Mission reliability assessment method for unmanned equipment system based on reconfigurable kill net

Abstract

The present invention discloses a method for assessing the mission reliability of an unmanned equipment system based on a reconfigurable kill net, which relates to the technical field of unmanned equipment mission reliability assessment. The method comprises the following steps: collecting multimodal data and preprocessing the multimodal data; extracting multimodal features based on the preprocessed multimodal data, and fusing the multimodal features using a multimodal fusion network to generate a high-dimensional environmental feature vector; predicting the reliability score of the task based on the high-dimensional environmental feature vector; and assessing the overall reliability trend of the task based on the task reliability score, and generating a task reliability assessment report. By combining a deep time series prediction model with LSTM and Transformer, the present invention effectively captures the dynamic changes in mission reliability, provides accurate future trend predictions, and significantly enhances the accuracy and timeliness of mission reliability assessments for unmanned equipment systems, providing strong support for decision-making.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned equipment mission reliability assessment, in particular to an unmanned equipment system mission reliability assessment method based on a reconfigurable kill net. Background Art

[0002] In recent years, with the widespread application of unmanned systems in military and other fields, the complexity and intelligence of their mission execution have gradually increased. In particular, in dynamic battlefield environments, unmanned systems based on reconfigurable kill webs have become a crucial component of modern military systems due to their flexible task allocation capabilities and modular reconfiguration. By integrating multiple unmanned systems in a networked manner, reconfigurable kill webs enable coordinated operations in complex mission environments, significantly improving the efficiency and accuracy of mission completion. However, since unmanned systems often need to perform missions in dynamic, hostile, and even extreme environments, mission reliability assessment has become a crucial research direction for measuring system performance and ensuring mission success. Existing mission reliability assessment techniques typically rely on single-modal data or static analysis methods, failing to fully consider the complex interactive characteristics of unmanned systems in multimodal dynamic environments. In particular, existing techniques for mission reliability assessment based on reconfigurable kill webs have significant limitations in data fusion, dynamic modeling, and trend prediction.

[0003] The shortcomings of existing technologies in assessing the mission reliability of unmanned equipment systems based on reconfigurable kill nets are mainly reflected in the following two points: First, current reliability assessment methods are usually based on simple statistical analysis or rule derivation, which makes it difficult to capture the changing characteristics of the mission reliability of unmanned equipment systems in dynamic environments. Second, in the process of multimodal data fusion, existing methods fail to fully utilize the differences in the importance of multimodal features, resulting in poor fusion effect and difficulty in accurately reflecting the mission reliability trends of unmanned equipment systems based on reconfigurable kill nets. In addition, there is also significant room for improvement in the existing methods' ability to predict the overall reliability trends of tasks and to automatically generate assessment reports. For example, it is difficult to predict the changing trends of future mission reliability through historical reliability score data, and it is also impossible to provide accurate decision-making assistance based on assessment trends. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for evaluating the mission reliability of an unmanned equipment system based on a reconfigurable kill net to solve the problems in the prior art of difficulty in capturing mission reliability changes in a dynamic environment and insufficient multimodal feature fusion effect.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for assessing the mission reliability of an unmanned equipment system based on a reconfigurable kill net, comprising collecting multimodal data and preprocessing the multimodal data; extracting multimodal features based on the preprocessed multimodal data, and fusing the multimodal features using a multimodal fusion network to generate a high-dimensional environmental feature vector; predicting a reliability score of the task based on the high-dimensional environmental feature vector; evaluating the overall reliability trend of the task based on the task reliability score, and generating a task reliability assessment report.

[0008] As a preferred solution of the unmanned equipment system mission reliability assessment method based on the reconfigurable kill net described in the present invention, the multimodal data includes terrain image data, weather data and enemy dynamic data.

[0009] As a preferred solution of the unmanned equipment system mission reliability assessment method based on the reconfigurable kill net of the present invention, the multimodal data is pre-processed in the following specific steps:

[0010] Gaussian filtering is used to remove noise from terrain images;

[0011] Use outlier detection to remove missing values and abnormal data in weather data, and use time alignment algorithms to unify weather data to the task execution timeline;

[0012] The normalization method is used to standardize the enemy's dynamic data.

