Aiming at the acquisition probability calculation of anti ship missile (ASM) when attacking target in reef island area, the radar searching process and target acquiring requirements were analyzed and the target selection rules of terminal guidance radar were given. The calculation models of acquisition probability under the influence of reef islands were built. The target acquiring criterions which integrated distance, azimuth, resolution, and target selection constraint were presented. Based on probability distribution function, the scattering of ASM programmed flight termination was studied; the surface target motion model was built; and their influence to the probability calculation was analyzed. The acquisition probability with target indication coordinates located in different positions around reef islands and with different search sector angle were simulated. The results showed that the acquisition probabilities were lower when surface target near the island or located at strip area behind the island and higher even if surface target was located at close distance of the front side of the island; and a smaller search sector angle was better if surface target was close to the island.

Aiming at the problems that the traditional judgment methods of the main offensive direction of air attack have higher accuracy and completeness requirements on the evaluation index system, and their adaptability to some complex conditions, such as fuzzy information, missing and contradictory information is not strong, the convolution neural network is introduced into the main offensive direction judgment model. With its strong ability of nonlinear modeling and its strong adaptability to fuzzy and noisy information, the implied intuitive thinking of the person, such as experience, knowledge, and so on, is obtained through the study of large sample set. The experiments show that the new evaluation model has strong fault tolerance and good robustness.