Flying object track prediction method and device and electronic equipment
By constructing the CKAN model and combining it with the goat optimization algorithm to optimize parameters, the problem of low accuracy in predicting the trajectory of flying objects was solved, and higher prediction accuracy and interception success rate were achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NO 15 INST OF CHINA ELECTRONICS TECH GRP
- Filing Date
- 2026-01-12
- Publication Date
- 2026-05-12
AI Technical Summary
Existing technologies have low accuracy in predicting the trajectory of flying objects, making it difficult to accurately predict the maneuvering direction and timing of flying objects under complex environments and human interference.
The CKAN model is constructed using convolutional layers and a Kolmogorov-Arnold network architecture, and the parameters are globally optimized by combining the goat optimization algorithm. Historical trajectory data is used for training and prediction, and the DILATE function is used as the loss function to optimize the combination of model parameters.
It improves the accuracy of object trajectory prediction, solves the problem of low prediction accuracy in existing technologies, and enhances the reaction speed and interception success rate of anti-aircraft interception systems.
Smart Images
Figure CN122020159A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of trajectory prediction technology, specifically to a method, apparatus, and electronic device for predicting the trajectory of flying objects. Background Technology
[0002] Maneuvering of an object in the mid-course phase of its trajectory is considered one of the most effective methods to counter anti-missile interception systems. However, due to the concealed deployment locations of anti-aircraft systems and the considerable flexibility in their interception methods and timing, it is difficult for the object to accurately determine its maneuvering direction, timing, and number of maneuvers. In this situation, the reaction speed of the anti-aircraft interception system becomes a decisive factor for effective interception during the active phase of the object's flight. Therefore, it is essential to utilize advanced predictive technologies to conduct forward-looking analysis of the object's flight trajectory, accurately obtain its flight parameters during the active phase, and thus allow sufficient reaction time for the anti-aircraft interception system, thereby improving the interception success rate.
[0003] Most trajectory prediction methods used in related technologies rely on kinematic or dynamic models to solve for target trajectory information through mathematical modeling. However, in practical applications, the flight process of target flying objects is easily affected by complex environmental factors and human interference, making accurate modeling difficult and resulting in low accuracy in predicting the trajectory of flying objects.
[0004] There is currently no effective technical solution to the problem of low accuracy in predicting the trajectory of flying objects in related technologies. Summary of the Invention
[0005] The main objective of this disclosure is to provide a method, apparatus, and electronic device for predicting the trajectory of flying objects, in order to solve the problem of low accuracy in predicting the trajectory of flying objects in related technologies.
[0006] To achieve the above objectives, a first aspect of this disclosure provides a method for predicting the trajectory of an object, comprising: Acquire historical trajectory data of the flying object, and divide the historical trajectory data into training set, verification set and test set according to a preset ratio; Based on convolutional layers and Kolmogorov-Arnold network architecture, a CKAN model is constructed and initialized. The parameters of the CKAN model are globally optimized using the goat optimization algorithm to determine the optimal parameter combination of the CKAN model and obtain the optimized CKAN model. The optimized CKAN model is trained based on the training set, and the test set is input into the trained optimized CKAN model to predict the trajectory of flying objects and obtain the prediction results.
[0007] Optionally, the step of acquiring historical trajectory data of the flying object and dividing the historical trajectory data into a training set, a validation set, and a test set according to a preset ratio includes: Acquire the first trajectory data of the flying object under different launch conditions and different environments; The first trajectory data is cleaned to remove abnormal and erroneous data, resulting in the second trajectory data. The second trajectory data is normalized and mapped to the [0,1] interval to obtain the third trajectory data; The third trajectory data is divided into a training set, a validation set, and a test set according to a preset ratio.
[0008] Optionally, the construction and initialization of the CKAN model based on convolutional layers and the Kolmogorov-Arnold network architecture includes: The convolutional layers are integrated into the Kolmogorov-Arnold network architecture to obtain the CKAN model, in which the convolutional layers are used to extract time series data features and the DILATE function is used as the loss function. Determine the parameters of the CKAN model in its initial state. These parameters include the number and size of filters in the convolutional layers, the number of layers and nodes in the KAN, and the weights of the DILATE loss function.
