Research on mural damage recognition method based on deep reinforcement learning

In this paper, the AE signal collected in the acoustic emission experiment of the mural collection is taken as the research object. The collected continuous mural state data are analyzed and processed, and the abnormal state information of mural cracks and falling off is extracted to obtain the sample set of disease characteristics. Wavelet transform was used to convert the collected AE signal of crack damage into a two-dimensional time-frequency image. Finally, deep reinforcement learning DQN network was used to identify the damage type. Compared with convolutional neural network, the test results showed that the damage recognition accuracy rate could reach 98%.