112 results about "Space Network" patented technology

The invention discloses an internet constellation dynamic routing optimization method and system, and the method comprises the steps: setting orbit plane parameters and satellite parameters, and carrying out the modeling of an orbit and a constellation; performing link visualization and time-varying graph generation according to ephemeris data and the constructed constellation model; defining a related space, a network and a function based on a deep reinforcement learning algorithm; and based on an MADDPG framework, introducing a multi-agent collaborative decision-making mechanism, and outputting action selection and execution results after collaborative optimization. The system comprises a model construction module, an embedding module, a reinforcement learning design module and a collaborative optimization module. By using the method, the dynamic change of the low-orbit satellite network can be effectively dealt with, satellite resources are fully utilized, and efficient and reliable communication is realized. The method can be widely applied to the field of wireless communication.

The invention relates to a computer vision technology, in particular to an event camera target detection method based on Euclidean-hyperbolic motion perception, which comprises the following steps: down-sampling original event data, constructing an event graph by using the down-sampled data, and inputting the event graph into a double-space network for target detection; performing local perception feature extraction on the event graph by using a graph convolutional network based on a B-spline kernel function, and projecting the extracted features to a hyperbolic space; extracting global event dependency features from the local sensing features mapped to the hyperbolic space through a learnable curvature hyperbolic graph convolutional network; and decoding the global event dependency feature and inputting the decoded global event dependency feature into a sensing head, and outputting a target detection result by the sensing head. The method solves the problems of noise suppression, topological mapping and hierarchical expression in event data, has good application prospects and popularization value, and is particularly suitable for real-time target sensing tasks in complex dynamic environments such as automatic driving and robot navigation.

The invention discloses a streaming telemetry data plane forwarding method and device, and belongs to the technical field of communication. According to the method disclosed by the invention, stream telemetering is realized by processing the header of a service message through multi-level cache, and satellite nodes and paths in a spatial network are measured and monitored in a high-fineness manner; according to the method, the proportional sampling of the stream telemetering is realized through the stream classification list, so that the resource overhead of the stream telemetering is saved, and the occurrence of network congestion possibly caused by the stream telemetering is reduced; the end-to-end sending of the telemetering message is realized by pre-configuring the telemetering message output interface, and the telemetering message uploading process is simplified. Based on the streaming telemetry data plane forwarding method, the streaming telemetry data plane forwarding device comprises a service message processing subsystem which is used for service message analysis, processing and stream classification; the telemetering message processing subsystem is used for constructing and uploading a telemetering message; and the message forwarding subsystem is used for forwarding the service message and the telemetering message.

The invention is suitable for the field of communication interference monitoring, and provides a 5G millimeter wave equipment high-frequency interference monitoring method and system, and the method comprises the steps: collecting a target monitoring frequency band, dividing the target monitoring frequency band into a plurality of sub-frequency bands with the bandwidth of 20MHz, collecting the signal power spectrum density of each sub-frequency band, and calculating the signal power spectrum density of each sub-frequency band; extracting interference intensity, an interference range and a service volume parameter of a corresponding frequency band; constructing a priority ranking model and grading the interference of each sub-band; the spatial position of an interference source is positioned through multi-TRP cooperation; adjusting time slot allocation and power resources of the space-air-ground network according to an interference priority sorting result; based on an interference source positioning result and a resource allocation scheme, dynamically adjusting beam forming parameters of the phased-array antenna or switching a working frequency band; through multi-dimensional parameter acquisition and priority modeling, the influence of interference on different services is accurately quantified, so that interference processing better meets actual requirements; the space-air-ground cooperation and multi-TRP positioning technology provides a reliable basis for interference treatment.

The invention provides a routing fast convergence method for next hop separation of a spatial network, and belongs to the technical field of communication. The method comprises the following steps: firstly, establishing a next hop group for a spatial network, distributing an array index for all possible next hop outbound interface combinations, and storing a next hop IP address and outbound interfaces in an array; and then the routing table entries are bound to the corresponding next hop groups, and a plurality of routing table entries pointing to the same next hop outbound interface share the same index. When the states of links, nodes and the like change, the routing table only needs to update the corresponding index or the next hop information corresponding to the index, and does not need to traverse each routing table item to modify the next hop and an outbound interface, so that rapid routing convergence is realized. According to the method, the routing storage resource consumption can be reduced, and the routing convergence rate is greatly improved.

