PGK precise guidance system and method for guided missile
By installing a PGK precision guidance system on the missile without using GPS module, using infrared target detection, inertial measurement and binocular intersection measurement technology, combined with reinforcement learning for target positioning, the problem of GPS module being susceptible to interference is solved and the missile's Strike accuracy.
Patent Information
- Application Number
- CN202510017946.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-06
- Publication Date
- 2025-02-18
AI Technical Summary
GPS modules are susceptible to geomagnetic and artificial electromagnetic signals, affecting the missile's strike accuracy.
The PGK precision guidance system without GPS module is adopted, and the target positioning is performed through infrared target detection components, inertial measurement components, navigation systems and control modules, combined with binocular intersection measurement technology and reinforcement learning.
The missile strike accuracy is improved and the impact of geomagnetic and artificial electromagnetic signal interference is avoided.
Smart Images
Figure CN119468815A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a PGK precision guidance system and method for missiles, belonging to the technical field of electrical data processing. Background Art
[0002] In modern warfare, the requirements for the precision strike capability of relative ammunition are getting higher and higher, but the accuracy of missiles has increased, and the price is unaffordable. Therefore, low-cost ballistic correction bombs with certain strike accuracy have been born. That is, the ballistic correction fuze is replaced in the position of the ammunition fuze to enable it to have a certain ballistic correction capability and improve the strike accuracy of artillery shells and rockets. The principle is to pre-set the ideal trajectory information based on information such as target coordinates, calculate the difference between the trajectory calculation and the ideal trajectory after launch, and control the correction mechanism to make corrections as close to the ideal trajectory as possible. Although this cannot keep up with the accuracy of the missile's continuous correction, it obtains the best cost-effectiveness in the kill zone, so it has become a popular technology.
[0003] The precision guidance kit (PGK) is a guidance kit that couples GPS and inertial guidance. It has a fuze function to reduce the ballistic dispersion of the artillery shells, and the miss distance is increased from hundreds of meters to less than 20 meters. Improving accuracy can use fewer shells, increase the damage effect, and reduce the possibility of damage to incidental infrastructure and civilian facilities. This fuze is actually a satellite guidance kit with correction canards on it, which can be directly screwed on ordinary artillery shells to turn ordinary grenades into satellite-guided artillery shells. After using the precision guidance kit, the amount of artillery shells used by artillery can be reduced by 74%, which also means saving 75% of the total weight, greatly improving combat effectiveness and deployment capabilities. However, GPS is susceptible to interference and failure, and GPS signals are susceptible to geomagnetism and interference from artificial electromagnetic signals, affecting strike accuracy. Summary of the invention
[0004] The purpose of the invention is to provide a PGK precision guidance system and method for missiles, which does not use a GPS module and is therefore not interfered by geomagnetic or artificial electromagnetic signals. Target positioning is performed through binocular intersection measurement and reinforcement learning, and the strike accuracy is high.
[0005] To achieve the above-mentioned invention object, the present invention provides a PGK precision guidance system for missiles, which includes a PGK kit, which is installed on the missile head, and includes an infrared target detection component, an inertial measurement component, a navigation system and a control module. The infrared target detection component includes a first infrared camera and a second infrared camera. The first infrared camera is used to obtain first image information of a target object struck by a missile equipped with the PGK kit and provide the first image information to the navigation system. The second infrared camera is used to obtain second image information of a target object struck by a missile equipped with the PGK kit and provide the second image information to the navigation system. The inertial measurement component is used to measure the angular velocity and acceleration of the missile equipped with the PGK kit and provide them to the navigation system. The navigation system calculates the sight unit vector of the missile equipped with the PGK kit relative to the target at time k according to the information provided by the first infrared camera, the second infrared camera and the inertial measurement component. , the rotation rate of the sight line relative to the target , the velocity vector relative to the target The distance to the target and provide it to the control module; the control module includes a reinforcement learning module, which controls the optimal line of sight curvature at time k Generate flight instructions , is the state of the missile with the PGK kit installed relative to the target at time k, .
