a zero-order learning method, and the method comprises the steps: obtaining a sensing data source of a cable during the operation of the cable, and enabling the sensing data source to be a state parameter capable of reflecting a cable insulation fault; preprocessing the sensing data source through a multi-source heterogeneous data fusion technology to obtain preprocessed data; inputting the preprocessed data into a preset evaluation model based on zero-order learning to obtain an evaluation result and recommended measures; and performing defect treatment according to the evaluation result and the recommended measures. Through evaluation model training of a zero-order learning method, hidden risks can be accurately identified, and the precision and reliability of a substation system on cable monitoring decision data are improved. 本发明提出了基于零次学习法的电缆多状态变量评估模型设计方法及装置，获取电缆运行时电缆的感知数据源，所述感知数据源是能够反应电缆绝缘故障的状态参量；通过多源异构数