[0013] As a preferred solution of the unmanned equipment system mission reliability assessment method based on the reconfigurable kill net of the present invention, wherein: the multimodal features are extracted based on the pre-processed multimodal data, and the specific steps are as follows:

[0014] Use convolutional neural network to perform convolution processing on the preprocessed terrain image to extract terrain features;

[0015] Extract weather characteristics from pre-processed weather data through statistical analysis;

[0016] Graph neural networks are used to extract spatial distribution features from preprocessed enemy dynamic data.

[0017] As a preferred solution of the unmanned equipment system mission reliability assessment method based on the reconfigurable kill net described in the present invention, wherein: the multimodal fusion network is used to fuse multimodal features to generate a high-dimensional environmental feature vector, and the specific steps are as follows:

[0018] The zero-padding method is used to align the dimensions of multimodal features, and the self-attention mechanism is used to dynamically assign the importance weight of each modality feature. The expression is:

[0019] ;

[0020] in, It is The attention weight of each modality feature, Attention score vector, It is The attention weight matrix of modality features, It is The feature vector after the modal features are aligned, It is The bias vector of each mode, j represents the index variable of all modal features in the normalization process, is the attention weight matrix of the j-th modal feature in the normalization process, is the feature vector after alignment of the jth modal feature in the normalization process, is the bias vector of the jth modal feature in the normalization process;

[0021] Based on the attention weight assigned to each modal feature, the attention mechanism is used to perform weighted fusion of multimodal features to generate a high-dimensional environment feature vector, which is expressed as:

[0022] ;

[0023] in, is the high-dimensional environment feature vector, is the linear transformation matrix, is a set of multimodal feature vectors, represents the average value of all elements in the multimodal feature vector set, Represents the standard deviation of all elements in the multimodal feature vector set.

[0024] As a preferred solution of the unmanned equipment system mission reliability assessment method based on the reconfigurable kill net of the present invention, wherein: the reliability score of the mission is predicted based on the high-dimensional environment feature vector, and the specific steps are as follows:

[0025] A deep time series prediction model is built based on LSTM and Transformer. The high-dimensional environment feature vector is input into the deep time series prediction model and combined with the activation function to capture the dynamic change characteristics in the time dimension and predict the reliability score of the task. The expression is:

[0026] ;

[0027] in, It is the current moment The task reliability score, Indicates to High-dimensional environmental features within the time window, is the Sigmoid activation function, is the weight matrix of the fully connected layer, is the weight matrix of the feedforward neural network, is the bias vector of the feedforward neural network, is the bias scalar of the fully connected layer, is the time window length.

[0028] As a preferred solution of the unmanned equipment system mission reliability assessment method based on the reconfigurable kill net of the present invention, wherein: the deep time series prediction model is constructed based on LSTM and Transformer, and the specific steps are as follows:

[0029] Based on LSTM, it captures the dynamic changes of task reliability in the time dimension, and combines the Transformer structure to extract global features in long time series;

[0030] Set up multiple layers of LSTM units, each unit is responsible for capturing local temporal dependencies within a time window, and the encoded time series is used as the output of the LSTM layer;

[0031] The Transformer layer uses a multi-head self-attention mechanism based on the output of the LSTM layer and extracts contextual information and long-term dependencies through a feedforward neural network;

[0032] The outputs of the LSTM layer and the Transformer layer are fused through the fully connected layer to build a deep time series prediction model.

[0033] As a preferred solution of the unmanned equipment system mission reliability assessment method based on the reconfigurable kill net of the present invention, wherein: the overall reliability trend of the mission is assessed based on the mission reliability score, and a mission reliability assessment report is generated. The specific steps are as follows:

[0034] Based on task reliability score , obtain the average score and extreme values of the task reliability score and combine them with the angular frequency and phase offset to predict the overall reliability trend of the task. The expression is:

[0035] ;

[0036] in, In the future to Overall reliability trend indicator of the task within, is the standard deviation of the reliability scores, is the maximum reliability score of the task, is the minimum reliability score of the task, is the average reliability score of the task, is the weight coefficient of the trend change rate, is the weight coefficient of cyclical fluctuations, is the trend change between adjacent moments, is the angular frequency of the periodic fluctuations, is the phase shift of the periodic fluctuation, Indicates the current moment;

[0037] Based on historical task data, define a high reliability threshold H and a low reliability threshold L;

[0038] when ≥H, the overall reliability of the task is considered to be in the future time period to There is an upward trend within

[0039] when When <L, the overall reliability of the task is considered to be in the future time period to There is a downward trend in

[0040] When L≤ When <H, the overall reliability of the task is considered to be in the future time period to Internal stability;

[0041] Generate a mission reliability assessment report based on the assessment results of the overall reliability trend of the mission.

