403 results about "Swarm control" patented technology

The invention relates to the technical field of unmanned aerial vehicle cluster control, and particularly discloses an intelligent cooperative flight path planning method and system for an unmanned aerial vehicle cluster system, and the method comprises the steps: firstly constructing a dynamic environment perception model, collecting data through all unmanned aerial vehicle sensors, and carrying out the preprocessing, attention feature extraction and federal learning fusion, and generating a global environment situation map; planning and screening a candidate track set by adopting a particle swarm-genetic hybrid optimization algorithm for adaptive weight adjustment on the basis of the image; a global optimal track consensus is achieved through an improved consensus algorithm and conflict resolution through a distributed collaborative negotiation mechanism and no human-computer interaction evaluation indexes; and finally, monitoring the environment in real time during execution, triggering dynamic re-planning when the environment is abnormal, and ensuring track adaptation through multi-level threshold and incremental planning. According to the method, the unmanned aerial vehicle cluster can quickly respond to the environment change and adjust the flight path, so that the task execution efficiency and success rate of the unmanned aerial vehicle cluster in the complex dynamic environment are improved.

The invention discloses a target intelligent cooperative identification method based on an unmanned aerial vehicle cluster, and belongs to the field of unmanned aerial vehicle cluster control and computer vision. According to the method, cluster networking and model initialization are realized through a dynamic heterogeneous federated learning architecture; a space-time attention mechanism is adopted to optimize task allocation, and a deformable network is utilized to extract multi-view target features; a cascade characteristic distillation fusion strategy is provided, and modal compression and cross-modal gating fusion are carried out on multi-source data such as multispectral data and laser radar data; an anti-interference elastic communication mechanism based on meta-learning is designed, and the system robustness is enhanced by combining space-time confrontation detection and a dynamic spectrum sensing technology; an unsupervised federal incremental learning system is established, and online evolution of the model is realized through momentum weighted aggregation. According to the method, the target identification accuracy is improved by 35% in a complex environment, the time delay is reduced to 200 ms, and high-precision real-time identification support is provided for military reconnaissance, disaster rescue and other scenes.

The invention discloses a hierarchical multi-agent robot cluster control method and system, and aims to solve the problems of partial observability and environment non-stability of a multi-agent system in a complex environment. According to the method, a three-layer layered reinforcement learning architecture is constructed, a high-layer strategy is responsible for global task decomposition and role allocation, a middle-layer strategy converts tactical intention into a cooperative behavior mode, and a low-layer strategy executes accurate motion control; a graph neural network is adopted for cluster modeling, global graph representation and local neighborhood features are extracted in parallel through graph convolution and an attention mechanism, and hierarchical decision making is supported; a centralized graph enhancement evaluation network is designed to be combined with an MAPPO algorithm for collaborative optimization, and dynamic adversarial training is introduced to improve strategy robustness. According to the method, effective decoupling of global planning and local control is realized, and the cluster cooperation efficiency, the strategy interpretability and the adaptive capacity in a dynamic environment are improved.

The invention relates to the technical field of unmanned aerial vehicle cluster control, in particular to an unmanned aerial vehicle cluster control method and system, and the method comprises the steps: predicting the remaining flight time of an unmanned aerial vehicle cluster for safely arriving at a destination in a current carrying state; calculating a cluster energy consumption deviation degree according to the current energy consumption parameter, predicting the remaining endurance time of each unmanned aerial vehicle, and determining the minimum predicted endurance time; dynamically generating a safe flight time threshold according to the minimum predicted endurance time and a preset safety margin; if the remaining flight time is smaller than the safe flight time threshold value, a cooperative control instruction is generated according to the offset, the offset speed and the cluster energy consumption deviation degree; and distributing the cooperative control instruction to the corresponding unmanned aerial vehicle in the unmanned aerial vehicle cluster. And the flight endurance crisis caused by non-uniform energy consumption in the irregular article carrying process is effectively solved.