[0006] To achieve the above-mentioned object of the invention, the present invention provides a PGK precision guidance method for a missile, which comprises the following steps: Step 1: Install the PGK kit on the missile head, wherein the PGK kit includes an infrared target detection component, an inertial measurement component, a navigation system and a control module; the infrared target detection component includes a first infrared camera and a second infrared camera; the control module includes a reinforcement learning module; Step 2: Acquire first image information of a target object hit by a missile equipped with a PGK kit through a first infrared camera and provide the first image information to a navigation system; acquire second image information of a target object hit by a missile equipped with a PGK kit through a second infrared camera and provide the second image information to a navigation system; Step 3: Measure the angular velocity and acceleration of the missile with the PGK kit installed through the inertial measurement unit and provide it to the navigation system; Step 4: The navigation system calculates the sight unit vector of the missile with the PGK kit installed relative to the target at time k based on the information provided by the first infrared camera, the second infrared camera, and the inertial measurement unit. , the rotation rate of the sight line relative to the target , the velocity vector relative to the target The distance to the target and provide it to the control module; Step 5: The reinforcement learning module controls the strategy according to the optimal line of sight curvature at time k Generate flight instructions , is the state of the missile with the PGK kit installed relative to the target at time k, .
[0007] Compared with the prior art, the PGK precision guidance system and method for missiles provided by the present invention do not use a GPS module, and therefore will not be interfered by geomagnetic or artificial electromagnetic signals. Target positioning is performed through binocular intersection measurement technology and reinforcement learning, and the strike accuracy is high. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] Figure 1 It is a block diagram of the composition of the PGK precision guidance system for missiles provided by the first embodiment of the present invention. DETAILED DESCRIPTION
[0009] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0010] Figure 1 FIG. 5 is a block diagram of a PGK precision guidance system for a missile provided by a first embodiment of the present invention, such as Figure 1 As shown, the PGK precision guidance system for missiles provided by the first embodiment of the present invention includes a PGK kit, and the PGK kit includes an infrared target detection component, an inertial measurement component, a navigation system and a control module. The infrared target detection component includes a first infrared camera and a second infrared camera. The first infrared camera is used to obtain first image information of a target object struck by a missile equipped with the PGK kit and provide the first image information to the navigation system. The second infrared camera is used to obtain second image information of a target object struck by a missile equipped with the PGK kit and provide the second image information to the navigation system. The inertial measurement component is used to measure the angular velocity and acceleration of the missile equipped with the PGK kit and provide them to the navigation system. The navigation system calculates the line of sight unit vector of the missile equipped with the PGK kit relative to the target at time k based on the information provided by the first infrared camera, the second infrared camera and the inertial measurement component. , the rotation rate of the sight line relative to the target , the velocity vector relative to the target The distance to the target and provide it to the control module; the control module includes a reinforcement learning module, which controls the optimal line of sight curvature at time k Generate flight instructions , is the state of the missile with the PGK kit installed relative to the target at time k, .
[0011] In the first embodiment, the optimal sight curvature control strategy is obtained The steps include: S1-01: Initialize the state value function V and the line of sight curvature control strategy ; S1-02: Let c←1, where c is the number of superposition steps; S1-03: Calculate the state o of the missile with the PGK kit relative to the target at time k according to the following formula: k The state value function value at time: , In the formula, is the state o of the missile with the PGK kit installed at time k relative to the target k Execute flight instructions Transfer to the state o relative to the target object k+1 probability; is the state o of the missile with the PGK kit installed at time k relative to the target k Execute flight instructions Transfer to the state o relative to the target object k+1 the reward received; is the state o relative to the target at time k+1 k+1 The state value function; U represents the flight instruction set of the missile equipped with the PGK kit to fly in all directions, and S represents the state set of all missiles equipped with the PGK kit relative to the target; For the improved sight curvature control strategy; S1-04: Judgment Is it less than or equal to the threshold value? If yes, execute step S1-08; if no, execute step S1-05; S1-05: , the state-action function is calculated according to the following formula: ; S1-06: Improve the sight curvature control strategy according to the following formula: , where Indicates the flight instruction when the function value reaches the maximum , o means the flight instruction is The state of the object relative to the target; S1-07: Make c←c+1, And return to S1-03; S1-08: Output the optimal sight curvature control strategy .
[0012] In a first embodiment, the navigation system includes an image processing module and a matching module, wherein the navigation system includes an image processing module and a matching module, wherein the image processing module extracts L candidate first image regions from the first image , extract R candidate second image regions from the second image The matching module Q matches the target template Q with the L candidate first image regions to obtain the left image of the target object in the first image. , and also matches the target template Q with the R candidate second image regions to obtain the right image of the target object in the second image , L and R are both positive integers greater than or equal to 1.