The invention relates to the technical field of satellite-borne edge computing and simulation, and provides a satellite-borne edge computing task unloading semi-physical simulation system. Comprising a physical satellite-borne edge computing device, a software virtual satellite-borne edge computing device, a ground user device, a space environment simulator, a container and cloud management base, a resource data distribution module and a task unloading scheduling module. The physical satellite-borne edge computing device and the software virtual satellite-borne edge computing device jointly construct a cloud side end cooperative computing cluster, the ground user device is used for initiating a computing task request, the space environment simulator is used for simulating spatial network characteristics, and the container and the cloud management base are used for achieving all-node unified management and control. The resource data distribution module is used for issuing and subscribing node resources and environment information, and the task unloading scheduling module is used for executing a task unloading decision. The problems that in the prior art, on-orbit verification cost is high, a pure software simulation environment is distorted, algorithm credibility is insufficient, and a satellite-borne data set is scarce are solved.

A method for measuring disaster resilience of urban public services includes the following steps: constructing a residence-service-transportation space network under normal conditions; removing, through disaster simulation, failed road segments and function nodes to construct a damaged residence-service-transportation space network; calculating a per capita accessible public service of each residential node to represent network performance; calculating a change rate of the per capita accessible public service level before and after the disaster; and drawing a relation curve between the change rate and the disaster intensity to measure the disaster resilience of the urban public services.

The invention relates to a deep learning-based structure anti-seismic performance evaluation system, which comprises a data acquisition module, a data preprocessing module, a feature extraction module, a numerical simulation module, a deep learning model training module, an evaluation and verification module, a visualization module and a model updating and maintenance module, the data preprocessing module is used for data preprocessing, the feature extraction module is used for data feature extraction, the numerical simulation module is used for simulating seismic response of a structure, the deep learning model training module is used for constructing a deep learning model, the evaluation and verification module is used for model evaluation and verification, and the visualization module is used for evaluation result display. And the model updating and maintaining module is used for updating and maintaining the model. According to the invention, an improved seismic data feature fusion extraction algorithm is proposed for feature extraction, an improved seismic perception depth state space network is proposed for model construction, and a better scheme is provided for a deep learning-based structure seismic performance evaluation system.

The invention provides a wind power plant inspection system and method based on cooperation of an unmanned aerial vehicle group, and the system enables the inspection tasks to be carried out in parallel through the cooperation of the unmanned aerial vehicle group, thereby improving the inspection efficiency. Meanwhile, the three-dimensional space network and the task allocation algorithm are applied, so that the planning of the inspection path is more accurate and reasonable, and the inspection cost is reduced; in addition, compared with manual inspection, unmanned aerial vehicle inspection has higher safety, and risks of personnel in high-altitude operation are avoided; finally, through cooperation of the unmanned aerial vehicle groups, the inspection coverage range is expanded, the inspection period is shortened, the operation state of the wind power plant can be monitored and analyzed in time, and the defects that in the wind power plant inspection process, the inspection efficiency is low, the detection coverage is incomplete, and the environmental adaptability is poor are overcome.

The invention discloses a multi-connection management method suitable for a high-orbit and low-orbit fusion satellite communication terminal, and the method comprises the steps: building a communication connection with a high-orbit satellite, and obtaining the ephemeris information of a low-orbit satellite; a visible time window of the target low earth orbit satellite is predicted, and the composite link quality at the future moment is dynamically evaluated; performing look-ahead multi-connection state management based on the visible time window and the composite link quality; wherein the multi-connection state management comprises a preparation state of triggering antenna pre-pointing before a target low-orbit satellite is visible, and a transition state of triggering high-orbit and low-orbit double-link simultaneous transmission before low-orbit satellite coverage is finished. According to the method, the defect that a communication blind area exists in the link handover period of traditional passive response type switching is overcome, the cross-track link is firstly established and then broken, and the continuity and high reliability of service data transmission in a complex space network are effectively guaranteed.

