Missile trajectory defense planning and data simulation based on deep learning algorithm

At present, distributed research on the inference process of neural networks mainly spreads the different stages of neural network functions to multiple devices. Many devices do not perform calculations simultaneously, and due to their dependence on multiple devices, their error rate is low and resource utilization is also low. On this issue, this article proposes a design scheme for distributed neural networks. Modern warfare requires increasingly high tactical requirements for high speed, high precision, and long-range strike capabilities. On the other hand, the diversity and complexity of missile missions may lead missiles to move toward informatization and intelligence. The relevant guidance and control systems will face many challenges. The environment in which missiles fly has undergone significant changes with the expansion of their range, and attack missions have evolved from unidirectional to complementary directions. Controlling self-adjusting flight and internet orbit planning have become the primary requirements for the next generation of information missiles. Therefore, this research is aimed at determining distributed neural network algorithms for coastal atmospheric characteristics, as well as protection plans for missile trajectory attacks.