Abstract: Aiming at the shortcomings of traditional dam monitoring model, the research on combinative application of Artificial Bee Colony algorithm and BP neural network in dam deformation monitoring were carried out, in terms of modeling principle, realization methodology and engineering case, on the basis of improving the traditional Artificial Bee Colony (ABC) algorithm. The adaptive proportion and average Euclidean distance were introduced into standard Artificial Bee Colony algorithm for overcoming the local optimal. Then, the initial weights and thresholds of BP neural network were optimized by the improved Artificial Bee Colony algorithm. Engineering application results showed that the combination of the improved Artificial Bee Colony algorithm and BP neural network technology can be used to establish dam deformation monitoring model, and effectively improve the model′s fitting and forecasting ability.