A distributed comprehensive perception method and device

Abstract

The application discloses a kind of distributed comprehensive perception method and device.The method comprises: according to the environmental data and task demand obtained, the task boundary of perception target and the resource condition required by system are determined, the system deployment scheme is optimized using particle swarm algorithm according to task boundary and resource condition, and the working timing of perception node is determined, the target information of all dimensions of perception target is obtained using perception node according to working timing and the system deployment scheme optimized, the target information of all dimensions is associated and fused, and target state information is obtained.Through the optimization of system deployment scheme and working timing of perception node, the target information of all dimensions of perception target is obtained by perception node, and accurate global monitoring of perception target is realized.

Description

Technical Field

[0001] This application relates to the field of multi-dimensional information monitoring technology, and more specifically, to a distributed integrated sensing method and device. Background Technology

[0002] Platform targets with strong carrying capacity (such as transport aircraft, large satellites, and airships equipped with multiple sensor systems) or strong maneuverability (such as supersonic aircraft and near-space vehicles) possess strong mission execution capabilities and play important roles in defense, commerce, and other fields, thus possessing high value and requiring comprehensive and accurate monitoring of their status information. The acquisition of target status information is typically undertaken by various sensors, such as radar, sonar, electronic reconnaissance, infrared, optical imaging, and microwave imaging. Different types of sensors have their applicable ranges. Active sensors such as radar and sonar can determine the target's position, velocity, and other motion information, but they struggle to acquire operational information about the electronic equipment carried by the target. Passive sensors, such as electronic reconnaissance, are the opposite; while they may not be able to comprehensively acquire the target's spatial and motion information, they can often acquire the radiation signals of the various electronic devices carried by the platform, identify their operational status, and thus support the judgment of target attributes and behavioral intentions. Clearly, comprehensive target monitoring requires not only acquiring its position and motion information but also determining its attributes and behavioral intentions; therefore, it necessitates the comprehensive use of multiple sensors for holistic perception.

[0003] In existing technologies, the most common way to achieve multi-sensor integrated perception is through multiple sensors mounted on a single platform. However, this approach presents two main problems: First, the lack of spatial diversity on a single platform leads to insufficient continuity of the acquired target state information. Because a single node can only perceive and acquire target state information from a single angle, there are significant difficulties in ensuring the completeness and continuity of the target state information data. For example, for sensing methods such as infrared, radar, and electronic reconnaissance, a single observation angle may result in a certain probability of missed detection due to factors such as weak infrared signals from the target's exhaust plume, the disappearance of Doppler features, and the unpredictable scanning method of the target payload's radiation source antenna. This leads to discontinuous and incomplete target state information data in scenarios involving long-term, multiple observations.

[0004] Secondly, the characteristics of target state information changes vary across different dimensions, with the agile nature of state information further complicating comprehensive target monitoring. For example, near-space vehicles, benefiting from their high maneuverability, often exhibit drastic changes in spatial state parameters such as azimuth and range. Active sensors like radar experience performance degradation when facing such targets due to echo cross-beam, cross-Doppler, and cross-range cell issues, leading to missing target points and difficulty in maintaining tracks. Furthermore, the target's high maneuverability makes it difficult for sensors to infer target position information using slow-moving target motion models even when points are lost, and it's challenging to extrapolate and complete missing state information using only partial data. Therefore, how to accurately monitor the multi-dimensional state information of targets across the entire domain has become a problem that those skilled in the art must consider. Summary of the Invention

[0005] The purpose of this application is to overcome the shortcomings of existing technologies and provide a distributed integrated sensing method and device. By optimizing the system deployment scheme and determining the working sequence of sensing nodes, the sensing nodes are managed so that different sensing nodes can switch in time according to the working sequence, acquire and target the state information in the same dimension, and realize the full-domain accurate monitoring of the multi-dimensional state information of the target.