[0013] In the first embodiment, the matching module Q matches the target template with L candidate first image regions. Matching is performed to obtain the left image of the target object in the first image Specifically include: Given the target template Q, take the center of the image template Q as the center and the center angle and radius The image template Q is radially sampled to produce The feature vector of the target template ; Make the feature vectors of two adjacent target templates Q of the same radius form a tuple ; Given the first image region , with the first image area The center of the circle is the center, with the central angle and radius For the first image area Perform radial sampling to generate The feature vector of the first image region ; Make the adjacent two first image areas of the same radius The feature vectors of ; The left image of the selected object in the first image is obtained by the following formula : , In the formula, , , is a hyperparameter, represents the two-norm, Represents the first image region where the function value is minimized.
[0014] In the first embodiment, the matching module Q matches the target template with R candidate second image regions. Matching is performed to obtain the right image of the target object in the second image Specifically include: Given the target template Q, take the center of the image template Q as the center and the center angle and radius The image template Q is radially sampled to produce The feature vector of the target template ; Make the feature vectors of two adjacent target templates Q of the same radius form a tuple ; Given the second image region , with the second image area The center of the circle is the center, with the central angle and radius For the second image area Perform radial sampling to generate The feature vector of the second image region ; Make the adjacent two second image areas of the same radius The feature vectors of ; The right image of the target object in the second image is obtained by the following formula : , In the formula, , , is a hyperparameter; represents the second norm, Represents the second image region where the function value is minimized.
[0015] In the present invention, N rotation angles
[0016] The present invention can perform rapid target matching through the above technical solution.
[0017] In the first embodiment, the navigation system further includes a target positioning module, wherein the target positioning module locates the target object according to the left image of the target object. Position in the first image, right image of the target The position in the second image, the distance between the center of the first infrared camera lens and the center of the second infrared camera lens, and the parameters of the first infrared camera lens and the second infrared camera lens are determined by binocular intersection measurement technology to determine the distance of the missile equipped with the PGK kit relative to the target.
[0018] The PGK precision guidance system for missiles provided in the first embodiment of the present invention also includes a controller and a flight mechanism. The processor provides the flight instructions provided by the main line of sight curvature control strategy to the controller, and the controller generates flight instructions for the missile flight mechanism according to the flight instructions.
[0019] The PGK precision guidance system for missiles provided in the first embodiment of the present invention does not use a GPS module, and therefore will not be interfered by geomagnetic or artificial electromagnetic signals. It locates the target through binocular intersection measurement technology and reinforcement learning, and has high strike accuracy.
[0020] Second embodiment
[0021] The second embodiment of the present invention only describes the contents that are different from the first embodiment, and the same contents are not repeated.
[0022] A PGK precision guidance method for a missile provided by a second embodiment of the present invention comprises the following steps: Step 1: Install the PGK kit on the missile head, wherein the PGK kit includes an infrared target detection component, an inertial measurement component, a navigation system and a control module; the infrared target detection component includes a first infrared camera and a second infrared camera; the control module includes a reinforcement learning module; Step 2: Acquire first image information of a target object hit by a missile equipped with a PGK kit through a first infrared camera and provide the first image information to a navigation system; acquire second image information of a target object hit by a missile equipped with a PGK kit through a second infrared camera and provide the second image information to a navigation system; Step 3: Measure the angular velocity and acceleration of the missile with the PGK kit installed through the inertial measurement unit and provide it to the navigation system; Step 4: The navigation system calculates the sight unit vector of the missile with the PGK kit installed relative to the target at time k based on the information provided by the first infrared camera, the second infrared camera, and the inertial measurement unit. , the rotation rate of the sight line relative to the target , the velocity vector relative to the target The distance to the target and provide it to the control module; Step 5: The reinforcement learning module controls the strategy according to the optimal line of sight curvature at time k Generate flight instructions , is the state of the missile with the PGK kit installed relative to the target at time k, .
[0023] The PGK precision guidance method for missiles provided in the second embodiment of the present invention does not use a GPS module, and therefore will not be interfered by geomagnetic or artificial electromagnetic signals. It locates the target through binocular intersection measurement technology and reinforcement learning, and has high strike accuracy.
[0024] Third embodiment
[0025] A third embodiment of the present invention provides a computer program product, which includes computer program codes. The computer program codes can be called by a processor to execute the method of the second embodiment.
[0026] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. The meaning of "several" is one or more, unless otherwise clearly and specifically defined.