[0042] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for assessing the mission reliability of an unmanned equipment system based on a reconfigurable kill net as described in the first aspect of the present invention is implemented.

[0043] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for assessing the mission reliability of an unmanned equipment system based on a reconfigurable kill network as described in the first aspect of the present invention.

[0044] The present invention achieves the following beneficial effects: by intelligently generating high-dimensional environmental feature vectors through a multimodal fusion network and dynamically adjusting the importance of each modality using a self-attention mechanism, the present invention improves the accuracy of data representation and the adaptability of the model. Combining a deep time series prediction model with LSTM and Transformer effectively captures the dynamic changes in mission reliability, providing accurate forecasts of future trends. This significantly enhances the accuracy and timeliness of mission reliability assessments for unmanned equipment systems, providing strong support for decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 Flowchart of the unmanned equipment system mission reliability assessment method based on the reconfigurable kill net in Example 1.

[0047] Figure 2 This is a flowchart of preprocessing multimodal data in Example 1. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0049] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0051] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for evaluating the mission reliability of an unmanned equipment system based on a reconfigurable kill net, comprising the following steps:

[0052] S1: Collect multimodal data and preprocess the multimodal data.

[0053] S1.1: Multimodal data includes terrain imagery data, weather data, and enemy dynamics data.

[0054] Furthermore, terrain image data is collected through satellite and drone aerial photography, weather data comes from weather stations or satellite weather services, and enemy dynamic data is obtained in real time by reconnaissance equipment and intelligence systems.

[0055] S1.2: Use Gaussian filtering to remove noise from the terrain image.

[0056] For example, by applying a 3x3 Gaussian filter to perform a convolution operation on the terrain image, the image is smoothed and random noise is effectively reduced, thereby improving image quality.

[0057] S1.3: Use outlier detection to remove missing values and abnormal data in the weather data, and use the time alignment algorithm to unify the weather data to the timeline of task execution.

[0058] For example, the box plot method is used to identify and eliminate outliers in weather data (such as data points where temperature and humidity exceed 1.5 times the interquartile range). For missing values, linear interpolation is used based on data from adjacent time points. Finally, a time alignment algorithm is used to ensure that all weather data is consistent with the specific time point of task execution.

[0059] S1.4: Use normalization methods to standardize enemy dynamic data.

[0060] For example, each feature value in the enemy dynamic data is scaled to a range between 0 and 1 to ensure that data of different dimensions are comparable in subsequent analysis, facilitating model training and prediction.

[0061] S2: Based on the preprocessed multimodal data, multimodal features are extracted and fused using a multimodal fusion network to generate a high-dimensional environment feature vector.

[0062] S2.1: Use a convolutional neural network to perform convolution processing on the preprocessed terrain image to extract terrain features.

[0063] Specifically: the preprocessed terrain image is input to the input layer of CNN; then, through multiple layers of convolutional layers, each convolutional layer contains multiple convolution kernels (or filters), which slide on the image and perform local weighted summation operations to extract low-level features such as edges and textures at different scales and directions; then, nonlinear transformations are introduced through activation functions (such as ReLU) to enhance the model's expressiveness; subsequently, pooling layers (such as maximum pooling) are used to reduce the spatial size of the feature map while retaining the most important feature information; finally, through a series of deep convolutional layers, more abstract and complex terrain structural features, such as peaks, valleys and other terrain elements, are gradually extracted, ultimately generating a high-dimensional feature representation rich in terrain information, providing a solid foundation for subsequent task reliability assessment.

[0064] S2.2: Extract weather characteristics from the preprocessed weather data through statistical analysis.

[0065] Specifically: First, the preprocessed weather data is classified and summarized according to name (such as temperature, humidity, wind speed, etc.); then, the basic statistics of each weather parameter, such as mean, standard deviation, maximum and minimum values, are calculated to capture its distribution characteristics; then, time series analysis methods are used to identify the time dependence and periodic patterns of each weather parameter; finally, based on these statistical analysis results, key features that can reflect weather conditions are extracted, such as the daily variation of temperature, seasonal fluctuations in humidity, and the average intensity of wind speed, providing detailed weather information support for subsequent mission reliability assessment.

