Optimal radar pulse scheduling using a neural network

In a multifunction radar, the maximum number of targets which can be managed (maintain their tracks) is one of the main performance figures. The interleaving algorithms exploit the dead times between the transmitted and the received pulses to allocate new tracking tasks (transmit and receive pulses) thus increasing the capacity of the system. Generally speaking, the interleaving of N targets is a complex problem (NP-complete type) and sub-optimal solutions are usually employed to satisfy the real-time constraints of the radar system. In this paper we design an optimal interleaving algorithm based on a Hopfield network. We describe the general problem, define the network and select the criteria to design the weights. Finally as an example, we simulate a simple scenario with five targets.<
>