Technical gazette, Vol. 30 No. 1, 2023.
Original scientific paper
https://doi.org/10.17559/TV-20220113192727
Solving Weapon-Target Assignment Problem with Salp Swarm Algorithm
İsa Avci
orcid.org/0000-0001-7032-8018
; Karabuk University, Kastamonu Yolu Demir Çelik Kampüsü, 78050 Kılavuzlar, Karabük, Türkiye
Mehmet Yildirim
; Karabuk University, Kastamonu Yolu Demir Çelik Kampüsü, 78050 Kılavuzlar, Karabük, Türkiye
Abstract
The weapon target problem is a combinatorial optimization problem. It aims to have the weapons on target properly assigned for the intended purposes. When focused on its target, it does things with its effective attack research in mind. It is an ongoing problem program to minimize survivors. This study, using the weapon target assignment model calculates the expected probabilities on the target with the salp model. The nature of this SHA model is designed to be appropriately predicted for this particular use. The Salp Swarm Algorithm (SSA) is a metaheuristic method of methods approaching the solution set as an approximation. Optimum solution or optimum example is in a working example. This study was done with 12 problem examples (200 training and 200 targets with pleasure to observe, to test the efficiency of SSA). In the problem, the iteration resulted in optimum results at the end of the definite usage time. Best value included 48.355 for WTA1, 92.654 for WTA2, 174.432 for WTA3, 155.658 for WTA4, 250.784 for WTA5, 284.967 for WTA6, 247.458 for WTA7, 362.636 for WTA8, 524.732 for WTA9, 548.580 for WTA10, 601.654 for WTA11, and WTA16812. It was obtained by finding in 200,000 iterations and the result value was 50. After 200000 improvements, it was observed to relax to increase iteration. The use of barter when generating new solutions to the problem. To find out the fitness values, mean, best, and worst values were found.
Keywords
metaheuristic optimization; particle-wide optimization; salp swarm algorithm; search weapons; target assignment
Hrčak ID:
288391
URI
Publication date:
15.12.2022.
Visits: 1.491 *