[0006] The objective of this application is achieved through the following technical solution:

[0007] Firstly, this application proposes a distributed integrated sensing method, which is applied to a distributed integrated sensing system comprising multiple sensing nodes, including:

[0008] Based on the acquired environmental data and task requirements, determine the task boundaries of the sensing targets and the resource conditions required by the system;

[0009] Based on the task boundaries and resource conditions, the system deployment scheme is optimized using the particle swarm optimization algorithm, and the working sequence of the sensing nodes is determined.

[0010] The sensing nodes are used to acquire target information of all dimensions of the sensing target according to the working sequence and the optimized system deployment scheme.

[0011] By associating and fusing target information from all dimensions, target state information is obtained.

[0012] In one possible implementation, the state of the target information is either agile or gradual, and the method further includes:

[0013] It adopts an intermittent relay sensing method to acquire target information with rapidly changing states in the first instance;

[0014] A time-division sparse observation method is adopted to obtain target information with slowly changing state using a second time, where the first time is longer than the second time.

[0015] In one possible implementation, the step of associating and fusing the target information of the said dimension to obtain target state information includes:

[0016] The target information of state agile transformation is organized using normalization technology, and the organized target information of state agile transformation is spliced ​​together in chronological order.

[0017] Extrapolate and interpolate target information whose state changes gradually;

[0018] By associating and fusing the spliced ​​target information with its rapidly changing state and the extrapolated target information with its gradually changing state, the target state information is obtained.

[0019] In one possible implementation, the environmental data includes physical environmental data and electromagnetic environmental data, wherein the physical environmental data includes climate and hydrology, and the electromagnetic environmental data includes electromagnetic signal spectrum distribution and amplitude.

[0020] In one possible implementation, the target status information includes one or more of the following: target azimuth, altitude, speed, load radiation source operating frequency band, and operating mode.

[0021] In one possible implementation, the method for determining the working timing of the sensing node includes: simultaneous search and tracking, tracking plus search, load balancing, and periodic expansion.

[0022] In one possible implementation, optimizing the system deployment scheme includes: optimizing the deployment based on the location of the sensing nodes, jointly adjusting the beam parameters of the sensing nodes, and constructing communication links.

[0023] Secondly, this application proposes a distributed integrated sensing device, the device comprising:

[0024] The first acquisition module is used to determine the task boundary of the sensing target and the resource conditions required by the system based on the acquired environmental data and task requirements;

[0025] The optimization module is used to optimize the system deployment scheme using the particle swarm optimization algorithm based on the task boundary and the resource conditions, and to determine the working sequence of the sensing nodes.

[0026] The second acquisition module is used to acquire target information of all dimensions of the sensing target by using the sensing node according to the working sequence and the optimized system deployment scheme;

[0027] The generation module is used to associate and fuse target information from all dimensions to obtain target state information.

[0028] Thirdly, this application also proposes a computer device comprising a processor and a memory, wherein the memory stores a computer program, which is loaded and executed by the processor to implement the distributed integrated sensing method as described in any of the first aspects.

[0029] Fourthly, this application also proposes a computer-readable storage medium storing a computer program that is loaded and executed by a processor to implement the distributed integrated sensing method as described in any of the first aspects.

[0030] The main solution and its various further alternatives described above can be freely combined to form multiple solutions, all of which are solutions that can be adopted and are claimed in this application; furthermore, the (non-conflicting alternatives) can also be freely combined with each other and with other alternatives. Those skilled in the art, after understanding the solution of this application, will realize from the prior art and common general knowledge that there are many combinations, all of which are technical solutions to be protected by this application, and will not be exhaustively listed here.

[0031] This application discloses a distributed integrated sensing method and apparatus. The method includes: determining the task boundary of the sensing target and the resource conditions required by the system based on acquired environmental data and task requirements; optimizing the system deployment scheme using a particle swarm optimization algorithm based on the task boundary and resource conditions; determining the working sequence of the sensing nodes; using the sensing nodes to acquire target information of all dimensions of the sensing target according to the working sequence and the optimized system deployment scheme; and associating and fusing the target information of all dimensions to obtain target state information. By optimizing the system deployment scheme and working sequence of the sensing nodes, the sensing nodes can acquire target information of the sensing target in all dimensions, achieving accurate full-domain monitoring of the sensing target. Attached Figure Description

[0032] Figure 1 This illustration shows an application scenario diagram of the distributed integrated sensing method proposed in an embodiment of this application.