[0009] Optionally, the step of using the goat optimization algorithm to globally optimize the parameters of the CKAN model, determine the optimal parameter combination of the CKAN model, and obtain the optimized CKAN model includes: The parameters of the CKAN model are used as individuals in the goat optimization algorithm. A goat population with a preset number of goats is randomly generated in the initial state. Each goat in the goat population represents a set of parameter combinations of the CKAN model. The goat optimization algorithm is used to iterate the parameters a preset number of times. In each iteration, the current CKAN model is constructed based on the current parameter combination composed of all current parameters. The current CKAN model is trained on the training set and the fitness value is determined on the validation set. All goats in the goat population are sorted in descending order of fitness value to determine the optimal goat. The optimal goat is then used as the optimal parameter combination to obtain the optimized CKAN model.
[0010] Further, determining the fitness value on the validation set includes: The prediction performance of the current CKAN model on the validation set is used as the fitness function of the goat optimization algorithm; The fitness value is calculated on the validation set using the fitness function.
[0011] Optionally, training the optimized CKAN model based on the training set includes: The training set is input into the optimized CKAN model for training. The weights and parameters of the optimized CKAN model are adjusted to obtain the trained optimized CKAN model.
[0012] Optionally, after obtaining the prediction result, the method further includes: The difference between the predicted results and the real trajectory data of the test set is measured by a preset index to evaluate the prediction accuracy of the optimized CKAN model; The preset indicators include any one or more of the following: root mean square error, mean absolute error, and mean absolute percentage error.
[0013] A second aspect of this disclosure provides an object trajectory prediction device, comprising: The acquisition unit is used to acquire historical trajectory data of the flying object and divide the historical trajectory data into a training set, a verification set, and a test set according to a preset ratio. The building unit is used to construct the CKAN model and initialize the model based on convolutional layers and the Kolmogorov-Arnold network architecture. The optimization unit is used to globally optimize the parameters of the CKAN model using the goat optimization algorithm, determine the optimal parameter combination of the CKAN model, and obtain the optimized CKAN model. The prediction unit is used to train the optimized CKAN model based on the training set, and input the test set into the trained optimized CKAN model to predict the trajectory of flying objects and obtain the prediction result.
[0014] A third aspect of this disclosure provides a computer-readable storage medium storing computer instructions for causing a computer to perform the flight trajectory prediction method provided in any of the first aspects.
[0015] A fourth aspect of this disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the flight trajectory prediction method provided in any of the first aspects.
[0016] In the flight trajectory prediction method disclosed herein, the parameters of the CKAN model are globally optimized using the goat optimization algorithm to determine the optimal parameter combination of the CKAN model, thereby obtaining the optimized CKAN model. By combining the CKAN model and the goat optimization algorithm, the accuracy of flight trajectory prediction is improved, and the problem of low prediction accuracy of flight trajectory in related technologies is solved. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of this disclosure, the accompanying drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a schematic flowchart of the flight trajectory prediction method provided in the embodiments of this disclosure; Figure 2 A block diagram of an object trajectory prediction device provided in an embodiment of this disclosure; Figure 3 A block diagram of an electronic device provided in an embodiment of this disclosure. Detailed Implementation
[0019] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.
[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0021] It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.
[0022] Maneuvering of an object in the mid-course phase of its trajectory is considered one of the most effective methods to counter anti-missile interception systems. However, due to the concealed deployment locations of anti-aircraft systems and the considerable flexibility in their interception methods and timing, it is difficult for the object to accurately determine its maneuvering direction, timing, and number of maneuvers. In this situation, the reaction speed of the anti-aircraft interception system becomes a decisive factor for effective interception during the active phase of the object's flight. Therefore, it is essential to utilize advanced predictive technologies to conduct forward-looking analysis of the object's flight trajectory, accurately obtain its flight parameters during the active phase, and thus allow sufficient reaction time for the anti-aircraft interception system, thereby improving the interception success rate.
