Due to good thermal conductivity and corrosion resistance, copper has become common material for transmission pipeline. It is necessary to detect the early damage of copper pipeline effectively and quickly. Laser ultrasound scanning is non-contact and non-destructive damage identification method, which can realize high-precision, non-contact detection. At the same time, with the progress of internet technology, the traditional damage testing began to use advanced technologies such as internet of things and cloud computing to promote the upgrading of the testing industry from offline to online. However, obtaining large number wavefield vibration data is time consuming. In this paper, a laser ultrasonic scanning cloud platform damage detection method for copper pipeline based on alternating learning Blind Compressive Sensing (BCS) and Adjacent Area Difference Coefficient (AADC) is presented, which can improve the real-time performance and the detection accuracy. Firstly, the damage detection method is introduced in detail. BCS is used to compress the laser scanning signal at the data acquisition terminal, and then transmitted to data processing cloud platform for reconstruction. Taking the AADC value of each measuring point as the pixel value, the copper tube damage imaging is realized. Then, the simulated detection data of copper pipeline are obtained through the finite element model, and the weighted vector of AADC are determined by genetic algorithm. Finally, experimental are used to verify the effectiveness of this method, and the experimental results are analyzed and discussed. The AADC and other distance damage imaging methods are compared. The results show that this method can compress the wavefield data to 13% of the original data, and realize the damage detection.