Neural Network Impact Point Prediction for Non-Linear Maneuvering Missiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in predicting the impact point of ballistic missiles capable of non-linear maneuvers, as these missiles evade traditional radar detection and interception methods by changing their flight trajectory.
Innovation Solution
A method and device that utilize a neural network model to predict the impact point of a non-linear maneuvering flying object by acquiring detection information from radar and prior information about enemy and friendly units, determining if the object is capable of non-linear maneuver, and calculating the impact point based on this determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional radar detection methods are used to track ballistic missiles, then detection is effective for typical parabolic trajectories, but detection and prediction fail when missiles perform non-linear maneuvers below radar loss altitudes
Solution Approach 1:
The system changes the parameters used for trajectory prediction from simple parabolic models to complex neural network models that can process multiple input parameters including dynamic characteristic information, prior information about enemy units, and radar detection data. This allows the system to adapt to non-linear maneuvers while maintaining detection reliability.
Solution Approach 2:
The patent introduces an intermediary neural network model that acts as a mediator between radar detection data and impact point prediction. This intermediary processes detection information and prior information to determine non-linear maneuver capability, bridging the gap between traditional detection methods and modern maneuvering missile threats.
2Measurement precision
If a neural network model is introduced to predict non-linear maneuver impact points, then prediction accuracy improves for maneuvering missiles, but system complexity increases
Solution Approach 1:
The patent segments the prediction system into distinct functional modules: a detection information acquisition module, a prior information management module, a neural network processing module, and an impact point calculation module. This segmentation allows the complex neural network functionality to be integrated while maintaining system manageability and reducing operational complexity.
Solution Approach 2:
The system performs preliminary actions by pre-processing and storing prior information about enemy units, friendly units, and facilities before they are needed for prediction. This preliminary preparation reduces the computational burden during real-time prediction, thereby reducing operational complexity while maintaining high prediction accuracy.
3Loss of information
If dynamic characteristic information is extracted by replaying radar images, then detection capability below radar loss altitudes improves, but information processing time increases
Solution Approach 1:
The system performs preliminary action by pre-processing radar images and extracting dynamic characteristic information in advance, storing it for rapid retrieval during prediction. This reduces real-time processing time while maintaining complete information retention about missile behavior below radar loss altitudes.
Solution Approach 2:
The patent uses copying by creating replayed versions of radar images that contain embedded dynamic characteristic information. This allows the system to access and process missile trajectory information multiple times without re-processing the original radar data, reducing processing time while preserving information about non-linear maneuvers.
Data Source
AI summary
A method for predicting an impact point is proposed. The method may include acquiring detection information related to a flying object detected by a radar linked to the impact point predicting device through a communication interface, acquiring prior information including information about an enemy unit, a friendly unit, and a friendly facility. The method may include determining whether the detected flying object is a flying object capable of non-linear maneuver based on the detection information and the prior information, using a neural network model pre-trained using training data so that the neural network model determines whether the flying object is the flying object capable of non-linear maneuver based on detection information and prior information and determining an impact point based on the detection information, the prior information, and a determining result of the neural network model on whether the detected flying object is the flying object capable of non-linear maneuver.