Underground coal mine scraper load anomaly detection method based on deep learning algorithm

The invention provides an underground coal mine scraper load anomaly detection method based on a deep learning algorithm. The underground coal mine scraper load anomaly detection method comprises the following steps that 1, historical data are extracted and preprocessed; 2) performing training set and test set division on the preprocessing result data according to the proportion; 3) based on the training set, optimizing historical monitoring variables, building a deep learning neural network, building a data loader, training the deep learning network, and generating a scraper current prediction model; 4) predicting an error statistical result through a test set to construct an error confidence interval, and further calculating an abnormal factor so as to quantify an abnormal level; and 5) the abnormal factors are combined with the variation coefficient, the amplification and the maximum current limiting value index of the real-time monitoring data to judge the abnormal mode, and intelligent alarm of the abnor