Spin-Stabilized Projectile Steering Using ML and Asymmetric Surfaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional guided projectiles face challenges in reducing the spatial volume and mass of guidance and control hardware to increase propellant, charge, and sensor volumes, thereby affecting the endurance, range, and accuracy of small calibre projectiles, particularly in steering without protruding external fins.
Innovation Solution
A computer-implemented method using a machine learning algorithm, specifically reinforcement learning, to control spin-stabilized steerable projectiles by training the algorithm with data from simulated or measured trajectories, allowing the projectile to adjust its trajectory through angular rotation of an asymmetric surface, thereby eliminating the need for external fins.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If protruding external control surfaces are used for steering, then steering capability is improved, but spatial volume and mass of control hardware increases
Solution Approach 1:
The invention extracts the control function from external protruding surfaces and relocates it to internal asymmetric mass distribution. The asymmetric mass element is positioned off-center within the projectile body, eliminating the need for external fins or control surfaces while maintaining steering capability through aerodynamic moment generation.
Solution Approach 2:
The control mechanism is nested within the projectile body. The asymmetric mass element is contained inside the projectile shell, with the mass distribution arranged such that the center of mass does not coincide with the geometric center, creating the necessary aerodynamic imbalance for steering without requiring external components.
2Ease of operation
If protruding external control surfaces are used for steering, then steering capability is improved, but mass of control hardware increases
Solution Approach 1:
The invention extracts the control function from external protruding surfaces and relocates it to internal asymmetric mass distribution. The asymmetric mass element is positioned off-center within the projectile body, eliminating the need for external fins or control surfaces while maintaining steering capability through aerodynamic moment generation.
Solution Approach 2:
The projectile employs composite construction with asymmetric mass distribution achieved through strategic placement of denser materials or voids within the projectile body. This allows mass redistribution for control purposes without adding overall projectile mass, as the control mechanism utilizes the existing structural materials in an asymmetric configuration.
3Ease of operation
If internal volume is allocated for control hardware, then steering capability is improved, but volume for propellant and explosives decreases
Solution Approach 1:
The invention extracts the control function from external protruding surfaces and relocates it to internal asymmetric mass distribution. The asymmetric mass element is positioned off-center within the projectile body, eliminating the need for external fins or control surfaces while maintaining steering capability through aerodynamic moment generation.
Solution Approach 2:
The projectile body structure serves multiple functions: it contains the propellant and explosive charges while simultaneously providing the asymmetric mass distribution necessary for steering. The same structural materials that form the projectile shell also create the control moment through their asymmetric arrangement, eliminating the need for separate dedicated control hardware volume.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy and precision of projectile steering by optimizing the use of internal space for propellant and sensors, improving the range and lethality of small calibre projectiles while reducing the reliance on external control surfaces.
Implementation Method 1
the asymmetric surface exerts an imbalance upon the projectile to control the trajectory of said projectile
Implementation Method 2
Spin-stabilized steerable projectiles
Data Source
AI summary
A computer-implemented method of training a machine learning, ML algorithm to control spin-stabilized steerable projectiles is described. The method comprises: obtaining training data including respective policies and corresponding trajectories of a set of spin-stabilized steerable projectiles including a first projectile, wherein each policy relates to steering a projectile of the set thereof towards a target and wherein each corresponding trajectory comprises a series of states in a state space of the projectile (S2001); and training the ML algorithm comprising determining relationships between the respective policies and corresponding trajectories of the projectiles of the set thereof based on respective results of comparing the trajectories and the targets (S2002).