The invention discloses a multi-target bridge unmanned aerial vehicle inspection path optimization method and system, and relates to the technical field of crossing of bridge operation and maintenance and unmanned aerial vehicle cluster control. The method comprises the following steps: constructing a bridge three-dimensional point cloud model, extracting key inspection points, and establishing a multi-objective optimization function including path length, time consumption, coverage rate, risk coefficient, cluster safety and formation retention; a multi-target reward mechanism is fused through a double-delay depth deterministic strategy gradient network, and a deep learning model is constructed and used for generating an unmanned aerial vehicle cluster obstacle avoidance strategy; training a deep learning model; and based on real-time data, performing multi-target bridge unmanned aerial vehicle routing inspection path optimization by using the trained deep learning model, and adjusting a weight coefficient of a multi-target optimization function through an attention network dynamic weight distribution technology in the optimization process. According to the invention, multi-objective optimization of routing inspection safety, efficiency, quality and cluster cooperation is realized, and the method is suitable for automatic routing inspection of various complex steel structure bridges.

The invention discloses a hybrid attack defense control method and system for a heterogeneous cluster in an urban confrontation environment, terminal equipment and a medium, and relates to the technical field of unmanned platform cluster control, and the method comprises the steps: constructing an ideal system model of an unmanned platform cluster comprising a leader and a plurality of followers, constructing an information physical hybrid attack model based on the model; using the attack model to simulate an attack behavior of an attacker on an ideal system to obtain an attacked system model; based on an attacked system model, constructing a distributed elastic security estimator with a compensation mechanism, compensating attack influence for each follower and estimating an expected position; and based on the expected position of the follower, constructing a distributed elastic safety controller with a compensation mechanism, and controlling the follower. By designing the estimator and the controller, attack interference is counteracted, control input is generated, and safe collaboration of the heterogeneous nonlinear unmanned cluster under the cyber-physical hybrid attack is guaranteed.

The invention discloses an unmanned autonomous cluster flight control method based on a bionic alert mechanism, which is applied to the field of unmanned autonomous cluster control, and is characterized in that a W-MSR algorithm and a dynamic weighted bionic alert mechanism are fused, the W-MSR filters and eliminates extreme values of neighbor individuals, the dynamic weighted bionic alert mechanism strengthens input from informed individuals, and the dynamic weighted bionic alert mechanism is used for improving the robustness of the unmanned autonomous cluster flight control. And meanwhile, the influence of suspicious individuals is inhibited, so that the local information aggregation degree is effectively improved, and group splitting can be prevented. Different from a scheme depending on explicit attacker recognition, the method can improve the motion accuracy and connectivity of the unmanned autonomous cluster in a confrontation environment by probabilistically suppressing the influence of suspicious individuals and amplifying a consistent signal, provides a new idea for improving the security of a swarm intelligence system, and has a wide application prospect. Damage of malicious individuals to the cluster is effectively defended, and robustness and recovery capability of the cluster in a complex environment are improved.

The invention relates to the technical field of intelligent power distribution network control, in particular to a variable grid group control optimization method, system and device based on cloud edge collaboration and a medium. Collecting real-time operation data of the distributed resources and performing state information processing to generate structured state information reflecting a relationship between a physical state and a network structure; the topological similarity and the operation characteristic difference degree are integrated through a clustering algorithm, self-adaptive division is conducted on the structured state information, and a plurality of variable grid groups and topological boundary information are generated; taking each variable grid group as an independent game main body, and combining a revenue function and a constraint condition to construct an initial strategy set of each variable grid group; performing multiple rounds of game interaction and income evaluation through a game algorithm to obtain an optimal variable grid group strategy; edge-side collaborative scheduling and resource allocation are carried out based on the optimal strategy, and an edge control result is obtained; an edge control result is fed back to the cloud for global coordination and integration, and a consistency strategy is generated, issued and executed.