[0033] Figure 2 This illustration shows another application scenario of the distributed integrated sensing method proposed in the embodiments of this application.

[0034] Figure 3 A flowchart illustrating a distributed integrated sensing method proposed in an embodiment of this application is shown.

[0035] Figure 4a This diagram illustrates the timing sequence of a sensing node acquiring target information from a satellite / airship.

[0036] Figure 4bA timing diagram illustrating the acquisition of target information of a supersonic vehicle by a sensing node is shown.

[0037] Figure 5a The frequency diagram of the electromagnetic signals acquired by the sensing node from the sensing target is shown.

[0038] Figure 5b A schematic diagram showing the location and distance of the sensing target obtained by the sensing node is shown. Detailed Implementation

[0039] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0040] Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this application.

[0041] In existing technologies, the comprehensive perception of multi-dimensional state information by using multiple sensors on a single platform has two drawbacks. First, the lack of spatial diversity of a single platform leads to insufficient continuity of the acquired target state information. Second, the characteristics of state information change in different dimensions of the target are usually different, and the agile nature of the state information exacerbates the difficulty of comprehensive monitoring of the target.

[0042] This application proposes a distributed integrated sensing method to address the shortcomings of single-node target monitoring, such as lack of spatial diversity and rapid changes in target state parameters. By optimizing the system deployment scheme and determining the working sequence of sensing nodes, different sensing nodes can switch in a time-sharing manner according to their working sequence to acquire and obtain the target's state information in the same dimension, thereby achieving accurate full-domain monitoring of the target's multi-dimensional state information. The following will provide a detailed explanation.

[0043] This application proposes a distributed integrated sensing method, which is applied to a distributed integrated sensing system. The distributed integrated sensing system includes multiple sensing nodes. Please refer to... Figure 1 and Figure 2 , Figure 1 This illustration shows an application scenario diagram of the distributed integrated sensing method proposed in an embodiment of this application. Figure 2 The figure shows another application scenario of the distributed integrated sensing method proposed in the embodiments of this application. Figure 1 The sensing targets are one artificial satellite and one airship. The sensing system acquires multi-dimensional information about the gradually changing states of the artificial satellite and the airship through multiple integrated sensing nodes, and transmits the information to the processing center for processing. Figure 2 The target of perception is a hypersonic vehicle in near space. Similarly, multiple integrated perception nodes are used to acquire multi-dimensional information on the hypersonic vehicle's state agility and transmit it to the processing center for processing.

[0044] The integrated sensing nodes monitoring artificial satellites / airships have limited wireless communication capabilities, so they adopt a chain-like communication transmission method of mutual transmission between neighboring nodes to transmit data to the central node for processing. The integrated sensing nodes monitoring hypersonic vehicles can be equipped with optical fibers, which have short communication latency and high throughput. Therefore, each node can independently transmit data to the processing center, and then the processing center processes the target information uniformly. The following uses artificial satellites / airships and hypersonic vehicles as examples to illustrate the distributed integrated sensing system.

[0045] Please refer to Figure 3 , Figure 3 The diagram illustrates a distributed integrated sensing method proposed in an embodiment of this application, comprising the following steps:

[0046] Step S100: Determine the task boundary of the sensing target and the resource conditions required by the system based on the acquired environmental data and task requirements.

[0047] Environmental data includes physical and electromagnetic environmental data. Physical environmental data includes climate and hydrology, while electromagnetic environmental data includes the spectrum distribution and amplitude of electromagnetic signals. The task boundary defines the system's sensing space domain and the approximate range of the sensing targets. System resource requirements include node resources, sensor types, and other system parameters. Determining the task boundary of the sensing targets and the system's required resource conditions based on environmental data and real-time task requirements allows for optimization of the spatial location and beam pointing of sensing nodes, achieving comprehensive coverage of the target's state parameter variation range while also considering spatial diversity and effectively acquiring Doppler, infrared, and other information.