[0027] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. A PGK precision guidance system for missiles, characterized in that: The invention comprises a PGK kit, which is installed on the missile head and comprises an infrared target detection component, an inertial measurement component, a navigation system and a control module. The infrared target detection component comprises a first infrared camera and a second infrared camera. The first infrared camera is used to obtain first image information of a target object struck by a missile equipped with the PGK kit and provide the first image information to the navigation system. The second infrared camera is used to obtain second image information of a target object struck by a missile equipped with the PGK kit and provide the second image information to the navigation system. The inertial measurement component is used to measure the angular velocity and acceleration of the missile equipped with the PGK kit and provide the information to the navigation system. The navigation system calculates the sight unit vector of the missile equipped with the PGK kit relative to the target object at time k according to the information provided by the first infrared camera, the second infrared camera and the inertial measurement component. , the rotation rate of the sight line relative to the target , the velocity vector relative to the target The distance to the target and provide it to the control module; the control module includes a reinforcement learning module, which controls the optimal line of sight curvature at time k Generate flight instructions , is the state of the missile with the PGK kit installed relative to the target at time k, .
2. The PGK precision guidance system for missiles according to claim 1, characterized in that: Optimal sight curvature control strategy Obtain it by following the steps below: S1-01: Initialize the state value function V and the line of sight curvature control strategy ; S1-02: Let c←1, where c is the number of superposition steps; S1-03: Calculate the state o of the missile with the PGK kit relative to the target at time k according to the following formula: k The state value function value of is: ， In the formula, is the state o of the missile with the PGK kit installed at time k relative to the target k Execute flight instructions Transfer to the state o relative to the target object k+1 probability; is the state o of the missile with the PGK kit installed at time k relative to the target k Execute flight instructions Transfer to the state o relative to the target object k+1 the reward received; is the state o relative to the target at time k+1 k+1 The state value function; U represents the flight instruction set of the missile equipped with the PGK kit to fly in all directions, and S represents the state set of all missiles equipped with the PGK kit relative to the target; For the improved sight curvature control strategy; S1-04: Judgment Is it less than or equal to the threshold value? If yes, execute step S1-08; if no, execute step S1-05; S1-05: , the state-action function is calculated according to the following formula: ， S1-06: Improve the sight curvature control strategy according to the following formula: , where Indicates the flight instruction when the function value reaches the maximum , o means the flight instruction is The state of the object relative to the target; S1-07: Make c←c+1, And return to S1-03; S1-08: Output the optimal sight curvature control strategy .
3. The PGK precision guidance system for missiles according to claim 2, characterized in that: The navigation system includes an image processing module and a matching module, wherein the image processing module extracts L candidate first image regions from the first image , extract R candidate second image regions from the second image The matching module matches the target template Q with the L candidate first image regions to obtain the left image of the target object in the first image. , and also matches the target template Q with the R candidate second image regions to obtain the right image of the target object in the second image .
4. The PGK precision guidance system for missiles according to claim 3, characterized in that: The matching module matches the target template Q with the L candidate first image regions Matching is performed to obtain the left image of the target object in the first image Specifically include: Given the target template Q, take the center of the image template Q as the center and the center angle and radius The image template Q is radially sampled to produce The feature vector of the target template Q ; Make the feature vectors of two adjacent target templates Q of the same radius form a tuple ; Given the first image region , with the first image area The center of the circle is the center, with the central angle and radius The first image region is radially sampled to generate a The feature vector of the first image region ; Make the feature vectors of two adjacent first image regions of the same radius form a tuple ; The left image of the selected object in the first image is obtained by the following formula : ， In the formula, , , is a hyperparameter, represents the two-norm, Represents the first image region where the function value is minimized.
5. The PGK precision guidance system for missiles according to claim 3, characterized in that: The matching module matches the target template Q with R candidate second image regions Matching is performed to obtain the right image of the target object in the second image Specifically include: Given the target template Q, take the center of the image template Q as the center and the center angle and radius The image template Q is radially sampled to produce The feature vector of the target template Q ; Make the feature vectors of two adjacent target templates Q of the same radius form a tuple ; Given the second image region , with the second image area The center of the circle is the center, with the central angle and radius The second image region is radially sampled to produce The feature vector of the second image region ; Make the adjacent two second image areas of the same radius The feature vectors of ; The right image of the target object in the second image is obtained by the following formula : ， In the formula, , , is a hyperparameter; represents the second norm, Represents the second image region where the function value is minimized.