[0066] S2.3: Use graph neural networks to extract spatial distribution features from preprocessed enemy dynamic data.

[0067] Specifically, the pre-processed enemy dynamic data is constructed into a graph structure according to geographical location, where each node represents a specific enemy unit or observation point, and the edge represents the spatial relationship or interaction between units; then, through the multi-layer propagation mechanism of GNN, message transmission is carried out on the graph, information of adjacent nodes is aggregated, and spatial correlations and local patterns between enemy units are captured; then, the node embedding vector is updated using node features and edge weights, and high-level spatial distribution features are gradually extracted; finally, a feature representation reflecting the overall spatial structure of the enemy dynamic data is generated, such as the cluster density, movement trends and strategic deployment of enemy units, providing detailed spatial distribution information for mission reliability assessment.

[0068] S2.4: Use zero padding to align the dimensions of multimodal features and use the self-attention mechanism to dynamically assign the importance weight of each modality feature. The expression is:

[0069] ;

[0070] in, It is The attention weight of each modality feature, Attention score vector, It is The attention weight matrix of modality features, It is The feature vector after the modal features are aligned, It is The bias vector of each mode, j represents the index variable of all modal features in the normalization process, is the attention weight matrix of the j-th modal feature in the normalization process, is the feature vector after alignment of the jth modal feature in the normalization process, is the bias vector of the jth modal feature in the normalization process.

[0071] It should be noted that the zero-filling method refers to a method of filling missing values or data points that need to be aligned with zero values in data processing.

[0072] It should also be noted that by using zero-padding to align the dimensions of multimodal features and combining it with a self-attention mechanism to dynamically assign importance weights to each modal feature, this step ensures that the different modal data have a unified dimension before fusion, while automatically adjusting the importance of each modal feature based on task requirements. This approach not only improves the accuracy and robustness of multimodal data fusion, but also enhances the model's adaptability to complex environmental changes, ultimately improving the accuracy and reliability of task reliability assessments.

[0073] S2.5: Based on the attention weights assigned to each modal feature, the attention mechanism is used to perform weighted fusion of multimodal features to generate a high-dimensional environment feature vector, which is expressed as:

[0074] ;

[0075] in, is the high-dimensional environment feature vector, is the linear transformation matrix, is a set of multimodal feature vectors, represents the average value of all elements in the multimodal feature vector set, Represents the standard deviation of all elements in the multimodal feature vector set.

[0076] It should be noted that the linear change matrix is defined based on historical data and is used to linearly combine the weighted multimodal feature vectors. This matrix is designed based on an understanding of the characteristics of different modal data, and its parameters are determined through mathematical methods to ensure that the different modal features are appropriately scaled and transformed during the fusion process. This ensures that the generated high-dimensional environment feature vectors have stronger expressive power and better structured information, thereby improving the effectiveness of task reliability assessment.

[0077] S3: Predict the reliability score of the task based on the high-dimensional environment feature vector.

[0078] S3.1: Build a deep time series prediction model based on LSTM and Transformer. Input the high-dimensional environment feature vector into the deep time series prediction model and combine it with the activation function to capture the dynamic change characteristics in the time dimension and predict the reliability score of the task. The expression is:

[0079] ;

[0080] in, It is the current moment The task reliability score, Indicates to High-dimensional environmental features within the time window, is the Sigmoid activation function, is the weight matrix of the fully connected layer, is the weight matrix of the feedforward neural network, is the bias vector of the feedforward neural network, is the bias scalar of the fully connected layer, is the time window length.

[0081] It should be noted that the reason for choosing LSTM is that it is good at capturing long-term dependencies in time series data and is very suitable for processing dynamically changing features in task reliability assessment.

[0082] The reason for choosing Transformer is that it can efficiently process global correlations in multimodal data through the self-attention mechanism, significantly improving the accuracy of feature extraction and fusion.

[0083] S3.2: Build a deep time series prediction model based on LSTM and Transformer. The specific steps are as follows:

[0084] S3.2.1: Based on LSTM, it captures the dynamic changing characteristics of task reliability in the time dimension, and combines the Transformer structure to extract global features in long time series.