[0048] In addition, step S100 can also actively detect illumination / receive and passively reconnoiter the receiving beam covering all possible directions of the target and the reconnaissance frequency band covering all possible operating frequency bands of the target payload radiation source.

[0049] Step S200: Optimize the system deployment scheme using the particle swarm optimization algorithm based on the task boundary and resource conditions, and determine the working sequence of the sensing nodes.

[0050] The optimization of the system deployment scheme includes: optimizing the site layout based on the location of sensing nodes, jointly adjusting the beam parameters of sensing nodes, and constructing communication links. The beam parameters include beam pointing range, beam azimuth, and elevation width. The steps for optimizing the system deployment scheme using the particle swarm optimization algorithm include: under constraints such as communication distance, establishing a mathematical model for system deployment scheme optimization based on a discretized reconnaissance and surveillance area and the worst-case performance criterion; and proposing a system site optimization deployment algorithm based on a hybrid coded particle swarm optimization (PSO) algorithm for the model.

[0051] Taking into account resource conditions such as the number of targets and the total amount of node resources, methods such as simultaneous search and tracking, tracking plus search, load balancing, and periodic expansion are used to determine and optimize the working sequence of sensing nodes.

[0052] Step S300: Use the sensing nodes to obtain target information of all dimensions of the sensing target according to the working sequence and the optimized system deployment plan.

[0053] According to the designed timing sequence and optimized system deployment plan, and in conjunction with the unified spatiotemporal reference provided by atomic clocks, navigation satellites, etc., the sensing nodes switch between different working modes to comprehensively acquire target information from all dimensions of the sensing target from different dimensions such as space, electromagnetic spectrum, and infrared. The acquired target status information is transmitted to the processing center according to a certain transmission and processing cycle (determined by factors such as node transmission capacity and processing capacity).

[0054] The target information is divided into state agile and state slowly changing. The distributed integrated perception system adopts an intermittent relay perception method to obtain the target information with agile state in the first time and adopts a time-division sparse observation method to obtain the target information with slowly changing state in the second time. The first time is greater than the second time.

[0055] State agility refers to parameter dimensions where the target's state changes rapidly. For artificial satellites / airships, state-agile target information includes parameters within the electromagnetic spectrum, such as the frequency band of the target's radiation source. For supersonic vehicles, the agile target information includes physical spatial parameters such as the target's position, velocity, and altitude. State gradual change refers to parameter dimensions where the target's state changes slowly.

[0056] The distributed integrated sensing system allocates different time resources to target information with different states. More time resources are invested in target information with rapidly changing states, using an intermittent relay sensing method to acquire it. For target information with slowly changing states, less time resources are invested, using a time-division sparse observation method to acquire it. This allows for the comprehensive acquisition of state information from different dimensions, ensuring the completeness of the information.

[0057] For artificial satellites / airships, spectral waveform parameters are used as target information for state agility, and spatial motion parameters are used as target information for state gradual change. For supersonic vehicles, spatial motion parameters are used as target information for state agility, and spectral waveform parameters are used as target information for state gradual change. Please refer to [reference needed]. Figure 4a and Figure 4b , Figure 4a This diagram illustrates the timing sequence of a sensing node acquiring target information about a satellite / airship. Figure 4b A timing diagram illustrating the acquisition of target information of a supersonic vehicle by a sensing node is shown.

[0058] Figure 4a Three sensing nodes were selected and intermittently relayed to acquire the timing of electromagnetic signals and azimuth motion information of two sensing targets (an artificial satellite and an airship). The time periods of the first two overlapping relay reconnaissances were marked with dashed lines. The timing of electromagnetic signals and azimuth motion information acquired by node 2 was slightly lower than that acquired by node 1, and the timing of electromagnetic signals and azimuth motion information acquired by node 3 was slightly lower than that acquired by node 2. Each node sent its acquired electromagnetic signals and azimuth motion information timing to the distributed integrated sensing system, and the system fused the received information.