[0023] Most trajectory prediction methods used in related technologies rely on kinematic or dynamic models to solve for target trajectory information through mathematical modeling. However, in practical applications, the flight process of target flying objects is easily affected by complex environmental factors and human interference, making accurate modeling difficult and resulting in low accuracy in predicting the trajectory of flying objects.
[0024] To address the aforementioned problems, embodiments of this disclosure provide a method for predicting the trajectory of flying objects, such as... Figure 1 As shown, the method includes the following steps S11 to S14: Step S11: Obtain the historical trajectory data of the flying object, and divide the historical trajectory data into training set, validation set and test set according to a preset ratio; the preset ratio can be 8:1:1 or 7:2:1.
[0025] In one optional embodiment of this disclosure, step S11 includes: Acquire the first trajectory data of the flying object under different launch conditions and different environments; different launch conditions may include different launch angles, launch velocities, etc., and different environments may include different weather conditions, terrain, temperature, humidity, air density (air resistance), etc. The first trajectory data is cleaned to remove abnormal and erroneous data, resulting in the second trajectory data. Through data cleaning, abnormal and erroneous data are removed to obtain accurate flight trajectory data. The second trajectory data is normalized and mapped to the [0,1] interval to obtain the third trajectory data; the influence of different feature dimensions is eliminated through normalization. The third trajectory data is divided into training set, validation set and test set according to a preset ratio.
[0026] Step S12: Construct the CKAN model and initialize it based on the convolutional layer and Kolmogorov-Arnold network architecture; the convolutional layer is used to learn the behavior and internal representation of the time series input data, and is activated at the edges of the Kolmogorov-Arnold network to change the training dynamics; the constructed CKAN model can focus on data feature mining and prediction, handle complex time series data, and facilitate subsequent optimization to obtain an effective and robust time series prediction model.
[0027] In one optional embodiment of this disclosure, step S12 includes: By integrating convolutional layers into the Kolmogorov-Arnold network architecture, the CKAN model is obtained. Convolutional layers are used to extract time-series data features, with the DILATE function used as the loss function. Convolutional layers are also used to extract time-series data features from historical trajectory data. Predictive power is enhanced through edge activation and nonlinear processing within the Kolmogorov-Arnold network. Nonlinear processing allows for differentiated feature processing and more precise control over the input's impact on the output. Furthermore, the DILATE function is used as the loss function to effectively handle non-stationary time series. Determine the parameters of the CKAN model in its initial state. These parameters include the number and size of filters in the convolutional layers, the number of layers and nodes in the KAN, and the weights of the DILATE loss function. Other parameters of the CKAN model may include the kernel size, the number of LSTM units, and the attention weights.
[0028] Step S13: Use the goat optimization algorithm to globally optimize the parameters of the CKAN model, determine the optimal parameter combination of the CKAN model, and obtain the optimized CKAN model; The Goat Optimization Algorithm (GOA) is inspired by the foraging behavior of goats. It optimizes problem-solving by simulating the herd behavior of goats and focuses on optimizing model parameters, possessing strong global search capabilities. GOA is a bio-inspired optimization algorithm, while the CKAN model is a deep learning model. This embodiment combines the bio-inspired optimization algorithm with the deep learning model. By simulating the herd behavior of goats, the parameters of the CKAN model are dynamically optimized, which can significantly improve the model's ability to fit nonlinear and time-varying trajectory data.
[0029] In one optional embodiment of this disclosure, step S13 includes: The parameters of the CKAN model are used as individuals in the goat optimization algorithm. A goat population with a preset number of goats is randomly generated in the initial state. Each goat in the goat population represents a set of parameter combinations of the CKAN model. The preset number of goats can be 30. The goat optimization algorithm is used to iterate the parameters a preset number of times. In each iteration, the current CKAN model is constructed based on the current parameter combination composed of all current parameters, and the current CKAN model is trained on the training set and the fitness value is determined on the validation set. The preset number of iterations can be 10 iterations. Each iteration can obtain the CKAN model and its fitness value under different parameter combinations. All goats in the goat population are sorted in descending order of fitness value to determine the optimal goat. This optimal goat is then used as the optimal parameter combination to obtain the optimized CKAN model. The optimal parameter combination corresponding to the highest fitness value is then determined to obtain the optimal optimized CKAN model.