The invention discloses a hydro-junction gate group intelligent cooperative control method based on digital twinning, and relates to the technical field of water conservancy control, and the method comprises the steps: taking a water conservancy dynamic digital twinning model as a reinforcement learning environment, setting gate group control parameters and performance indexes, carrying out the training under diversified hydrological conditions, and generating a preliminary control strategy; inputting the preliminary control strategy into a water conservancy dynamic digital twinborn model, executing rollback simulation covering multiple working conditions, and obtaining simulation responses of the corresponding working conditions; scheduling performance indexes of simulation response are analyzed, high-quality control strategies are screened, scheduling conflict identification and conflict resolution among gate groups are carried out, and an optimal control strategy set is output; according to the method, by executing rollback simulation covering multiple working conditions and automatically identifying and eliminating scheduling conflicts among gate groups, the adaptability and accuracy of a scheduling strategy are improved, conflicts and risks are reduced, and efficient and safe operation of the hydro-junction is ensured.

The invention relates to the technical field of unmanned aerial vehicle cluster control, in particular to a multi-mode sensing fusion unmanned aerial vehicle cluster control method, device and equipment based on deep learning and a storage medium. According to the invention, gesture, voice, vision and touch data are collected in parallel through a multi-mode perception access layer and are preprocessed and synchronized; utilizing a special deep network to extract high-level features rich in cluster semantics; through cross-modal semantic alignment, graph neural network association learning and a multi-dimensional conflict detection and intelligent resolution mechanism, deep fusion and accurate intention analysis of four modals in a cluster control semantic space are realized; high-level instructions are efficiently converted into single-machine executable tasks and coordination strategies by adopting hierarchical task decomposition, virtual structure formation control and a multi-objective optimization algorithm; state feedback and adaptive parameter optimization are carried out in real time, and the accuracy, reliability, environmental adaptability and man-machine interaction efficiency of large-scale unmanned aerial vehicle cluster control are improved.

The invention discloses a reinforcement learning-based cluster spacecraft multi-target intelligent cooperative tracking method. The method comprises the steps of establishing a relative motion relationship between a tracking spacecraft and a target spacecraft through a nonlinear orbit kinetic equation; designing a double-layer game framework, constructing a non-zero sum game in the cluster to drive cooperation, and introducing a zero and maximum and minimum game between the cluster and a target to describe a confrontation relationship; based on communication topology and relative state information, defining a local error term and a performance index function of the tracking spacecraft and the target spacecraft, and defining an optimization target of each agent under cooperation and confrontation; and iteratively updating the value function and the control law. According to the invention, collaborative tracking can be realized without defining a system model. The method can be widely applied to the field of cluster control.

The invention discloses a robot cluster cooperative control method and device based on indoor positioning and virtual-real fusion simulation, equipment and a medium, and relates to the technical field of robot cluster control, and the method comprises the steps: building a unified coordinate system through arranging a plurality of optical dynamic capture cameras indoors, obtaining the three-dimensional space coordinates and attitude information of a target object, and obtaining the three-dimensional space coordinates and attitude information of the target object; based on the data, data fusion display synchronized with the actual environment is realized in the virtual simulation environment. And then, a cluster control algorithm is utilized to generate a cooperative control instruction, and the cooperative control instruction is sent to the robot cluster through wireless communication to execute a specific task, so that high-precision positioning of the robot cluster is realized, and the task execution efficiency and cooperative control capability of the robot cluster in an indoor environment are greatly improved.

The invention relates to the technical field of unmanned aerial vehicle cluster control and intelligent scheduling, and discloses an industrial unmanned aerial vehicle cluster intelligent scheduling management method based on multi-data analysis, and the method comprises the steps: extracting a quantitative risk feature vector based on multi-source operation data; constructing and updating a four-dimensional dynamic risk field; constructing a rolling time domain optimization model to generate a cooperative scheduling scheme including adaptive formation adjustment; decomposing and issuing a scheduling instruction; and carrying out dynamic risk field updating based on the real-time returned data, and triggering the compensatory adjustment. According to the method, real-time sensing and quantitative evaluation of multi-source and dynamic risks in a complex industrial environment can be realized, flight safety and task efficiency are dynamically balanced through rolling optimization and an elastic compensation mechanism, and robustness and intelligence of overall operation of a cluster are improved.