6. A PGK precision guidance method for missiles, characterized in that: The steps include: Step 1: Install the PGK kit on the missile head, wherein the PGK kit includes an infrared target detection component, an inertial measurement component, a navigation system and a control module; the infrared target detection component includes a first infrared camera and a second infrared camera; the control module includes a reinforcement learning module; Step 2: Acquire first image information of a target object hit by a missile equipped with a PGK kit through a first infrared camera and provide the first image information to a navigation system; acquire second image information of a target object hit by a missile equipped with a PGK kit through a second infrared camera and provide the second image information to a navigation system; Step 3: Measure the angular velocity and acceleration of the missile with the PGK kit installed through the inertial measurement unit and provide it to the navigation system; Step 4: The navigation system calculates the sight unit vector of the missile with the PGK kit installed relative to the target at time k based on the information provided by the first infrared camera, the second infrared camera, and the inertial measurement unit. , the rotation rate of the sight line relative to the target , the velocity vector relative to the target The distance to the target and provide it to the control module; Step 5: The reinforcement learning module controls the strategy according to the optimal line of sight curvature at time k Generate flight instructions , is the state of the missile with the PGK kit installed relative to the target at time k, .
7. The PGK precision guidance method for missiles according to claim 6, characterized in that: Optimal sight curvature control strategy Obtain it by following the steps below: S1-01: Initialize the state value function V and the line of sight curvature control strategy ; S1-02: Let c←1, where c is the number of superposition steps; S1-03: Calculate the state o of the missile with the PGK kit relative to the target at time k according to the following formula: k The state value function value of is: ， In the formula, is the state o of the missile with the PGK kit installed at time k relative to the target k Execute flight instructions Transfer to the state o relative to the target object k+1 probability; is the state o of the missile with the PGK kit installed at time k relative to the target k Execute flight instructions Transfer to the state o relative to the target object k+1 the reward received; is the state o relative to the target at time k+1 k+1 The state value function; U represents the flight instruction set of the missile equipped with the PGK kit to fly in all directions, and S represents the state set of all missiles equipped with the PGK kit relative to the target; For the improved sight curvature control strategy; S1-04: Judgment Is it less than or equal to the threshold value? If yes, execute step S1-08; if no, execute step S1-05; S1-05: , the state-action function is calculated according to the following formula: ， S1-06: Improve the sight curvature control strategy according to the following formula: , where Indicates the flight instructions that maximize the function value , o means the flight instruction is The status of the missile with the PGK kit installed relative to the target; S1-07: Make c←c+1, And return to S1-03; S1-08: Output the optimal sight curvature control strategy .
8. The PGK precision guidance method for missiles according to claim 7, characterized in that: The navigation system includes an image processing module and a matching module, wherein the image processing module extracts L candidate first image regions from the first image , extract R candidate second image regions from the second image The matching module matches the target template Q with the L candidate first image regions to obtain the left image of the target object in the first image. , and also matches the target template with the R candidate second image regions to obtain the right image of the target object in the second image .
9. The PGK precision guidance method for missiles according to claim 8, characterized in that: The matching module matches the target template q with the L candidate first image regions Matching is performed to obtain the left image of the target object in the first image Specifically include: Given the target template Q, take the center of the image template Q as the center and and radius The image template Q is radially sampled to produce The feature vector of the target template Q ; Make the feature vectors of two adjacent target templates of the same radius form a tuple ; Given the first image region , with the first image area The center of the circle is the center of and radius The first image region is radially sampled to generate a The feature vector of the first image region ; Make the adjacent two first image areas of the same radius The feature vectors of ; The left image of the selected object in the first image is obtained by the following formula : ， In the formula, , , is a hyperparameter, represents the two-norm, Represents the first image region where the function value is minimized.
10. The PGK precision guidance method for missiles according to claim 8, characterized in that: The matching module q matches the target template with R candidate second image regions Matching is performed to obtain the right image of the target object in the second image Specifically include: Given the target template Q, take the center of the image template Q as the center and , using the radius The image template Q is radially sampled to produce The feature vector of the target template ; Make the feature vectors of two adjacent target templates of the same radius form a tuple ; Given the second image region , with the second image area The center of the circle is the center, with the central angle and radius The second image region is radially sampled to produce The feature vector of the second image region ; Make the adjacent two second image areas of the same radius The feature vectors of ; The right image of the target object in the second image is obtained by the following formula : ， In the formula, , , is a hyperparameter; represents the second norm, Represents the second image region where the function value is minimized.