Method and system for predicting simultaneous impact of aircraft during interval launching

Abstract

The invention discloses a method and a system for predicting simultaneous impact during interval launching of aircrafts, and belongs to the technical field of data prediction processing. The method comprises the following steps: modeling according to an aircraft; changing the initial launching angle and the starting control distance to obtain a launching angle-starting control distance function curve; normalization processing is carried out, and multi-layer image data features are obtained through wavelet decomposition; feature points obtained through wavelet decomposition are used for labeling, and two kinds of wavelets with different parameter coefficients are used for reconstructing an emission angle-starting control distance function; performing difference operation on a function prediction value obtained by prediction and an actual value, and performing multiple rounds of learning to transform parameters of the wavelet itself; reconstructing a prediction function curve by using wavelet transform, and setting miss distance as a trust degree function; and analyzing the obtained wavelet prediction function, setting an initial emission angle and required interval time, and searching a proper interval according to a credibility function. According to the method, the region generated by the minimum value and the maximum value of the overall time can be accurately predicted.

Description

Technical Field

[0001] This invention belongs to the field of data prediction and processing technology, and relates to a method and system for predicting the simultaneous impact of aircraft during interval launches. Background Technology

[0002] Modern warfare is a nonlinear system characterized by a highly information-driven environment where matter, energy, and information are fully open and interwoven with numerous feedback loops. In modern warfare, where information is increasingly crucial, infantry will react accordingly after receiving the initial artillery barrage. Approximately 50% of the infantry will lie prone within 2 seconds, and the entire infantry will transition to a prone or concealed position within 8 seconds. This directly reduces the artillery kill rate to 50% to 10% of its original value. Therefore, the effectiveness of the first or initial artillery strikes becomes particularly important. In the 1980s, the American Machine-Building Research Institute first proposed the Multiple Round Simultaneous Impact (MRSI) method. By altering the propellant charge and firing angle of the artillery, multiple projectiles can simultaneously hit the target within a fixed firing interval, significantly increasing the destructive power of the projectiles, directly improving the combat efficiency of artillery units, and indirectly enhancing their survivability. Currently, the 155mm gun of the US AGS Advanced Naval Gun System has a rate of fire of 10 to 12 rounds per minute, and it also has the ability to fire projectiles at intervals while they hit targets at the same time. This allows it to fire 4 to 6 projectiles and hit targets 75 nautical miles away at the same time, which represents a significant advancement in chemical energy naval guns.

[0003] As the literature indicates, the development of simultaneous impact technology in my country began relatively late. Research and exploration of MRSI technology in my country started in 2001. Lu Xin, Zhou Yanhuang, and others elaborated on the concept of simultaneous impact of multiple rounds from a single gun, the mathematical model architecture, and the basic ideas of the development program. Xie Liyan et al., based on this, analyzed the feasibility of simultaneous impact of multiple rounds from a single gun in a 155mm self-propelled howitzer under multiple constraints. In 2010, Yang Shenglei et al. began to focus on the simultaneous impact problem and discussed and analyzed the influence of single factors. In 2021, Sun Shiyan et al. also conducted research and discussion on the multi-constraint and multi-factor influence problem of aircraft, providing significant assistance to the development of simultaneous impact technology. The literature points out that the influencing factors of simultaneous impact technology for aircraft mainly consist of: initial velocity, ammunition load, initial firing angle, impact angle, and the variation law of rudder angle. This paper studies the simultaneous impact problem of aircraft, investigating the influence of initial firing angle, guidance initiation time, and guidance control strategy on simultaneous impact. Neural network wavelet transform is used for impact time prediction and data analysis, proposing multiple strategies to satisfy simultaneous impact.

[0004] There is an urgent need for a method and system for predicting the impact of intermittent launches of aircraft. Summary of the Invention

[0005] The purpose of this invention is to solve the above-mentioned technical problems and provide a method and system for predicting the simultaneous impact of spacecraft launched at intervals. This invention also includes research on the influence of various launch parameters and ballistic parameters on the overall impact time, in-depth research on ballistic data feature algorithms, and research on the simultaneous impact of spacecraft launched at intervals from fixed launch points.