The invention belongs to the technical field of mobile communication, and relates to an unmanned aerial vehicle group formation control method in a forest fire scene, which comprises the following steps: constructing system models including an unmanned aerial vehicle formation model and a forest fire environment model; according to the unmanned aerial vehicle formation model and the forest fire environment model, constructing an optimization problem by taking minimization of an unmanned aerial vehicle formation total error as a target; the optimization problem is converted into a Markov decision process, the optimization problem is solved by adopting a multi-agent reinforcement learning algorithm based on the Markov decision process, and a formation control strategy for the unmanned aerial vehicle group is obtained; according to the method, the unmanned aerial vehicle group formation model and the forest fire environment model are constructed by comprehensively considering stroke, smoke, fire spreading and fireman positions in the forest fire scene, the optimization problem is constructed according to the models, and the target function of the optimization problem considers the position, speed, attitude and monitoring area total error of the unmanned aerial vehicle. Therefore, the method adapts to the actual environment condition of forest fire, and the unmanned aerial vehicle group formation can be controlled more efficiently.

The invention provides an energy consumption balance scheduling system and method for a low-altitude unmanned aerial vehicle group, and relates to the technical field of low-altitude unmanned aerial vehicle group control, and the system comprises an unmanned aerial vehicle state sensing module which collects the flight state information of each unmanned aerial vehicle in real time; the task information acquisition module is used for acquiring task position information and task time information; the energy consumption balance scheduling algorithm module is used for determining a flight task and a flight path of each unmanned aerial vehicle based on the flight state information, the task position information and the task time information of each unmanned aerial vehicle; and the flight control module is used for scheduling each unmanned aerial vehicle based on the flight task and the flight path of each unmanned aerial vehicle. According to the system and the method provided by the invention, the state information of the unmanned aerial vehicles is analyzed, task distribution and flight path planning are carried out in combination with the task information, the tasks are reasonably distributed, and the flight path is planned, so that the energy consumption balance scheduling of the low-altitude unmanned aerial vehicle group is realized, and the cruising ability and the task execution efficiency of the unmanned aerial vehicle group are improved.

The invention provides an intelligent network connection device remote cluster control method and system based on vehicle-road cooperation, and relates to the technical field of intelligent traffic, and the method comprises the steps: obtaining vehicle end state information and road side sensing information, carrying out the cross-domain fusion based on a vehicle-road space-time alignment rule to obtain a global view, grouping vehicle end devices according to the road segment attribution and task association degree, and carrying out the clustering of the vehicle end devices; and generating a hierarchical control instruction according to the grouping structure and the global view, executing remote control, and adaptively adjusting an alignment rule by using feedback information. According to the invention, the accurate control of the equipment cluster in the vehicle-road cooperation environment is realized, and the operation efficiency and safety of the vehicle-road cooperation system are improved.

The invention discloses a multi-blade large-size cutterhead wear prediction and early warning method and device and a medium, and relates to the technical field of machine manufacturing and control, and the method comprises the steps: S1, multi-source heterogeneous data synchronous collection and feature fusion; s2, constructing a single blade wear-life collaborative prediction model; s3, carrying out multi-blade collaborative wear distribution modeling and dynamic compensation; and S4, online adaptive learning and prediction robustness enhancement are carried out. According to the method, the multi-blade prediction model is deduced through single-blade modeling, model comparison verification is combined, the abrasion trend is automatically recognized, the service life of the tool is accurately predicted, the tool utilization rate can be effectively increased, the machining cost can be effectively reduced, and reliable technical support is provided for efficient machining of large machine tool cluster control.

