The invention relates to the technical field of power system maintenance and particularly relates to a high-voltage circuit breaker fault early warning method based on electric power Internet of Things. The method comprises the steps of (A) acquiring historical detection data, (B) manually setting a fault source, enabling a high-voltage circuit breaker to work until a fault occurs, and periodically detecting to obtain detection data, (C) obtaining sample data and training a fault research and judgment neural network model, (D) extracting precursor reference data, (E) emitting fault early warning if a difference between the detection data and the precursor reference data is smaller than a set threshold value, and (F) inputting the detection data into a fault early warning neural network model if the fault exists and sending out a fault alarm. The method has the substantive effects that the fault research and judgment can be rapidly carried out on the high-voltage circuit breaker throughthe detection data, the early warning is carried out on the fault of the high-voltage circuit breaker, maintenance personnel are prompted to carry out targeted maintenance, and the maintenance of thehigh-voltage circuit breaker is more reliable.