[0006] To achieve the above objectives, the present invention mainly provides the following technical solutions:

[0007] First, embodiments of the present invention provide a method for predicting the simultaneous impact of spacecraft launches at intervals.

[0008] Step 1: Model the types of aircraft such as ground-launched, UAV-borne separation, and air-launched aircraft. The initial ammunition load and the time of action after ignition are fixed. The terminal guidance law adopts proportional guidance.

[0009] Step 2: Change the initial launch angle and the starting control distance to obtain the launch angle-starting control distance function curve;

[0010] Step 3: Normalize the aircraft ballistic feature data obtained in Step 2 to facilitate wavelet decomposition, and use wavelet decomposition to obtain multi-layer image data features.

[0011] Step 4: Use the feature points obtained by wavelet decomposition (such as the trajectory vertex, launch control point, proportional guidance control point, etc.) to mark them, and use wavelets of the parameter coefficients of two different launch angle aircraft to reconstruct the launch angle-launch control distance function;

[0012] Step 5: Perform difference calculation on the predicted and actual values ​​of the predicted flight time parameters, and conduct multiple rounds of learning to transform the parameters of the wavelet itself.

[0013] Step 6: Reconstruct the prediction function curve using wavelet transform, and set the off-target value as the confidence function;

[0014] Step 7: Analyze the obtained wavelet prediction function, set the initial launch angle, set the required interval time, find a suitable interval based on the confidence function, and finally satisfy the condition of fixed launch point and fixed interval time for simultaneous impact.

[0015] Furthermore, in step 1, the modeling of the aircraft includes the following steps: constructing the overall design length of the aircraft, the chord length of the pitch control, the chord length of the yaw control, etc.; setting the trajectory calculation time process, including the rocket working process, the pitch control opening time period, and the gliding time period, wherein the gliding time period includes the scheme trajectory segment and the proportional guidance segment, i.e. the terminal guidance segment.

[0016] Furthermore, in step 1, the target distance is set to a fixed value of 70,000 meters.

[0017] Furthermore, in step 3, the multi-layer image data features include feature points of different frequencies, providing preprocessing for subsequent wavelet prediction.

[0018] Furthermore, in step 6, the feature points and other points are decomposed using different wavelet functions by utilizing the wavelet transform of the neural network, which is beneficial for the reconstruction of the overall function and reduces the error.

[0019] Furthermore, in step 7, after selecting the initial launch angle, the optimal particular solution with the smallest miss distance is obtained from multiple general solutions using the confidence function.

[0020] Second, this embodiment of the invention also provides a spacecraft interval launch and simultaneous impact prediction system, the system comprising: one or more processors; a memory for storing one or more programs; the processors being configured to execute program instructions stored in the memory, wherein the program instructions, when executed, perform the aforementioned spacecraft interval launch and simultaneous impact prediction method.

[0021] Third, this embodiment of the invention also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by one or more processors, implements the above-described method for predicting the simultaneous impact of spacecraft launches at intervals.

[0022] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0023] This invention utilizes complete aircraft modeling, wavelet decomposition, and neural network-based feature wavelet prediction. Under a fixed launch angle, changing the launch control time reveals significant oscillations in the rate of change near the minimum value, with a larger slope. Further away from the minimum value, the rate of change also exhibits large oscillations and a larger slope. In other intervals, the slope changes gradually flatten out, showing a certain regularity. With a fixed launch control time, changing the launch angle, through approximation coefficients, reveals a clear decaying trend in the overall time before reaching its minimum. Using neural network wavelet transform for overall prediction effectively masks errors caused by near-ground weather interference and weak anti-interference at small initial launch angles. Furthermore, it can accurately predict the regions where the overall time reaches its minimum and maximum values, and also provides good prediction of regions with abrupt changes and their ascent and descent trends. Attached Figure Description

[0024] Figure 1 This is a graph showing the relationship between the change of the initial firing angle and the overall time in an embodiment of the present invention;

[0025] Figure 2This is a graph showing the relationship between the initial distance of the final guidance control rate at an initial firing angle of 59° and the overall time in an embodiment of the present invention.