[0030] In one optional embodiment of this disclosure, determining a fitness value on the validation set includes: The prediction performance of the current CKAN model on the validation set is used as the fitness function of the goat optimization algorithm; The fitness value is calculated using the fitness function on the validation set.
[0031] Step S14: Train the optimized CKAN model based on the training set, and input the test set into the trained optimized CKAN model to predict the trajectory of flying objects and obtain the prediction results.
[0032] The embodiments disclosed herein combine the CKAN model and the goat optimization algorithm to improve the accuracy of flight trajectory prediction and solve the problem of low accuracy in flight trajectory prediction in related technologies.
[0033] In one optional embodiment of this disclosure, step S14, training the optimized CKAN model based on the training set, includes: The training set is input into the optimized CKAN model for training. The weights and parameters of the optimized CKAN model are adjusted to obtain the trained optimized CKAN model. Through training, the weights and parameters of the optimized CKAN model are adjusted so that the model can better learn the characteristics and patterns of flight object trajectory data.
[0034] In one optional embodiment of this disclosure, after obtaining the prediction result in step S14, the method further includes: The difference between the predicted results and the real trajectory data of the test set is measured by a preset index to evaluate the prediction accuracy of the optimized CKAN model; the prediction accuracy of the optimized CKAN model is evaluated by comparing the predicted results with the real trajectory data of the test set.
[0035] The preset indicators include any one or more of the following: root mean square error, mean absolute error, and mean absolute percentage error.
[0036] This embodiment integrates convolutional layers into the KAN network architecture, uses the DILATE function as the loss function, and employs the goat optimization algorithm to globally optimize the parameters. By combining the CKAN model and the goat optimization algorithm, the accuracy of object trajectory prediction is improved.
[0037] As can be seen from the above description, this disclosure achieves the following technical effects: This disclosure combines the CKAN model and the goat optimization algorithm to achieve accurate modeling and dynamically optimize the parameters of the CKAN model, thereby improving the accuracy of flight trajectory prediction and solving the problem of low prediction accuracy of flight trajectory in related technologies.
[0038] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0039] This disclosure also provides an apparatus for predicting the trajectory of an object for implementing the above-described method embodiments, such as... Figure 2 As shown, the flight trajectory prediction device 20 includes: The acquisition unit 21 is used to acquire historical trajectory data of the flying object and divide the historical trajectory data into training set, verification set and test set according to a preset ratio; Building unit 22 is used to build the CKAN model and perform model initialization based on convolutional layers and Kolmogorov-Arnold network architecture; Optimization unit 23 is used to globally optimize the parameters of the CKAN model using the goat optimization algorithm, determine the optimal parameter combination of the CKAN model, and obtain the optimized CKAN model. The prediction unit 24 is used to train the optimized CKAN model based on the training set, and input the test set into the trained optimized CKAN model to predict the trajectory of flying objects and obtain the prediction results.
[0040] The specific methods of execution of each unit in the above device embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.
[0041] This disclosure also provides an electronic device, such as... Figure 3 As shown, the electronic device includes one or more processors 31 and a memory 32. Figure 3 Take a processor 31 as an example.
[0042] The controller may also include an input device 33 and an output device 34.
[0043] The processor 31, memory 32, input device 33, and output device 34 can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.
[0044] Processor 31 can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips. The general-purpose processor can be a microprocessor or any conventional processor.
[0045] The memory 32, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the control method in this embodiment. The processor 31 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions, and modules stored in the memory 32, thereby implementing the flight trajectory prediction method of the above-described method embodiment.
[0046] The memory 32 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the use of the processing device operated by the server. Furthermore, the memory 32 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 32 may optionally include memory remotely located relative to the processor 31, and these remote memories can be connected to a network connection device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0047] Input device 33 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the server's processing device. Output device 34 may include display devices such as a display screen.
[0048] One or more modules are stored in memory 32, and when executed by one or more processors 31, they perform actions such as... Figure 1 The method shown.