Disclosed in the present invention is a construction system for a big data analysis algorithm library, comprising: an analysis process construction module, an operator platform selection module, a code reverse generation module, a user code verification module, a cluster control host, and a cluster computing host. Cross-platform and cross-language algorithm fusion can be realized, and data analysis is realized in a complete and heterogeneous data analysis flow. Also disclosed in the present invention is a construction method for a big data analysis algorithm library.

An unmanned surface vehicle cluster formation control algorithm based on a network topology structure belongs to the technical field of unmanned surface vehicle control, and the core of the algorithm comprises a network topology structure construction module which is used for automatically adjusting the network topology structure according to the task target and number of an unmanned surface vehicle cluster and the current marine environment condition; the communication protocol optimization module is used for guaranteeing the communication reliability between the unmanned ships; the formation control algorithm core module is used for realizing accurate formation control of the unmanned ship cluster; in addition, a fault processing and self-adaptive adjusting mechanism is further arranged. According to the unmanned ship cluster formation control algorithm based on the network topology structure, an innovative solution is provided for solving the problems of unstable communication, poor formation flexibility, low operation efficiency in a complex marine environment and the like existing in current unmanned ship cluster control; the adaptability, the reliability and the collaborative operation efficiency of the unmanned ship cluster in a complex marine environment can be comprehensively improved, and a new path is opened up for intelligent control of the unmanned ship cluster.

The invention provides a micro-nano robot cluster navigation obstacle avoidance method and system based on deep reinforcement learning, and the method comprises the steps: enabling a model to have a powerful migration capability from virtuality to reality through a multi-level domain randomization training cluster control strategy; a visual detection module is used for obtaining position information of a micro-nano robot cluster and obstacles in the environment in real time, and a Transformer strategy network of a causal self-attention mechanism including observation vectors of relative states of a target, the cluster and the obstacles and historical information input integration time expansion is constructed; and the problem of long time sequence dependence in part of observable environments can be solved. And outputting a speed control instruction for driving the cluster to move through a near-end strategy optimization algorithm, and mapping the speed control instruction into a physical parameter of an external driving magnetic field to realize closed-loop control of the cluster. After simulation training, the control strategy can be directly migrated to a physical system, fine tuning is not needed, and precise and robust complex tasks such as autonomous navigation, dynamic obstacle avoidance and target tracking are achieved.

The invention belongs to the technical field of intelligent power grids, and particularly relates to a large-scale variable frequency air conditioner aggregation control method and device. The method comprises the steps that variable frequency air conditioners in a to-be-evaluated time period are clustered, and a plurality of target variable frequency air conditioner clusters are obtained; the temperature adjustable margin of the target variable frequency air conditioner cluster is determined; based on the temperature adjustable margin of the target variable frequency air conditioner cluster, determining the load aggregation power adjustable margin of the large-scale variable frequency air conditioner in the to-be-evaluated time period by using a pre-established large-scale variable frequency air conditioner aggregation response potential evaluation model; and based on the time sequence large-scale variable frequency air conditioner load aggregation power adjustable margin of the time period to be evaluated, the variable frequency air conditioner cluster control strategy is used for conducting temperature control on the target variable frequency air conditioner cluster. According to the technical scheme, the temperature of the large-scale variable frequency air conditioner is accurately controlled, the temperature control efficiency of the large-scale variable frequency air conditioner is improved, and the quality of demand response is improved.

The invention provides a photovoltaic cleaning robot multi-machine task scheduling and collaborative operation method and system, electronic equipment and a storage medium, and relates to the technical field of multi-machine task scheduling and collaborative operation, and the method comprises the steps: obtaining the position and speed information of each robot in a robot cluster, and constructing a dynamic adjacency graph model; controlling each robot to interact information through an ad hoc network communication relay node by using a time division multiple access protocol, controlling communication delay and broadcasting obstacle information in real time; dividing a to-be-cleaned area based on related information, determining task sub-areas, and realizing adaptive distribution of tasks according to models; and finally, in the cleaning process, by fusing the swarming control of the artificial potential field method, the adjacent robots synchronously clean the boundary and adjust the track, multi-machine efficient collaborative operation of the photovoltaic cleaning robot can be achieved, and the cleaning efficiency and flexibility are improved.

