Distribution network fault studying and judging method based on artificial intelligence

The invention discloses a distribution network fault research and judgment method based on artificial intelligence, and the method comprises the steps: S1, obtaining original data, and carrying out the preprocessing of the original data; s2, storing the preprocessed data into a database; s3, establishing a learning machine model, inputting the data into the learning machine model to train the model, and obtaining a tripping event judgment model; inputting into a learning machine model to train the model to obtain a tripping event judgment model; and S4, evaluating the performance of the tripping event judgment model by using a k-fold cross validation method, and adjusting the tripping event judgment model according to a result. By introducing an artificial intelligence technology, approximate reasoning and linguistic variables in human thinking can be fully simulated to express expert experience, and self-learning and diagnosis algorithm logic adjustment can be continuously performed based on increase of hist