The present application relates to a kind of based on heat-power collaborative perception's crystallizer sticking breakout intelligent prediction method, belong to continuous casting safety monitoring and intelligent manufacturing technical field.It includes: in the matrix arrangement MEMS thermal sensor array on crystallizer copper plate, copper plate local temperature and heat flux density are synchronously detected online;Online detection crystallizer friction force;Single time network model and group space network model are constructed, and thermal quantity dynamic characteristic and space propagation characteristic are extracted;Thermal quantity neural network model is constructed to the mode recognition of characteristic waveform;Friction force signal is decomposed by empirical mode, and trend quantity change characteristic is extracted;Friction force neural network prediction model is constructed, and abnormal state is identified by forecast deviation;Steel grade composition crack sensitive index and other auxiliary judgment index are calculated;Finally, through the weighted score and the multi-source information fusion decision maker of dynamic threshold correction output sticking breakout prediction grade.

The application discloses a congestion-aware routing method for a deep space network. In order to solve the problem of redundant inter-satellite forwarding and transmission efficiency reduction caused by the lack of remote link queue state awareness in a distributed long-delay deep space network, an exogenous mapping load element is maintained for each contact at each node. When the node perceives the loop risk caused by inconsistent queue states through the quasi-loop data packet, the delay increment interval of unknown remote traffic is solved by using the locally known routing information without explicit information exchange, and the exogenous mapping load is updated accordingly. Then, the load is mapped to the subsequent route estimation time cost calculation as an available capacity penalty term, so as to actively suppress the selection of contacts with potential congestion risk in the forward routing stage. The application can improve the remote traffic awareness capability of the long-delay distributed network, reduce the redundant inter-satellite relay, and improve the end-to-end transmission efficiency and reliability of the deep space network without increasing the signaling overhead.

This application discloses a training method, apparatus, device, and storage medium for a joint angle prediction model, relating to the field of computer technology. The method includes: acquiring training sample data, which includes skeletal parameters, sample wrist joint pose sequences, and arm angle labels for the sample wrist joint pose sequences; obtaining arm angle feature information based on the sample wrist joint pose sequences using a selective state-space network of the joint angle prediction model to be trained; obtaining elbow position prediction information based on the arm angle feature information and skeletal parameters using a differentiable kinematic layer of the joint angle prediction model to be trained; and iteratively updating and training the joint angle prediction model to be trained based on a preset objective function, the training sample data, the arm angle feature information, and the elbow position prediction information to obtain a trained joint angle prediction model.

The application discloses a space network networking method and device, a network resource arrangement platform and a storage medium. The method comprises the following steps: in the case that a UAV service accesses a network, the position of the UAV performing the UAV service is determined; the service score corresponding to the cell within the preset distance range from the position of the UAV is determined; the preset number of cells with the highest service score are determined as the space candidate working cells, and the number of adjustable beams of the space candidate working cells is determined; and the space-to-air beam and the ground-to-air beam of the space candidate working cells are determined and set according to the number of adjustable beams. The application solves the technical problems that the UAV space coverage scheme in the related art mostly needs to add equipment for transmission transformation, the cost is too high, the scheme of covering the space by directly using the existing site resources has too great influence on the ground coverage, and the beam resources for covering the space are wasted.

The application discloses a self-iteration-based deep subspace training method and device, which comprises the following steps: a pre-training step, in which a first optimization function is minimized to train a deep subspace network, so as to initialize a similarity matrix; a training step, in which when the iteration number t is less than a first iteration number, a self-expression coefficient matrix is fixed, the second iteration number is iterated, the deep subspace network parameters are updated by minimizing a second optimization function; the deep subspace network parameters are fixed, the third iteration number is iterated, the self-expression coefficient matrix is updated by minimizing a third optimization function, the similarity matrix generated in the tth iteration is updated according to the updated self-expression coefficient matrix, and finally the update of the similarity matrix in the first t iterations is realized; and the iteration number t is increased by 1, and the training step is repeated. The application introduces the idea of self-iteration, supervises the training of the model through the results of the previous training, and can discard the previous training results, so that the memory and the calculation resources are saved.