[0026] Figure 3 This is a diagram of the approximation coefficients for the 6-layer wavelet transform in this embodiment of the invention.

[0027] Figure 4 This is a detail coefficient diagram of the wavelet transform 6 layers in an embodiment of the present invention;

[0028] Figure 5 This is a chart showing the start time of different terminal guidance laws corresponding to different initial firing angles in embodiments of the present invention;

[0029] Figure 6 This is a prediction chart of the overall time corresponding to different groups in an embodiment of the present invention;

[0030] Figure 7 This is a bar chart showing the difference between the prediction time and the overall time for different groups in this embodiment of the invention;

[0031] Figure 8 This is a mind map for analyzing the simultaneous impact strategy in an embodiment of the present invention;

[0032] Figure 9 This is a diagram illustrating the simultaneous impact strategy with a 5-second interval in an embodiment of the present invention.

[0033] Figure 10 This is a simulation diagram of simultaneous impacts at 5-second intervals in an embodiment of the present invention;

[0034] Figure 11 This is a diagram illustrating the simultaneous impact strategy with a 10-second interval in an embodiment of the present invention.

[0035] Figure 12 This is a simulation diagram of simultaneous impacts at 10-second intervals in an embodiment of the present invention. Detailed Implementation

[0036] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0037] Among them, Figure 1 The main data shows the overall flight time corresponding to different initial launch angles at the same launch point. Corresponding to step (2-1), it can be concluded that the change in the overall flight time exhibits a relationship of first decreasing and then increasing, with a unique minimum value. Furthermore, when located at the critical initial launch angle, the rate of change of the overall flight time significantly increases. Figure 2The main display shows the overall flight time relationship at the same launch point and with a fixed initial launch angle, corresponding to different launch control distances. As shown in step (2-2), the overall curve exhibits an oscillating downward trend as the launch control distance increases. Figure 3 and Figure 4 The main focus is on displaying the wavelet decomposition of the above-mentioned graphs, further demonstrating the overall trend of the curves; corresponding to step (3-1); in Figure 5 The display shows the changes in overall flight time corresponding to different combinations of initial launch angles and different initial control distances; Figure 6 This is a prediction chart of the overall time corresponding to different groups in an embodiment of the present invention; in Figures 9-12 Based on the feature wavelet prediction based on the neural network given in step (3-2), and according to the selection principle of minimizing the miss distance, the launch point is fixed, an appropriate initial launch angle is selected, and launch strategies and diagrams are provided at intervals of 5s and 10s. Figure 7 By comparing the actual data set obtained by the feature wavelet prediction algorithm based on neural networks given in step (3-2) with the predicted data, it can be seen that the prediction algorithm has a small error and a high degree of feasibility. Figure 8 This is the flowchart for the overall algorithm prediction.

[0038] An embodiment of the present invention provides a method for predicting the impact of missiles launched at intervals from an aircraft. The specific steps are as follows:

[0039]

[0040]

[0041] This invention is implemented in Matlab and classifies images in a dataset. Wavelet decomposition and feature wavelet prediction based on neural networks include the following steps:

[0042] Step 1:

[0043] Step (1-1): In this invention, the aircraft is modeled with a fixed initial ammunition load and a fixed duration of action after ignition. Proportional guidance is used for the terminal guidance law. The target distance is a fixed value of 70,000 meters.

[0044] Step (1-2): With the parameters of the aircraft and the target distance fixed, and the terminal guidance law time set to 0, the corresponding initial firing angle range can be obtained. That is, under the condition of extreme initial firing angle, the aircraft can hit the target horizontally at the maximum range.

