Buckling leads the failure of thin-walled cylinders under axial compression. Due to the manufacturing imperfection, a significant variation was observed between experimental and theoretical buckling load. The current design criteria use knockdown factor to estimate the buckling of thin-walled structures. However, since it is difficult to accurately predict the knockdown factor, the design criteria employed a very conservative knockdown factor. In order to give a better knockdown factor, in this paper, the physics-informed artificial neural network (PANN) were employed to predict the thin-walled cylinder buckling load using experimental data. The PANN has potential to reduce the training data size and improve the convergence. A beam problem was presented to demonstrate the PANN capability. Then, the cylinder buckling analysis was carried out with PANN. The result shows PANN can accurately predict the buckling load with the experimental data from NASA.