Initial in-situ stress field is an important basis for the design and construction of underground engineering, it is difficult to accurately measure the initial in-situ stress field in practical engineering, in order to accurately obtain distribution law of initial geostress field, the immune algorithm combined with BP neural network (IA-BP algorithm) for inversion of initial in-situ stress field is studied. The optimization of BP neural network by immune algorithm is to encode the connection weights and thresholds of BP neural network as antibodies in the immune algorithm. The hybrid algorithm can not only advantage of the characteristics of immune algorithm is global optimization quick search to the global optimal solution or near optimal solution, and can adopt BP algorithm to avoid the near optimal and sub-optimal solutions, oscillation on the local optimization, so as to achieve the aim of fast converge the global optimal solution. The three-dimensional model was constructed by COMSOL to carry out positive analysis and calculation, and the calculated results were taken as “measured values” to conduct inversion analysis of in-situ stress, and the inversion results of IA-BP algorithm were compared with the inversion results of PSO-BP algorithm and multiple linear regression algorithm. The results show that the absolute value of the relative error between the measured value and the inversion value are obtained by IA-BP algorithm is 0~10.64%(3.39% on average), the absolute value of the relative error between the measured value and the inversion value are obtained by PSO-BP algorithm is 0~48.39% (6.93% on average), the absolute value of the relative error between the measured value and the inversion value are obtained by multiple linear regression algorithm is 0.55%~121.95% (21.87% on average). By comparison, it can be known that the overall inversion results of IA-BP algorithm have the highest accuracy. The application of IA-BP intelligent algorithm to the inversion of in-situ stress field can provide help and basis for the construction of underground engineering.