[0045] Steps (1-3): The spacecraft should launch at intervals and the missiles should hit simultaneously to meet the following requirements.

[0046] θ min ≤θ≤θ max

[0047] In the formula, θ is the actual initial firing angle of the aircraft. min For the minimum initial angle of attack, θ max The maximum initial firing angle is predicted by the neural network to be 46.290°, and the corresponding minimum initial firing angle is 69.05°.

[0048] Steps (1-4): The fundamental purpose of simultaneous impact technology is to improve the combat efficiency of artillery units and enhance their destructive capabilities against the enemy. To ensure a high hit rate, the number of projectiles impacting simultaneously is generally set at [number missing].

[0049] N≥3

[0050] Steps (1-5): There is a time difference between adjacent aircraft. The specific time difference value corresponds to different simultaneous impact strategies, but the time difference value is a fixed constant, i.e.

[0051] t fi -t fi-1 ≥ΔT,ΔT∈R +

[0052] Steps (1-6): Given the known target distance for the aircraft, and fixing the timing of servo deployment, it can be deduced that the terminal guidance rate initiation time should be after the servo deployment time.

[0053]

[0054] in The distance at which the final guidance rate begins. As shown in the experiment, the closer the start time of the terminal guidance rate is to the servo deployment time, the smaller its change trend is, which can be ignored. Therefore, this invention focuses on analyzing the rate of change within 15,000 meters.

[0055] The above constraints together constitute the mathematical model for the spacecraft to launch at intervals and land simultaneously.

[0056] Step 2:

[0057] Step (2-1): Under the premise of a specified target distance, fix the terminal guidance rate start time, change the initial firing angle, and you can obtain the specific trend of the change of the initial angle and the impact time.

[0058] Near the minimum value, the rate of change oscillates violently, and the slope becomes larger. In the interval far from the minimum value, the rate of change also oscillates significantly, and the slope becomes larger. In the remaining intervals, the slope changes gradually and shows a certain regularity.

[0059] Step (2-2): Under the premise that the initial angle remains unchanged, changing the start time of the end control rate can reflect the difference in the variation of different intervals of a single angle.

[0060] Due to the instability of the airflow at high altitude and near ground, and the use of Gaussian distribution method for the equatorial rotational inertia and polar rotational inertia after the combustion of the charge in the modeling, some oscillations will occur. After wavelet decomposition into 6 layers, it can be more intuitively found through the approximation coefficient that the trend of the change of the overall time before reaching the minimum overall time shows a clear decay trend.

[0061] Step (2-3): Under the premise of changing the initial angle, the start time of the end control rate is also changed. It can be found that there are multiple similar trend intervals. According to the above, under the condition of 59° initial firing angle, there is a sudden change in the trend. In the range of 9000 meters to 10000 meters, at different initial firing angles, the sudden change interval will produce corresponding sinking and floating.

[0062] Different terminal control rates start times correspond to different overall times, and the time variation trends differ within different intervals. Specifically, these intervals can be divided as follows: For initial firing angles close to 55° (the minimum overall time), the abrupt change range is 9000-10000 meters, with a size of 50°-61°. Within the 62°-69° initial firing angle interval, the abrupt change range gradually increases with the initial firing angle, until it reaches 3000-4000 meters. Within the 47°-49° initial firing angle interval, the abrupt change range is 3000-4000 meters. Within the 220s-240s variation interval, overlapping variation intervals will appear, corresponding to multiple selectable initial firing angles.

[0063] Step 3:

[0064] Step (3-1): Use neural network wavelet transform for overall prediction. It can basically shield the errors caused by near-ground meteorological interference and the errors caused by weak anti-interference at small initial angles, and can also predict the overall time trend.

