Countermeasuring Anti-Ship Missiles for Surface Naval Platforms: A Machine Learning Approach With Explainable Artificial Intelligence
Considering the advancements in missile technologies, particularly in infrared or radio frequency-guided missile seeker systems, threats to naval platforms have become a significant danger today. Potential missile threats have made it imperative to equip ships with the most advanced defense systems....
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11043148/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Considering the advancements in missile technologies, particularly in infrared or radio frequency-guided missile seeker systems, threats to naval platforms have become a significant danger today. Potential missile threats have made it imperative to equip ships with the most advanced defense systems. This has led to the development of newer systems with advanced technologies capable of countering various threats. The effective deployment of existing countermeasures and the determination of the most optimal platform maneuvers have also become crucial. Chaffs and flares can be launched from naval platforms as soft-kill countermeasures to address such threats within the context of conflict. This paper aims to devise effective strategies for deploying countermeasures and executing platform maneuvers against radar and infrared-guided seekers, utilizing machine learning and artificial intelligence techniques. Using a commercial simulator containing countermeasure algorithms, datasets representing large-scale scenarios have been created, and the collected data have been trained with the proposed Multilayer Perceptron model. This model has been used to predict target parameters. The simulator includes parameters for the ship, missile, and chaff/flare. Launcher configurations have also been incorporated into the evaluated ship model. The model’s success was assessed through predefined performance metrics, and the results were visualized transparently using explainable artificial intelligence. The authors believe that the proposed model can be further improved and integrated with existing countermeasure techniques. |
|---|---|
| ISSN: | 2169-3536 |