[0059] Figure 4b Two sensing nodes were selected and intermittently relayed the acquisition of position and velocity parameters, communication and control signals, and exhaust infrared signals of a single sensing target (supersonic aircraft) in physical space. The time periods of the first two overlapping relay sensing were marked with dashed lines. The timing of the position and velocity parameters, communication and control signals, and exhaust infrared signals acquired by node 2 was slightly lower than that acquired by node 1. Each node sent its acquired timing data to the distributed integrated sensing system, which then fused the received information.

[0060] Please refer to the corresponding information. Figure 5a and Figure 5b , Figure 5a The diagram shows the frequency distribution of electromagnetic signals acquired by sensing nodes from a target. Taking target 1 as an example, there is a certain range of dwell time and instantaneous bandwidth for a single scan. During the dwell time, the radiation source frequency acquired by sensing node 1 is in an upward trend. Within this time range, sensing node 2 also acquires the upward radiation source frequency within its own time range. Subsequently, sensing node 3 also acquires the upward radiation source frequency. The overlapping part in the diagram is... Figure 4a The overlapping signals correspond to the signals received simultaneously from the target radiation signals within the same frequency band.

[0061] Figure 5bThis diagram illustrates how a sensing node acquires the location and distance of a sensed target. The sensing node (radar) acquires its beam coverage area, indicating the target's trajectory. The overlapping portion of the target detected by each node corresponds to... Figure 4b The overlapping detection of target location and parameters allows for simultaneous detection by two sensing nodes when the target is in the overlapping area.

[0062] S400. Correlate and fuse target information from all dimensions to obtain target state information.

[0063] Optionally, the target information of agile state changes is organized using normalization technology, the organized target information of agile state changes is spliced ​​together in chronological order, the target information of slowly changing state changes is extrapolated and interpolated, and the spliced ​​target information of agile state changes and the extrapolated target information of slowly changing state changes are associated and fused to obtain the target state information.

[0064] Target status information includes target azimuth, altitude, velocity, operating frequency band of payload radiation source, and operating mode. To eliminate the influence of factors such as amplitude fluctuations and measurement errors, normalization and other techniques are used to organize target information with rapidly changing states, and the organized data is then stitched together in chronological order. For target information with slowly changing states, the state change patterns are inferred based on the target information obtained from sensing nodes. Based on the inferred patterns, missing data is supplemented through extrapolation and interpolation. Finally, the state information of the sensed target in different dimensions is correlated and fused to obtain multi-dimensional target status information.

[0065] Compared with the prior art, the embodiments of this application have the following beneficial effects:

[0066] First, by selecting multiple spatially distributed sensing nodes to comprehensively perceive the target and obtain its state parameter information in different dimensions, the shortcomings of insufficient spatial diversity in obtaining target information by selecting a single node can be overcome.

[0067] Second, by optimizing the system deployment plan and determining the working sequence of the sensing nodes, different sensing nodes can be switched in time according to the working sequence to obtain and target status information in the same dimension, thereby achieving full-domain accurate monitoring of the target's multi-dimensional status information.

[0068] Furthermore, this application also proposes a possible implementation of a distributed integrated sensing device, which is used to execute the various execution steps and corresponding technical effects of the distributed integrated sensing method shown in the above embodiments and possible implementations, which will not be repeated here. The distributed integrated sensing device includes:

[0069] The first acquisition module is used to determine the task boundary of the sensing target and the resource conditions required by the system based on the acquired environmental data and task requirements;

[0070] The optimization module is used to optimize the system deployment scheme based on task boundaries and resource conditions using the particle swarm optimization algorithm, and to determine the working sequence of the sensing nodes;

[0071] The second acquisition module is used to acquire target information of all dimensions of the perceived target by utilizing the sensing nodes according to the working sequence and the optimized system deployment scheme.