[0065] Step (3-2): At low initial firing angles, significant deviations will occur. In fact, when the initial firing angle is small, the trajectory of ordinary aircraft is relatively straight, and the ballistic parameters have a greater impact on it. Based on experimental experience, such aircraft have a higher miss rate and poorer accuracy at an initial firing angle of 45°. Furthermore, under the premise of minimum initial firing angle, the greater the launch distance, the greater the deviation. At non-minimum initial firing angles, the deviation gradually decreases as the initial angle increases. This trend is more pronounced when the initial angle is close to the minimum initial firing angle. As the initial firing angle increases, the deviation exhibits an irregular distribution, and when the initial firing angle reaches its maximum value range, the deviation will increase again. The two wavelet prediction functions mentioned above are shown below.

[0066]

[0067] For a given training set, the overall time prediction using wavelet-based neural network learning can predict the dataset with minimal error. The prediction of the overall time change intervals corresponding to different initial angles mentioned above is also basically consistent with the table above.

[0068] This invention also provides a system for predicting the simultaneous impact of spacecraft launches at intervals, comprising:

[0069] It includes: one or more processors; a memory for storing one or more programs; the processors are configured to execute program instructions stored in the memory, which, when executed, perform the aforementioned spacecraft interval launch and simultaneous impact prediction method.

[0070] This invention also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by one or more processors, implements the above-described method for predicting the simultaneous impact of spacecraft launches at intervals.

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0072] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0073] In addition, the memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0074] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0076] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0077] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0078] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0079] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0080] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0081] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0082] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] The above description is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Furthermore, although some specific terms are used in this specification, these terms are merely for convenience of explanation and do not constitute any limitation on the present invention.

Claims

1. A method for predicting simultaneous impact of intermittently launched projectiles from an aircraft, characterized in that, The method includes the following steps: Step 1: Model the ground-launched, UAV-borne separation, and air-launched aircraft. The initial ammunition load and the time of action after ignition are fixed. The terminal guidance law adopts proportional guidance. Step 2: Change the initial launch angle and the starting control distance to obtain the launch angle-starting control distance function curve; Step 3: Normalize the aircraft ballistic feature data obtained in Step 2 to facilitate wavelet decomposition, and use wavelet decomposition to obtain multi-layer image data features. Step 4: Use the feature points obtained by wavelet decomposition to label them, and use wavelets of the parameter coefficients of two different launch angle aircraft to reconstruct the launch angle-launch control distance function; Step 5: Perform difference calculation on the predicted and actual values ​​of the predicted flight time parameters, and conduct multiple rounds of learning to transform the parameters of the wavelet itself; Step 6: Reconstruct the prediction function curve using wavelet transform, and set the off-target value as the confidence function; Step 7: Analyze the obtained wavelet prediction function, set the initial launch angle, set the required interval time, find a suitable interval based on the confidence function, and finally satisfy the condition of fixed launch point and fixed interval time for simultaneous impact.

2. The method according to claim 1, characterized in that, In step 1, the modeling of the aircraft includes the following steps: constructing the overall design length of the aircraft, the chord length of the pitch control, and the chord length of the yaw control; setting the trajectory calculation time process, including the rocket working process, the pitch control opening time period, and the gliding time period, wherein the gliding time period includes the scheme trajectory segment and the proportional guidance segment.

3. The method according to claim 1, characterized in that, In step 1, the target distance is set to a fixed value of 70,000 meters.

4. The method according to claim 1, characterized in that, In step 3, the multi-layer image data features include feature points of different frequencies.

5. The method according to claim 1, characterized in that, In step 6, the feature points and other points are decomposed using different wavelet functions by utilizing the neural network wavelet transform.

6. The method according to claim 1, characterized in that, In step 7, after selecting the initial launch angle, the optimal particular solution with the smallest miss distance is obtained from multiple general solutions using the confidence function.

7. A system for predicting the simultaneous impact of intermittent launches of aircraft, characterized in that, include: It includes: one or more processors; a memory for storing one or more programs; the processors are configured to execute program instructions stored in the memory, which, when executed, perform the spacecraft interval launch simultaneous impact prediction method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by one or more processors, implements the spacecraft interval launch simultaneous impact prediction method according to any one of claims 1 to 6.

Images