Machine learning-based out-of-bore speed control method, device and system

Abstract

The invention discloses a machine learning-based out-of-bore speed control method, device and system, and belongs to the technical field of electricians and electrical appliances. The method comprises the steps: S1, obtaining the corresponding moments and speeds (t1, v1, t2 and v2) when an armature of an electromagnetic rail gun arrives at a first preset position and a second preset position of a launching track and corresponding trigger signals (n0 and t0) in various emergent states; S2, taking the moment speed signals (t1, v1, t2 and v2) corresponding to various emergent states as dependent variables, and taking the trigger signals (n0 and t0) corresponding to various emergent states as independent variables to train a machine learning model; S3, acquiring moment speed signals (t1 *, v1 *, t2 * and v2 *) corresponding to the current emitting state, and processing the moment speed signals (t1 *, v1 *, t2 * and v2 *) by using the trained machine learning model to obtain current trigger signals (n0 * and t0 *); and S4, when the triggering moment t0 * is reached, controlling n0 * pulse power supplies to drive the armature of the electromagnetic rail gun. The trained machine learning model is adopted to solve the trigger signal of the out-of-bore speed, so that the control precision of the out-of-bore speed can be improved.

Description

technical field [0001] The invention belongs to the technical field of electrical appliances, and more specifically relates to a machine learning-based method, device and system for controlling the chamber discharge speed. Background technique [0002] With the development of modern artillery firing technology, many new problems have been raised in the study of internal ballistics. For artillery weapons, whether it is to improve the effective combat capability of anti-aircraft weapons, or to develop anti-tank weapons to deal with new types of armored targets in the future, and to suppress weapons that provide fire support to infantry on a large depth and wide front, it is required to greatly increase the projectile muzzle velocity and muzzle kinetic energy. The traditional artillery launch technology uses the chemical energy released by the combustion of the propellant to drive the projectile. Due to the limitations of the energy density of the chemical propellant, the ther...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above defects or improvement needs of the prior art, the present invention provides a machine learning-based method, device and system for controlling the speed of the chamber, the purpose of which is to use the machine learning algorithm to learn the collected speed time signal and trigger signal, Then use the trained machine learning model to process the collected current speed and time signal to obtain the current trigger signal, and then use the current trigger signal to discharge and drive the armature, thereby solving the technical problem of low launch accuracy of the existing electromagnetic launch system

Images