Terminal off-line detection and self-weight starting method and device

The invention relates to the field of power systems, in particular to a terminal off-line detection and self-weight starting method and device, and the method comprises the steps: collecting the operation data of power terminal equipment, and carrying out the preprocessing and analysis of the collected data, and obtaining feature information; in combination with the preprocessed terminal data information, establishing a terminal state detection neural network model, inputting data acquired in real time into a trained deep learning model, and judging the offline state of the terminal equipment through model detection; according to the obtained historical recovery time and basic cost of the terminal and in combination with an output result of the terminal state detection neural network model, monitoring a self-weight starting process; and comparing the obtained terminal self-weight starting success efficiency with the preset terminal self-weight starting success efficiency, and optimizing the set self-weight st