The invention discloses a composite game reinforcement learning method and device for a four-rotor unmanned aerial vehicle cluster, and relates to the technical field of unmanned aerial vehicle cluster control. The method comprises the steps that an evaluation-execution network of the unmanned aerial vehicle is used for directly approaching a value evaluation and cooperation strategy online in a state-control input data space of cluster flight, repeated offline solving of a high-dimensional coupling HJ equation set under strong coupling nonlinear dynamics of the unmanned aerial vehicle is avoided, and therefore the modeling precision requirement and the calculation overhead are remarkably reduced. By introducing a filtering mechanism with a'forgetting factor ', weighted integral processing is performed on samples such as pose / speed / relative formation errors, control instructions, energy consumption and safety cost collected in the historical flight process of a cluster, and a composite'evaluation' network error and regression signal fusing current and historical information is constructed; and a finite excitation criterion which can be inspected on line is given on an information matrix level, so that the unmanned aerial vehicle cluster can still keep effective learning under the condition that a continuous PE condition is not met.

The invention discloses a deep reinforcement learning multi-unmanned aerial vehicle cooperative path planning method of an HCA-MAPPO, and relates to multi-agent reinforcement learning and unmanned aerial vehicle cluster control. From a multi-unmanned aerial vehicle cluster collaborative path planning method, a simulation environment comprising a three-degree-of-freedom unmanned aerial vehicle kinematic model and a dual-coordinate system management system is established, and accurate simulation of a complex geographic scene is realized; a deep reinforcement learning method based on hierarchical cross attention HCA and multi-agent near-end strategy optimization MAPPO is provided; the method comprises the following steps: introducing an HCA executor network for performing priority processing on multi-source heterogeneous information; an internal curiosity module based on collaborative consistency gating is designed, so that the effective exploration efficiency in a sparse reward environment is improved; the invention provides a tangent guidance mixed reward shaping method based on conflict perception, and solves the problem of local optimum in path planning. And the situation awareness capability, the training convergence efficiency and the path planning success rate of the unmanned aerial vehicle cluster are obviously improved.

The invention discloses a training fault tolerance method and device applied to a distributed training system and a chip product, and relates to the technical field of distributed training. The method comprises the following steps: for a distributed training system which comprises a plurality of computing node clusters and each computing node cluster comprises a plurality of computing node groups, the plurality of computing node groups are used for executing distributed training tasks of the computing node clusters in parallel, and the plurality of computing node clusters are used for executing distributed training tasks of the distributed training system in parallel; under the condition that a fault node occurs in the distributed training system, determining a fault node cluster from a plurality of computing node clusters, the fault node cluster being a computing node cluster comprising the fault node; and controlling the fault node cluster to cancel execution of the distributed training task corresponding to the fault node cluster, and controlling at least one residual computing node cluster to execute the distributed training task of the distributed training system. According to the embodiment of the invention, the training fault-tolerant capability and the training stability of the distributed training system can be improved.

The invention relates to a robot control technology, and discloses a robot cluster control method and system and a storage medium, and the method comprises the steps: receiving motion state data, network link state data and service type information of each robot; predicting a motion track of each robot in a future preset time period based on the motion state data in combination with a digital map, and predicting a communication quality change trend of a current network link of each robot in the future preset time period based on the network link state data; determining a target network link of each robot based on the motion trail, the communication quality change trend, the digital map, the service type information and the received node operation state information of each edge relay node, and generating a network switching instruction containing the target network link and the switching opportunity, and the corresponding robot executes network link switching according to the network switching instruction. According to the invention, global prediction and active switching of robot cluster communication can be realized.