The embodiment of the invention provides a hypoxia risk spatio-temporal distribution prediction method and device, equipment and a medium, and belongs to the technical field of safety monitoring. The method comprises the following steps: collecting geographic coordinates, low-oxygen threshold values and real-time oxygen contents of all monitoring nodes in a region; calculating an edge generation index based on the node coordinates and a threshold value, and if the index is lower than a preset value, connecting the two nodes (regarded as similar oxygen change trends) to form a node network; the connected nodes are clustered into monitoring sets, and the number of low-oxygen nodes (the nodes with the oxygen content lower than the threshold mean value of all the nodes) in each set is counted; the oxygen growth rate of each node is calculated, and a hypoxia condition prediction index of the set is generated by combining the number of hypoxia nodes in the set, the total number of nodes, the average growth rate and the average oxygen content; and finally, plotting a set area of which the prediction index exceeds a threshold value on the map as a hypoxia risk area. According to the method, the low-oxygen high-risk area is identified and drawn based on the spatial network and set division and comprehensive indexes, and accurate prediction of the low-oxygen area is realized.

The invention discloses an autonomous positioning method and terminal equipment, and the method comprises the steps: obtaining a first observation position of a mobile body in a world coordinate system at a current moment, the first observation position being determined according to a positioning signal of a positioning sensor of the mobile body at the current moment; matching the first observation position with local road information in a road network map to obtain a target road point where the mobile subject is currently located, the target road point being a projection point of the first observation position in the road network map; calculating road network observation noise at the current moment by taking the position of the target road point as road network observation quantity according to the spatial network attribute information of the target road point; and according to the road network observation noise, determining an estimated position of the mobile body in the world coordinate system at the current moment so as to update the state of the mobile body according to the estimated position.

The invention discloses an unsupervised anomaly detection method for an aviation composite material hole wall, and relates to the technical field of aviation composite material processing detection, and the method comprises the steps: carrying out the fusion of public texture data and a gray-scale map of a hole wall through an anomaly mask to construct an anomaly training sample, and carrying out the manual annotation, in addition, the Mama state space model is introduced into the anomaly detection field to construct a visual state space network model of a Unet structure, and the difference between a prediction mask generated by the visual state space network model and an anomaly mask is evaluated to obtain a loss function which can be used for training the model; by means of the method, under the condition that defect data does not need to be marked, CFRP complex fiber textures and unknown defect types can be effectively handled, and the accuracy of detection is improved. And an efficient and accurate solution with a wide application prospect is provided for automatic detection of the inner wall defects of the aviation composite hole.

In one embodiment, a method is disclosed, comprising: receiving a packet; processing the packet in a Control Unit–User Plane (CU-UP) as a user-space application with kernel-bypass networking; performing packet Input / Output (I / O) by the CU-UP user-space application, wherein the CU-UP performs Internet Protocol (IP) validation on received user-plane packets before processing Packet Data Convergence Protocol (PDCP), Service Data Adaptation Protocol (SDAP) and General Packet Radio Service Tunnelling Protocol (GTPU) protocol stack and performing direct I / O to a Network Interface Controller (NIC) for sending the packet over a network to a Distributed Unit (DU). The method may further comprise using a containerized CU-UP. The method may further comprise using a plurality of worker threads. The method may further comprise using a polling user space networking accelerator framework.

The present application relates to the technical field of data transmission management, and more particularly to a data flow circulation method across data spaces, which determines a plurality of data flow circulation spaces by acquiring node parameters of adjacent device nodes on a data transmission path, determines data flow circulation characteristic time periods by determining a plurality of circulation state explicit nodes on traffic variation curves of different data flow circulation spaces, determines whether there is an invalid circulation phenomenon by performing continuity analysis on the data flow circulation characteristic time periods determined according to a first constraint condition, and determines whether to transmit data of the space network cache node to a target device node having an interface mapping relationship according to a second constraint condition by setting a space network cache node between adjacent device nodes. The present application performs associated recognition analysis on the data flow circulation states of adjacent nodes across data spaces, thereby avoiding waste of data flow circulation resources caused by redundant transmission, response delay and other problems.

