A NEURAL NETWORK APPROACH FOR WEAPON-TARGET ALLOCATION

PDF

Authors
  1. Berger, J.
Corporate Authors
Defence Research Establishment Valcartier, Valcartier QUE (CAN)
Abstract
The decision-making process responsible for weapon-target allocation (WTA) constitutes a key component for battle management command and control systems. Real-time constraints imposed on such systems involve very strict computational requirements on the resolution of this challenging problem. In that respect, the classical formulations considered for modeling WTA, generally prone to suffer from combinatorial explosion, suggest the development of cost-effective optimization-based techniques. In the paper, a neural network-based optimization algorithm is proposed in order to solve static WTA problems. Largely inspired from the principles of Hopfield neural networks, it exploits implicit parallelism for computing fast near-optimal solution while maintaining constraint satisfaction. The approach is currently being investigated in the context of naval anti-air warfare applicable to single and multiple platforms.
Report Number
CMR-OR-1993-P-49 — CONTAINED IN 94-06141
Date of publication
01 Mar 1993
Number of Pages
7 (49-55)
DSTKIM No
94-06136
CANDIS No
144703
Format(s):
Document Image stored on Optical Disk

Permanent link

Document 1 of 1

Date modified: