Method for predicting online patrol result state of power transmission line

The invention belongs to the technical field of power transmission line inspection, and particularly relates to a method for predicting the online inspection result state of a power transmission line.The method mainly comprises the following steps: periodically acquiring data, generating training sample data, splitting a sample data set, predicting by adopting a logistic regression binary classification model, establishing a model, solving by adopting a gradient descent method, training the model, evaluating the model by adopting an AUC evaluation index, and updating the model. Evaluation indexes obtained by training the collected data in the previous period are compared with the evaluation indexes obtained by currently collecting the data, and whether the current model is used for replacing the model in the previous period or not is judged according to the size. The beneficial effects of the invention are that the method employs the machine learning technology, carries out the intelligent evaluation and pred