The application discloses a UE dedicated dynamic resource pool communication method and system based on a dynamic security root. The method establishes a dedicated dynamic resource pool for each user equipment, and provides a logically independent resource index space. The network side and the user equipment calculate the same pool index at a logical time based on a sharing rule, and are mapped to physical resources and time through a predetermined method. When the user moves, the network side dynamically updates the mapping relationship, adds new coverage resources to the pool, and removes resources away from the pool without switching signaling. The dedicated pools of multiple UEs are allowed to overlap in physical resources, and conflicts are solved by two-step deterministic arbitration. The application realizes complete decoupling of the UE and the physical network, eliminates switching, requires zero signaling, and allows the UE to move without feeling, and can be widely applied to the fields of 6G, satellite internet, industrial internet and the like.

The invention relates to the technical field of unmanned aerial vehicles, in particular to a meshing method and system based on flight trajectory data of an unmanned aerial vehicle, and the method comprises the following steps: constructing a spatial network subdivision and coding system based on the operation characteristics of the unmanned aerial vehicle, and obtaining a target geographic region corresponding to a target airspace; dividing the target geographic area according to a target space grid level, and generating an initial space grid list corresponding to the target geographic area; generating a target space grid list corresponding to a target airspace according to the initial space grid list and historical flight path data of a target unmanned aerial vehicle; therefore, differentiated rasterization processing is carried out on the airspace according to the flight activity density of the unmanned aerial vehicle, and the problem that the unmanned aerial vehicle flight activity dense area and the unmanned aerial vehicle flight activity sparse area both adopt airspace grids of the same size, and great inconvenience is brought to unmanned aerial vehicle flight activity management under dense flight activities is solved.

The present invention discloses a spacecraft navigation method based on a combination of pulsars and deep space network, which mainly solves the problem that existing technologies are difficult to meet the real-time requirements of complex tasks and have limited coverage capabilities. It includes: establishing a navigation system state model of the spacecraft based on the orbital dynamics equation; using an X-ray detector to obtain the time when the photon arrives at the spacecraft and convert it to the SSB, and establishing a photon arrival phase measurement equation based on the relationship between the photon arrival SSB phase and the spacecraft state; using the deep space network ground station to receive spacecraft signals, and establishing a time difference and Doppler frequency shift measurement equation based on the time collected by multiple ground stations and the frequency information of a single ground station; integrating the data of pulsars and deep space network, and using extended Kalman filtering to calculate the estimated vector of the spacecraft state. The present invention effectively improves the continuity and accuracy of navigation, while enhancing system performance, so that spacecraft can obtain more stable navigation support in complex environments.

The application relates to the technical field of DQN algorithm, in particular to a mobile robot path planning method based on DM-DQN, which comprises the following steps: a mobile robot path planning model based on DM-DQN is established; a state space, an action space, a DM-DQN network model and a reward function of the DM-DQN algorithm are designed; the DM-DQN algorithm is trained to obtain an experienced reward value, and collision-free path planning of a robot is completed. The application introduces a competitive network structure, decomposes the network structure into a value function and an advantage function, thereby decoupling action selection and action evaluation, so that the state is no longer completely dependent on the value of the action for judgment, individual value prediction can be carried out, and the problem of slow convergence speed is solved; and through the design of a reward function based on an artificial potential field, the problem that the robot is too close to the edge of an obstacle is solved.

Systems and techniques for optimizing utilization of hostlers of a hub based on a dual-stream resource optimization (DSRO). In embodiments, a dual-stream optimization model is utilized, incorporating a consolidated time-space network and a deconsolidated time-space network spanning a planning horizon. The model identifies hostler operations and pairs them based on proximity criteria, forming operation pairs that lead to higher unit throughput within the hub. An optimized hostler operation schedule is generated for implementation during the planning horizon. The system also includes a feature for automatically transmitting a control signal to a hostler control system to direct a hostler to execute the paired operations in accordance with the pairing.

The invention provides an observation station system error correction method and system, computer equipment and a storage medium, and belongs to the field of spaceflight measurement and control, and the method comprises the steps: respectively obtaining observation matrixes of a laser ranging station SLR and a deep space network observation station, building observation equations of laser ranging and deep space network ranging and speed measurement, building an orbital motion equation for a satellite, and obtaining an orbital motion equation; superposing the SLR observation equation, the UXB observation equation and the orbital motion equation according to weights to construct a normal equation set; calculating theoretical prediction matrixes of the SLR and a deep space network observation station by combining an orbital motion equation, the SLR and an observation equation of the deep space network, calculating respective residual matrixes according to the difference between the prediction matrixes and the observation matrixes, and solving to-be-estimated parameter correction of an equation set by using a least square method; and comparing the orbit correction with a threshold value, obtaining a final to-be-estimated parameter correction through multiple iterations, and calibrating and compensating the measurement process of the deep space network tracking station by using the to-be-estimated parameter correction, thereby improving the satellite orbit determination precision.

The invention relates to the technical field of space network communication and satellite intelligent management, in particular to an LEO satellite network intelligent routing system and method based on intention recognition. Comprising a natural language instruction input module, a text preprocessing module, a BERT semantic modeling module for RoPE position coding enhancement, a bidirectional LSTM context enhancement module, an intention recognition module, an entity recognition module, a structured result generation module and an interface interaction module. According to the method, a path request instruction in a natural language form is mapped into a structured scheduling parameter, the problems that a parameter configuration process in a traditional satellite scheduling system depends on manpower, the response timeliness is poor and the analysis capability is weak are solved, meanwhile, rotation position coding is introduced to improve the sequence structure sensing capability, and local context features are captured in combination with BiLSTM, so that the real-time performance of the satellite scheduling system is improved. Through intention recognition and entity recognition dual-task joint modeling, high-precision output of a structured request analysis result is realized, and key support is provided for satellite network intelligent scheduling.

The invention discloses a cloud platform system based on edge computing and an edge computing implementation method. The system comprises an edge computing node, a multi-source heterogeneous fusion gateway connected with the edge computing node, an intelligent scheduling module connected with the multi-source heterogeneous fusion gateway, and a central cloud server. The edge computing node unifies the file format and the file coding mode of the computing data of the terminal equipment, so that the forwarding efficiency is improved; the multi-source heterogeneous fusion gateway pre-processes the preliminarily pre-processed data again, so that the storage space and the network bandwidth occupied by the preliminarily pre-processed data are reduced; and the intelligent scheduling module determines execution equipment of the calculation task according to the standard data type and the processing requirement related to the calculation task included in the scheduling instruction, the resource occupation condition of the edge calculation node and the central cloud server, and the network condition of the edge calculation node and the central cloud server. And the occupation condition of the storage space, the complex condition of the scheduling task and the occupation condition of the network bandwidth are reduced.

The embodiment of the invention discloses a COE interconnection simulation method and system based on a DPDK and a full user mode protocol stack and a medium. Constructing a user state simulation environment comprising a DPDK driver and a full-user state network protocol stack on at least two network interconnected nodes; encapsulating a memory access request of the CXL protocol into frame data conforming to a predetermined format, and adding network layer and transport layer protocol headers through a full-user-state network protocol stack to form an Ethernet data frame; the Ethernet data frame is submitted to a physical network card for sending through a DPDK interface; receiving an Ethernet data frame from a physical network card through a DPDK interface, stripping protocol heads of a network layer and a transport layer by a full-user-state network protocol stack, and de-encapsulating to obtain CXL protocol data; and performing response processing according to the decapsulated CXL protocol data, generating confirmation information when needed, and sending the confirmation information to an opposite-end node through a full-user-state network protocol stack and a DPDK interface.