[0085] Specifically, the high-dimensional environment feature vector is processed layer by layer through multiple layers of Long Short-Term Memory (LSTM) units. Each LSTM unit is responsible for capturing local temporal dependencies within a time window and memorizing long-term historical information. The output of the LSTM layer is then passed to the Transformer architecture, which uses its multi-head self-attention mechanism to process all positions in the input sequence in parallel, extracting global features and complex patterns from long time series. Finally, a fully connected layer fuses the local dynamics captured by the LSTM with the global features extracted by the Transformer.

[0086] S3.2.2: Set up multiple layers of LSTM units, each unit is responsible for capturing local temporal dependencies within a time window, and the encoded time series is used as the output of the LSTM layer.

[0087] For example, consider a three-layer LSTM unit. The first layer receives high-dimensional environment feature vectors as input and processes these feature vectors one by one using a sliding time window to capture short-term temporal dependencies. The second layer, based on the output of the first layer, further captures dynamic changes over longer time spans, enhancing memory for historical information. The third layer finally integrates the information from the first two layers to generate a more abstract and high-level time series representation, which serves as the output of the entire LSTM layer.

[0088] S3.2.3: The Transformer layer uses a multi-head self-attention mechanism based on the output of the LSTM layer and extracts contextual information and long-term dependencies through a feedforward neural network.

[0089] Specifically, the time series representation generated by the LSTM layer is input into the encoder portion of the Transformer. A multi-head self-attention mechanism processes the information at each time step in parallel, capturing global correlations and contextual information between different time points. Next, a feedforward neural network performs a nonlinear transformation on the features at each time step to further extract and enhance contextual information and long-term dependencies. This process not only efficiently processes complex patterns in long time series but also ensures that the features at each time step receive sufficient attention and optimization, ultimately generating a high-dimensional representation rich in global features, providing more accurate support for task reliability assessment.

[0090] S3.2.4: The outputs of the LSTM layer and the Transformer layer are fused through a fully connected layer to construct a deep time series prediction model.

[0091] It should be noted that the fully connected layer integrates the different time scale features extracted by the two layers and generates the final task reliability score through nonlinear transformation, thereby achieving accurate prediction and evaluation of task reliability trends.

[0092] S4: Based on the task reliability score, evaluate the overall reliability trend of the task and generate a task reliability assessment report.

[0093] S4.1: Scoring based on task reliability , obtain the average score and extreme values of the task reliability score and combine them with the angular frequency and phase offset to predict the overall reliability trend of the task. The expression is:

[0094] ;

[0095] in, In the future to Overall reliability trend indicator of the task within, is the standard deviation of the reliability scores, is the maximum reliability score of the task, is the minimum reliability score of the task, is the average reliability score of the task, is the weight coefficient of the trend change rate, is the weight coefficient of cyclical fluctuations, is the trend change between adjacent moments, is the angular frequency of the periodic fluctuations, is the phase shift of the periodic fluctuation, Indicates the current moment.

[0096] S4.2: Based on historical task data, define a high reliability threshold H and a low reliability threshold L.

[0097] when ≥H, the overall reliability of the task is considered to be in the future time period to There is an upward trend within.

[0098] when When <L, the overall reliability of the task is considered to be in the future time period to There is a downward trend within.

[0099] When L≤ When <H, the overall reliability of the task is considered to be in the future time period to Internally stable.

[0100] For example, suppose historical data shows that the mean reliability score for a task is 0.75, with a standard deviation of 0.1. Based on these statistics, combined with expert experience and specific task requirements, a high reliability threshold, H, is set to the mean plus one standard deviation (i.e., 0.85), indicating a highly reliable task. A low reliability threshold, L, is set to the mean minus one standard deviation (i.e., 0.65), indicating a high-risk task. This ensures that the thresholds reflect the actual distribution of historical data while adapting to the specific needs of different tasks, providing a scientifically sound evaluation standard.

[0101] S4.3: Generate a mission reliability assessment report based on the assessment results of the overall reliability trend of the mission.

[0102] Furthermore, the mission reliability assessment report includes an analysis of the overall reliability trend of the mission, prediction results of future reliability, and assessment conclusions and recommendations based on high and low reliability thresholds set based on historical data and expert experience.