[0072] The generation module is used to associate and fuse target information from all dimensions to obtain target state information.

[0073] This preferred embodiment provides a computer device that can implement the steps in any embodiment of the distributed integrated sensing method provided in this application. Therefore, it can achieve the beneficial effects of the distributed integrated sensing method provided in this application. For details, please refer to the previous embodiments, which will not be repeated here.

[0074] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. Therefore, embodiments of this application provide a storage medium storing multiple instructions that can be loaded by a processor to execute the steps of any embodiment of the distributed integrated sensing method provided in this application.

[0075] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0076] Since the instructions stored in the storage medium can execute the steps in any of the distributed integrated sensing method embodiments provided in this application, the beneficial effects that any of the distributed integrated sensing methods provided in this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0077] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A distributed integrated sensing method, characterized in that, The method is applied to a distributed integrated sensing system, which includes multiple sensing nodes, including: Based on the acquired environmental data and task requirements, determine the task boundaries of the sensing targets and the resource conditions required by the system; Based on the task boundaries and resource conditions, the system deployment scheme is optimized using the particle swarm optimization algorithm, and the working sequence of the sensing nodes is determined. The sensing nodes are used to acquire target information of all dimensions of the sensing target according to the working sequence and the optimized system deployment scheme. By associating and fusing target information from all dimensions, target state information is obtained; The target information is in a state of agile change and a state of gradual change, and the method further includes: It adopts an intermittent relay sensing method to acquire target information with rapidly changing states in the first instance; A time-division sparse observation method is adopted to acquire target information with slowly changing state using the second time, where the first time is longer than the second time. The steps of associating and fusing target information from all dimensions to obtain target state information include: The target information of state agile transformation is organized using normalization technology, and the organized target information of state agile transformation is spliced ​​together in chronological order. Extrapolate and interpolate target information whose state changes gradually; By associating and fusing the spliced ​​target information with its rapidly changing state and the extrapolated target information with its gradually changing state, the target state information is obtained.

2. The distributed integrated sensing method as described in claim 1, characterized in that, The environmental data includes physical environmental data and electromagnetic environmental data. The physical environmental data includes climate and hydrology, and the electromagnetic environmental data includes the electromagnetic signal spectrum distribution and amplitude.

3. The distributed integrated sensing method as described in claim 1, characterized in that, The target status information includes one or more of the following: target azimuth, altitude, speed, load radiation source operating frequency band, and operating mode.

4. The distributed integrated sensing method as described in claim 1, characterized in that, Methods for determining the working timing of the sensing nodes include: simultaneous search and tracking, tracking plus search, load balancing, and periodic expansion.

5. The distributed integrated sensing method as described in claim 1, characterized in that, The optimization of the system deployment plan includes: optimizing the deployment based on the location of the sensing nodes, jointly adjusting the beam parameters of the sensing nodes, and building communication links.

6. A distributed integrated sensing device, characterized in that, The device includes: The first acquisition module is used to determine the task boundary of the sensing target and the resource conditions required by the system based on the acquired environmental data and task requirements; The optimization module is used to optimize the system deployment scheme using the particle swarm optimization algorithm based on the task boundary and the resource conditions, and to determine the working sequence of the sensing nodes; The second acquisition module is used to acquire target information of all dimensions of the sensing target by using the sensing node according to the working sequence and the optimized system deployment scheme; The generation module is used to organize the target information of state agility through normalization technology, and to splice the organized target information of state agility in chronological order. Extrapolate and interpolate target information whose state changes gradually; By associating and fusing the spliced ​​target information with its rapidly changing state and the extrapolated target information with its gradually changing state, the target state information is obtained. The device is also used to acquire target information with rapidly changing state in the first moment by using an intermittent relay sensing method. A time-division sparse observation method is adopted to obtain target information with slowly changing state using a second time, where the first time is longer than the second time.

7. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program, which is loaded and executed by the processor to implement the distributed integrated sensing method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which is loaded and executed by a processor to implement the distributed integrated sensing method as described in any one of claims 1-5.

Images