Industrial control system intrusion detection method based on time convolutional network and transfer learning

The invention provides an industrial control system intrusion detection method based on a time convolutional network and transfer learning. The method adopts a network structure combining the time convolutional network and the transfer learning. Aiming at the problems of low detection precision and low timeliness in the field of intrusion detection of the industrial control system, the method comprises the following steps: constructing an original data set by using data traffic captured in an industrial production process by utilizing the characteristic of time sequence of the data traffic of the industrial control system; performing data preprocessing on the original data set and dividing a training set and a test set; constructing a source domain pre-training model by using a time convolutional network, carrying out training processing on a training set, extracting related information features, then introducing transfer learning, transferring knowledge obtained by source domain learning to a target domain,