[0103] This embodiment also provides a computer device suitable for the case of an unmanned equipment system mission reliability assessment method based on a reconfigurable kill net, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the unmanned equipment system mission reliability assessment method based on a reconfigurable kill net as proposed in the above embodiment.

[0104] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0105] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for evaluating the mission reliability of an unmanned equipment system based on a reconfigurable kill net as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0106] In summary, this invention improves the accuracy of data representation and the adaptability of the model by intelligently generating high-dimensional environmental feature vectors using a multimodal fusion network and dynamically adjusting the importance of each modality using a self-attention mechanism. Combining a deep time series prediction model with LSTM and Transformer effectively captures the dynamic changes in task reliability, providing accurate forecasts of future trends. This significantly enhances the accuracy and timeliness of task reliability assessments for unmanned equipment systems, providing strong support for decision-making.

[0107] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of the unmanned equipment system mission reliability assessment method based on the reconfigurable kill net is provided.

[0108] In order to verify the effectiveness of the mission reliability assessment method for unmanned equipment systems based on reconfigurable kill nets, a simulated military exercise was designed with three experimental groups to demonstrate the invention through objective data analysis.

[0109] First, terrain imagery, weather data, and enemy dynamics data are collected from multiple sources to ensure data diversity and authenticity. The collected data is then preprocessed, including denoising, outlier processing, and temporal alignment.

[0110] Then, a deep time series prediction model is constructed based on LSTM and Transformer to capture the temporal dependencies in multimodal data.

[0111] Next, the fused features are input into the deep time series prediction model constructed by LSTM and Transformer, and the task reliability score is output through the fully connected layer.

[0112] Finally, the overall reliability trend index is calculated based on the reliability score, high reliability and low reliability thresholds are set based on historical data, and a task reliability assessment report containing analysis, prediction results and recommendations is generated.

[0113] The details are shown in Table 1 below:

[0114] Table 1 Task reliability evaluation report

[0115]

[0116] Analyzing the data in the table above clearly shows that terrain image clarity and weather stability significantly affect mission reliability scores. When terrain image clarity is high and weather is stable (as in Experiment 1), mission reliability scores are high, with overall reliability trending upward. When weather is unstable and enemy activity density increases (as in Experiment 2), mission reliability scores drop significantly, with overall reliability trending downward. Even when enemy activity density is high, but terrain image clarity is low and weather is stable (as in Experiment 3), mission reliability scores remain at a moderate level, with overall reliability tending to stabilize.

[0117] By integrating multimodal data and utilizing a deep time series prediction model combining LSTM and Transformer, this paper can effectively predict mission reliability scores. For example, in Experiment 1, with terrain image clarity of 85%, weather stability of 78%, and enemy activity density of 22%, the mission reliability score reached 0.83, indicating high mission reliability. In contrast, in Experiment 2, with terrain image clarity of 63%, weather stability of 42%, and enemy activity density of 58%, the mission reliability score was only 0.62, indicating lower mission reliability.

[0118] The above results show that the method of the present invention has obvious advantages in dealing with complex environments and dynamic changes, and can provide more reliable support for decision makers.

[0119] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for evaluating the mission reliability of an unmanned equipment system based on a reconfigurable kill net, characterized by: include, Collect multimodal data and preprocess the multimodal data; Based on the preprocessed multimodal data, multimodal features are extracted and fused using a multimodal fusion network to generate a high-dimensional environmental feature vector. Predict the reliability score of the task based on the high-dimensional environment feature vector; Based on the mission reliability score, the overall reliability trend of the mission is evaluated and a mission reliability assessment report is generated; The reliability score of the task is predicted based on the high-dimensional environment feature vector. The specific steps are as follows: A deep time series prediction model is built based on LSTM and Transformer. The high-dimensional environment feature vector is input into the deep time series prediction model and combined with the activation function to capture the dynamic change characteristics in the time dimension and predict the reliability score of the task. The expression is: ； in, It is the current moment The task reliability score, Indicates to High-dimensional environmental features within the time window, is the Sigmoid activation function, is the weight matrix of the fully connected layer, is the weight matrix of the feedforward neural network, is the bias vector of the feedforward neural network, is the bias scalar of the fully connected layer, is the time window length; According to the task reliability score, the overall reliability trend of the task is evaluated and a task reliability evaluation report is generated. The specific steps are as follows: Based on task reliability score , obtain the average score and extreme values of the task reliability score and combine them with the angular frequency and phase offset to predict the overall reliability trend of the task. The expression is: ； in, In the future to Overall reliability trend indicator of the task within, is the standard deviation of the reliability scores, is the maximum reliability score of the task, is the minimum reliability score of the task, is the average reliability score of the task, is the weight coefficient of the trend change rate, is the weight coefficient of cyclical fluctuations, is the trend change between adjacent moments, is the angular frequency of the periodic fluctuations, is the phase shift of the periodic fluctuation, Indicates the current moment; Based on historical task data, define a high reliability threshold H and a low reliability threshold L; when ≥H, the overall reliability of the task is considered to be in the future time period to There is an upward trend within when When <L, the overall reliability of the task is considered to be in the future time period to There is a downward trend in When L≤ When <H, the overall reliability of the task is considered to be in the future time period to Internal stability; Generate a mission reliability assessment report based on the assessment results of the overall reliability trend of the mission.