The invention discloses a collaborative awareness and recognition method and system based on an unmanned aerial vehicle cluster, and relates to the field of unmanned aerial vehicle cluster control and computer vision. The method comprises the steps of starting ground control software to load a route path file, constructing a sequence image optical scene and evaluating the effect, dynamically fusing and evaluating the effect of a wide-area optical scene, intelligently and collaboratively recognizing an optical target, confirming and judging collaborative recognition data, and counting and evaluating recognition accuracy. The system comprises a central node unmanned aerial vehicle subsystem, an edge node unmanned aerial vehicle subsystem and ground control software. According to the method, the central node and the edge nodes cooperatively work, the global scheduling decision-making capability of the central node and the real-time computing capability of the edge nodes are exerted, efficient coverage of a wide-area scene, high-resolution image splicing and cooperative recognition and tracking of a dynamic target are achieved, the problems of unbalanced computing load, information redundancy and the like of a traditional architecture are solved, and the method is suitable for large-scale popularization and application. The image quality and the target recognition accuracy are improved, the reliability is high, and the expandability is high.

The invention discloses a wind driven generator cluster power optimization distribution method based on congestion control, and belongs to the technical field of wind driven generator cluster control. According to the method, the power distribution problem of the wind driven generator cluster is solved by using a congestion control thought through the similarity between the power flow and the information flow, so that the optimization solution of the output of each wind driven generator in the wind driven generator cluster is realized. Firstly, a global congestion index reflecting the overall power tracking accuracy of a wind driven generator cluster is constructed, and power tracking of a wind driven generator cluster level is achieved; then, constructing a local congestion index reflecting the operation cost of each wind driven generator, and realizing power optimization distribution of a wind driven generator level, thereby reducing the overall operation cost of a wind driven generator cluster; finally, on the basis of the two congestion indexes, the output power of each wind driven generator is adjusted in a self-adaptive mode, and power optimal distribution is achieved. The method is simple in calculation, low in communication burden, plug-and-play and high in practicability.

The invention provides a wafer-level chip-oriented dual-dynamic scheduling reconstruction computing architecture, which comprises a plurality of task flow ports, each task flow port is connected with at least one control block processing unit (CBU), and the task flow ports are used for receiving data flows and standardizing the data flows into task blocks; a plurality of task block processing units (TBUs), each TBU comprising a TBU data plane and a TBU control plane, the TBU data plane comprising a reconfigurable computing array for performing computing functions, the TBU control plane comprising a task block state detector and a task flow trigger; a plurality of control block processing units (CBUs), each CBU comprises a CBU data plane and a CBU control plane, the CBU data plane comprises a control block engine and a task flow queue, and the CBU control plane comprises a cluster control unit and a TBU scheduler; the control network and the data network are physically separated and share the same topological framework. The architecture can realize fine / coarse granularity dynamic joint optimization at the wafer scale, eliminate assembly line blockage, prevent load inclined propagation, and support wafer system expansion.

The invention relates to the technical field of aircrafts, and discloses an intelligent cruise method and device for a super-intelligent adaptive multi-sensor aircraft and a medium, and the method comprises the steps: carrying out the data timestamp marking and data reliability calculation of a position sensor, a speed sensor, an attitude sensor and an environment sensor in an aircraft cluster; obtaining a multi-source sensor data packet; performing time sequence alignment and feature extraction on the sensor data in each subgroup to obtain group state feature data; respectively calculating a stand-alone anomaly score, a local anomaly score and a global anomaly score to obtain a communication anomaly aircraft identification result; generating a segmented return path; performing clustering and cluster head election on normal aircrafts except the abnormal aircrafts, and constructing an optimized communication network topological structure; according to the method, the reliability of the intelligent cruise of the aircraft is improved, and the continuous and stable operation of the aircraft cluster is ensured.