Power plant fan system abnormal working condition detection method based on one-dimensional convolution

The invention relates to the technical field of power plant fan system detection, in particular to a power plant fan system abnormal working condition detection method based on one-dimensional convolution, which comprises the following steps: step 1, data processing including data acquisition, abnormal sample elimination, data standardization and data set division; 2, constructing a one-dimensional convolution regression model of auxiliary variables and fan power, and setting model parameters by using an Adam optimization algorithm; 3, comparing and evaluating the model prediction performance by adopting the model prediction performance evaluation index; and 4, constructing a monitoring model by using the deviation between the predicted value of the model and the power measured value of the fan, monitoring the variation trend of the deviation in real time, performing early warning in time, monitoring the state of the equipment on line, and performing timely and accurate early warning at the early stage of fau