Fire trajectory analysis method for firearms

Abstract

The application discloses a shooting trajectory analysis method of a firearm, and relates to the field of firearm analysis.The method comprises the following steps: S1, acquiring firearm shooting information to be analyzed; S2, extracting features of each shooting information; a previous predicted action trajectory and a previous shooting action trajectory are introduced into an SCM neural network model for online learning, and a covariance matrix is corrected; a predicted action trajectory is obtained by introducing current shooting information into the SCM neural network model after learning; S3, identifying local action trajectories according to the extracted features; S4, performing time-space alignment and covariance fusion between action trajectories to obtain a complete shooting action trajectory; the service life of the firearm is accurately estimated by collecting firearm shooting action features in all aspects through multidimensional sensors and constructing a multi-sensor fusion algorithm. Multi-sensor collaborative fusion uses multiple sensors to generate a new scene, and by using a Kalman filter, the speed, position and action of an object are estimated by fusing data.

Description

Technical Field

[0001] This invention relates to the field of firearms analysis, and more particularly to a method for analyzing the firing trajectory of firearms. Background Technology

[0002] In the context of the military's current efforts to advance informatization and develop a scientific approach to support, shifting from qualitative to quantitative analysis of firearm maintenance and lifespan management is of great significance for improving the level of scientific management and informatization in ordnance support.

[0003] The chamber and rifling are the main parts through which a bullet passes during firing, resulting in a significant accumulation of gunpowder residue after each shot. Accurately capturing and analyzing the firing action of a firearm, along with statistical analysis of the number of shots fired, can promptly identify or predict barrel wear, allowing for timely maintenance and upkeep. This extends the lifespan of the firearm, reduces malfunctions, ensures the weapon is always in optimal condition, and further improves firearm maintenance. However, current firearm management technologies lack a simple method for capturing firing action and calculating the number of shots, thus failing to provide information for determining the lifespan of firearms and establishing ideal maintenance plans. Summary of the Invention

[0004] The purpose of this invention is to design a method for analyzing the firing trajectory of firearms in order to solve the above-mentioned problems.

[0005] The present invention achieves the above objectives through the following technical solutions:

[0006] Methods for analyzing the firing trajectory of firearms include:

[0007] S1. Obtain the firing information of the firearm to be analyzed. The firing information includes the vibration information, pressure information, recoil information, acceleration information and angular velocity information of the firearm during firing.

[0008] S2. Extract the features of each shooting information; import the previous predicted action trajectory and the previous shooting action trajectory into the SCM neural network model for online learning, and correct the covariance matrix; import the current shooting information into the learned SCM neural network model to obtain the predicted action trajectory.

[0009] S3. Identify local motion trajectories based on the extracted features;

[0010] S4. Based on the local action trajectory, the modified covariance matrix is ​​used to perform spatiotemporal alignment and covariance fusion between action trajectories to obtain the complete shooting action trajectory.

[0011] The beneficial effects of this invention are as follows: By comprehensively collecting the characteristics of firearm firing actions through multi-dimensional sensors, a multi-sensor fusion algorithm is constructed to accurately estimate the service life of the firearm. Multi-sensor collaborative fusion uses multiple sensors to generate a new scene, and utilizes a Kalman filter to estimate the velocity, position, and motion of objects through data fusion, thereby capturing the firing action. This allows for the calculation of the number of shots, providing information for the service life of the firearm and an ideal maintenance plan. Attached Figure Description

[0012] Figure 1 This invention relates to a distributed fusion processing structure for multi-sensor data;

[0013] Figure 2 This invention is a sequential form of the covariance cross-fusion algorithm;

[0014] Figure 3 This is a structural diagram of the SCM neural network model of the present invention. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0016] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0017] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0018] In the description of this invention, it should be understood that the terms "upper," "lower," "inner," "outer," "left," "right," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this invention is in use, or the orientation or positional relationship commonly understood by those skilled in the art. They are only used to facilitate the description of this invention and to simplify the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0019] Furthermore, the terms "first," "second," etc., are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0020] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, terms such as "set" and "connection" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0021] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0022] like Figure 1 As shown, the method for analyzing the firing trajectory of a firearm is characterized by including:

[0023] S1. Acquire the firearm firing information to be analyzed through c sensors. The firing information includes vibration information, pressure information, recoil information, acceleration information and angular velocity information during firearm firing.

[0024] S2. The sensors extract the features of each shooting information; the previous predicted action trajectory and the previous shooting action trajectory are imported into the SCM neural network model for online learning, and the covariance matrix is ​​corrected. The current shooting information is imported into the learned SCM neural network model to obtain the predicted action trajectory.

