Jacket platforms are commonly used structures in offshore operations, and their health status determines the safety of the ocean development process. Aiming at the problem of extracting damage-sensitive features during the damage detection process of jacket platform, a damage detection model based on deep learning is proposed. In order to better fit the characteristics of the convolutional neural network, this model first converts the one-dimensional time domain signal into a two-dimensional grayscale image; then extracts the damage features existing in the two-dimensional grayscale image through the convolutional neural network and This is used for damage detection. Through experiments on the jacket platform model, the effects of different grayscale image generation methods on the detection results were compared. Finally, the results of damage detection experiments show that the detection model can identify damage types with an accuracy of 99.4% , and has good damage detection capabilities; The accuracy of identifying the degree of damage is 96.3%, and it can be applied to damage early warning of jacket platforms.