[0049] Those skilled in the art will understand that all or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes as described in the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory (FM), hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.
[0050] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for predicting the trajectory of a flying object, characterized in that, include: Acquire historical trajectory data of the flying object, and divide the historical trajectory data into training set, verification set and test set according to a preset ratio; Based on convolutional layers and Kolmogorov-Arnold network architecture, a CKAN model is constructed and initialized. The parameters of the CKAN model are globally optimized using the goat optimization algorithm to determine the optimal parameter combination of the CKAN model and obtain the optimized CKAN model. The optimized CKAN model is trained based on the training set, and the test set is input into the trained optimized CKAN model to predict the trajectory of flying objects and obtain the prediction results.
2. The method according to claim 1, characterized in that, The process of acquiring historical trajectory data of the flying object and dividing the historical trajectory data into a training set, a validation set, and a test set according to a preset ratio includes: Acquire the first trajectory data of the flying object under different launch conditions and different environments; The first trajectory data is cleaned to remove abnormal and erroneous data, resulting in the second trajectory data. The second trajectory data is normalized and mapped to the [0,1] interval to obtain the third trajectory data; The third trajectory data is divided into a training set, a validation set, and a test set according to a preset ratio.
3. The method according to claim 1, characterized in that, The construction and initialization of the CKAN model based on convolutional layers and Kolmogorov-Arnold network architecture includes: The convolutional layers are integrated into the Kolmogorov-Arnold network architecture to obtain the CKAN model, in which the convolutional layers are used to extract time series data features and the DILATE function is used as the loss function. Determine the parameters of the CKAN model in its initial state. These parameters include the number and size of filters in the convolutional layers, the number of layers and nodes in the KAN, and the weights of the DILATE loss function.
4. The method according to claim 1, characterized in that, The process of using the goat optimization algorithm to globally optimize the parameters of the CKAN model, determining the optimal parameter combination of the CKAN model, and obtaining the optimized CKAN model includes: The parameters of the CKAN model are used as individuals in the goat optimization algorithm. A goat population with a preset number of goats is randomly generated in the initial state. Each goat in the goat population represents a set of parameter combinations of the CKAN model. The goat optimization algorithm is used to iterate the parameters a preset number of times. In each iteration, the current CKAN model is constructed based on the current parameter combination composed of all current parameters. The current CKAN model is trained on the training set and the fitness value is determined on the validation set. All goats in the goat population are sorted in descending order of fitness value to determine the optimal goat. The optimal goat is then used as the optimal parameter combination to obtain the optimized CKAN model.
5. The method according to claim 4, characterized in that, Determining the fitness value on the validation set includes: The prediction performance of the current CKAN model on the validation set is used as the fitness function of the goat optimization algorithm; The fitness value is calculated on the validation set using the fitness function.
6. The method according to claim 1, characterized in that, The process of training the optimized CKAN model based on the training set includes: The training set is input into the optimized CKAN model for training. The weights and parameters of the optimized CKAN model are adjusted to obtain the trained optimized CKAN model.
7. The method according to claim 1, characterized in that, After obtaining the prediction result, the method further includes: The difference between the predicted results and the actual trajectory data of the test set is measured using preset indicators to evaluate the prediction accuracy of the optimized CKAN model; The preset indicators include any one or more of the following: root mean square error, mean absolute error, and mean absolute percentage error.
8. A device for predicting the trajectory of an object, characterized in that, include: The acquisition unit is used to acquire historical trajectory data of the flying object and divide the historical trajectory data into a training set, a verification set, and a test set according to a preset ratio. The building unit is used to construct the CKAN model and initialize the model based on convolutional layers and the Kolmogorov-Arnold network architecture. The optimization unit is used to globally optimize the parameters of the CKAN model using the goat optimization algorithm, determine the optimal parameter combination of the CKAN model, and obtain the optimized CKAN model. The prediction unit is used to train the optimized CKAN model based on the training set, and input the test set into the trained optimized CKAN model to predict the trajectory of flying objects and obtain the prediction result.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the flight trajectory prediction method according to any one of claims 1 to 7.
10. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the flight trajectory prediction method according to any one of claims 1 to 7.