2. The method for evaluating mission reliability of an unmanned equipment system based on a reconfigurable kill net according to claim 1, wherein: The multimodal data includes terrain image data, weather data and enemy dynamic data.

3. The method for evaluating mission reliability of an unmanned equipment system based on a reconfigurable kill net according to claim 2, wherein: The multimodal data is preprocessed, and the specific steps are as follows: Gaussian filtering is used to remove noise from terrain images; Use outlier detection to remove missing values and abnormal data in weather data, and use time alignment algorithms to unify weather data to the task execution timeline; The normalization method is used to standardize the enemy's dynamic data.

4. The method for evaluating mission reliability of an unmanned equipment system based on a reconfigurable kill net according to claim 3, wherein: The multimodal features are extracted based on the preprocessed multimodal data. The specific steps are as follows: Use convolutional neural network to perform convolution processing on the preprocessed terrain image to extract terrain features; Extract weather characteristics from pre-processed weather data through statistical analysis; Graph neural networks are used to extract spatial distribution features from preprocessed enemy dynamic data.

5. The method for evaluating mission reliability of an unmanned equipment system based on a reconfigurable kill net according to claim 4, wherein: The multimodal fusion network is used to fuse multimodal features to generate a high-dimensional environment feature vector. The specific steps are as follows: The zero-padding method is used to align the dimensions of multimodal features, and the self-attention mechanism is used to dynamically assign the importance weight of each modality feature. The expression is: ； in, It is The attention weight of each modality feature, Attention score vector, It is The attention weight matrix of modality features, It is The feature vector after the modal features are aligned, It is The bias vector of each mode, j represents the index variable of all modal features in the normalization process, is the attention weight matrix of the j-th modal feature in the normalization process, is the feature vector after alignment of the jth modal feature in the normalization process, is the bias vector of the jth modal feature in the normalization process; Based on the attention weight assigned to each modal feature, the attention mechanism is used to perform weighted fusion of multimodal features to generate a high-dimensional environment feature vector, which is expressed as: ； in, is the high-dimensional environment feature vector, is the linear transformation matrix, is a set of multimodal feature vectors, represents the average value of all elements in the multimodal feature vector set, Represents the standard deviation of all elements in the multimodal feature vector set.

6. The method for evaluating mission reliability of an unmanned equipment system based on a reconfigurable kill net according to claim 5, wherein: The specific steps of building a deep time series prediction model based on LSTM and Transformer are as follows: Based on LSTM, it captures the dynamic changes of task reliability in the time dimension, and combines the Transformer structure to extract global features in long time series; Set up multiple layers of LSTM units, each unit is responsible for capturing local temporal dependencies within a time window, and the encoded time series is used as the output of the LSTM layer; The Transformer layer uses a multi-head self-attention mechanism based on the output of the LSTM layer and extracts contextual information and long-term dependencies through a feedforward neural network; The outputs of the LSTM layer and the Transformer layer are fused through the fully connected layer to build a deep time series prediction model.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for evaluating mission reliability of an unmanned equipment system based on a reconfigurable kill net according to any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating mission reliability of an unmanned equipment system based on a reconfigurable kill net according to any one of claims 1 to 6 are implemented.

Images