[0025] like Figure 3 As shown, the SCM neural network model includes an input layer, a hidden layer, a receiving layer, and an output layer. The input layer is used to receive firearm shooting information, the output of the hidden layer at the previous time step returned by the receiving layer, and the shooting trajectory at the previous time step. The hidden layer performs linear or nonlinear transformations on the information output by the input layer. The receiving layer is used to store the output of the hidden layer at the previous time step and return it to the input layer. The output layer performs linear weighting on the information output by the hidden layer at the current time step and outputs it.

[0026] Where y represents the output vector of the output layer of the SCM neural network model, x represents the output vector of the hidden layer, u represents the output vector of the input layer, and Xc represents the output vector of the connecting layer. w1, w2, and w3 represent the connection weight matrices from the connecting layer to the hidden layer, from the input layer to the hidden layer, and from the hidden layer to the output layer, respectively.

[0027] S3. Each sensor is equipped with an unscented Kalman filter, which identifies local motion trajectories based on the extracted features. , where i = 1, 2, 3...c, and c is the number of sensors;

[0028] S4. Based on the local motion trajectory, the modified covariance matrix is ​​used for spatiotemporal alignment and covariance fusion between motion trajectories to obtain the complete shooting motion trajectory, such as... Figure 2 As shown, it specifically includes:

[0029] S41. Randomly select two local motion trajectories and fuse them to obtain the first fusion result. ;

[0030] S42. The first fusion result is fused with any other local motion trajectory to obtain the second fusion result. ;

[0031] S43. Determine whether all local motion trajectories have been successfully fused. If so, use the second fusion result as the shooting motion trajectory; otherwise, use the second fusion result as the first fusion result and return to S42.

[0032] The working principle of the firearm firing trajectory analysis method of this invention is as follows:

[0033] Each sensor first extracts features from the collected data source, performs motion analysis processing within a local Kalman filter, identifies its own local motion trajectory data, and then performs spatiotemporal alignment and correlation fusion between the local motion trajectories from each sensor in the fusion center, finally outputting the final shooting motion trajectory.

[0034] Building upon this, a distributed motion trajectory fusion algorithm based on the SCM neural network was designed using UKF filtering. Each sensor is configured with an unscented Kalman filter. At each fusion time, multiple local motion trajectories are first generated, and then these local motion trajectories are sequentially cross-fused using covariance. After obtaining the fused estimate of the target, the residual data between the state prediction and the optimal estimate is input into the SCM neural network for online learning. This data compensates for the fusion result and corrects the covariance matrix.

[0035] The technical solutions of the present invention are not limited to the specific embodiments described above. Any technical modifications made in accordance with the technical solutions of the present invention fall within the protection scope of the present invention.

Claims

1. A method for analyzing the firing trajectory of firearms, characterized in that, include: S1. Obtain the firing information of the firearm to be analyzed. The firing information includes the vibration information, pressure information, recoil information, acceleration information and angular velocity information of the firearm during firing. S2. Extract features from each shooting information; import the previous predicted action trajectory and the previous shooting action trajectory into the SCM neural network model for online learning, and correct the covariance matrix; import the current shooting information into the learned SCM neural network model to obtain the predicted action trajectory; the SCM neural network model includes an input layer, a hidden layer, a receiving layer, and an output layer. The input layer is used to receive firearm shooting information, the output of the hidden layer at the previous time step returned by the receiving layer, and the shooting action trajectory at the previous time step. The hidden layer performs linear or nonlinear transformation on the information output by the input layer. The receiving layer is used to store the output of the hidden layer at the previous time step and return it to the input layer. The output layer performs linear weighting on the information output by the hidden layer at the current time step and outputs it. S3. Identify local motion trajectories based on the extracted features; S4. Based on the local action trajectory, the modified covariance matrix is ​​used to perform spatiotemporal alignment and covariance fusion between action trajectories to obtain the complete shooting action trajectory.

2. The method for analyzing the firing trajectory of a firearm according to claim 1, characterized in that, The various shooting information is obtained through multiple sensors, each equipped with an unscented Kalman filter. The sensors are used to collect the corresponding shooting information and extract features, while the unscented Kalman filter is used to identify the local motion trajectory of each shooting information.

3. The method for analyzing the firing trajectory of a firearm according to claim 1, characterized in that, In S4, covariance fusion specifically involves: S41. Select any two local motion trajectories and fuse them to obtain the first fusion result; S42. The first fusion result is fused with any other local motion trajectory to obtain the second fusion result; S43. Determine whether all local motion trajectories have been successfully fused. If so, the second fusion result shall be used as the shooting motion trajectory. Conversely, if the result is different, the second fusion result is used as the first fusion result, and the process is returned to S42.

Images