203 results about "Mix network" patented technology

The invention discloses an industrial equipment defect detection method based on multi-modal feature fusion and dynamic optimization, and belongs to the technical field of computer vision, and the method comprises the steps: 1, multi-modal industrial data collection: deploying multiple sensors in a production line, collecting data in multiple periods, constructing a defect-free and multi-type defect sample library, and carrying out multi-modal industrial data collection; a time-space aligned multi-modal label is marked; step 2, data enhancement and defect synthesis; step 3, multi-modal hybrid model training: constructing a hybrid network, and performing pre-training and fine tuning by using a dynamic loss function; step 4, edge end dynamic optimization and deployment: edge end reasoning is realized through dynamic knowledge distillation, and model fine tuning is automatically triggered when false detection and missing detection are found; and step 5, intelligent labeling and result visualization: a front-end interface displays a detection result in real time. The problem that a current target detection framework is not high in small target recognition accuracy and low in efficiency is solved, and the reliability of industrial equipment defect detection is improved.

The invention relates to the technical field of radio frequency power matching, and discloses a direct-current radio frequency hybrid high-power network matching optimization method. The method comprises the following steps: collecting current fluctuation data of a direct-current power supply module and power reflection data of a radio-frequency emission module, and generating a hybrid network impedance characteristic set; calling a power grid topology analysis engine to analyze the set to obtain an impedance track characteristic matrix; performing dynamic trajectory optimization on the matrix based on a preset frequency domain stability constraint rule to generate corrected impedance trajectory distribution; fusing the corrected track distribution and the radio frequency load dynamic response data, and constructing multi-band matching topological feature representation; performing parameter decoupling on the topological feature representation through a nonlinear matching mapping engine to generate an optimal matching parameter configuration table; and finally adjusting the voltage stabilization coefficient of the DC power supply module and the tuning capacitance value of the radio frequency emission module according to the configuration table. According to the method, efficient matching optimization of the hybrid network is realized, and the stability and adaptability of system operation are improved.

The invention discloses a stainless steel thin-wall pipe bending forming production line control method and system. The method comprises the steps that state feature vectors are generated through data collection; establishing a hybrid network model, and optimizing hyper-parameters of the hybrid network model by using an OOA eagle optimization algorithm to obtain an improved hybrid network model; inputting the state feature vector into an improved hybrid network model, and outputting predicted values of the springback value, the wrinkling probability and the ovality which are about to occur in the current bending section; inputting the predicted value into a multi-objective optimization algorithm, and performing back calculation in real time to obtain an optimal compensation parameter set by taking minimization of springback, wrinkling risk and ovality as optimization objectives; and the compensation parameter set is transmitted to a physical execution unit for production line control including bending control, core rod control, clamping control and feeding control. And the first-pass yield of bending forming and the production control efficiency are improved.

The invention discloses a power load prediction method and system. The method comprises the following steps: acquiring historical power attribute data and constructing a time sequence; carrying out standardization processing on the sequence; performing multi-scale decomposition and reconstruction on the standardized sequence by using a wavelet transform convolution module, and extracting a reconstructed sequence fused with multi-scale features; and inputting the reconstructed sequence into an xLSTM-Informer hybrid network, capturing time sequence dependence characteristics through xLSTM, and outputting a load prediction result through introducing an Informer model of a probability sparse attention mechanism. According to the method, the problems of insufficient long sequence dependence capture, single multi-scale feature extraction and low calculation efficiency are effectively solved, and the precision and stability of long-time prediction are improved.

The invention relates to a lightweight low-delay continuous authentication method and system based on a linear attention hybrid network, and belongs to the technical field of information. The method specifically comprises the following steps: S1, a registration stage: collecting behavior data of a legal user and preprocessing the behavior data; training a lightweight hybrid feature extraction model, and establishing and storing a user behavior contour; s2, an authentication stage: collecting user behavior data in real time and preprocessing the user behavior data, extracting behavior characteristics and matching the behavior characteristics with stored behavior contours, and executing access control operation according to a matching result. According to the method, a global attention mechanism and a space-time attention mechanism are introduced, the long-term dependency relationship in a behavior biological feature sequence is fully captured, and the robustness of the model to noise and abnormal values is enhanced; through effective fusion of multi-sensor data and global features of different time points, high-precision legality verification of a user identity in a small authentication window is finally realized.

The invention discloses an intelligent pipe network leakage active prediction and early warning system based on multi-technology fusion, and the system comprises a multi-source heterogeneous data fusion collection module, a spatial-temporal feature depth extraction module, a degradation trend prediction and residual life evaluation module, and a multi-stage early warning and decision generation module. The multi-source heterogeneous data fusion acquisition module acquires and fuses ultrasonic guided wave signals, pressure flow time sequence data and environmental factor data; the spatial-temporal feature depth extraction module extracts spatial-temporal fusion features through continuous wavelet transform and a CNN-LSTM hybrid network; the degradation trend prediction and residual life evaluation module determines a degradation level, predicts residual life and quantifies a pipe explosion risk probability; the multi-stage early warning and decision generation module generates graded early warning signals and maintenance strategy suggestions, the technology crossing from post-event detection to pre-event prediction is realized, and the scientificity and refinement level of operation and maintenance management of a pipe network are effectively improved.

The invention discloses a port container automatic scheduling method based on multi-agent reinforcement learning, and the method comprises the steps: S1, building a corresponding relation between equipment and agents, and constructing a task set; s2, collecting operation state data, and constructing global and local state vectors; s3, generating a scheduling constraint vector, and cutting actions according to the resource, storage yard and path state to form a feasible action set; s4, on the basis of an improved QPLEX algorithm, constructing an individual value network containing a dump structure, and calculating an individual action value; s5, constructing a joint action value hybrid network, and mixing individual values according to the global state vector to form joint action values; s6, constructing a training sample, differentiating and aggregating instant and delayed return, and updating network parameters; and S7, during online scheduling, selecting an optimal action combination according to the combined action value, and generating and issuing a scheduling instruction. According to the invention, automatic collaborative scheduling of port container operation is realized.

The invention discloses a virtual power plant load regulation method and system based on a deep learning scheduling strategy, and relates to the technical field of power plant load regulation, and the method comprises the steps: obtaining multi-source heterogeneous data, and obtaining a feature tensor through preprocessing; the feature tensor is input into an LSTM-Transform hybrid network model, and a context code is output; inputting the context code into the time sequence convolutional network model, outputting an ultra-short-term prediction result, and further obtaining a short-term prediction result; constructing a multi-objective optimization model, and modeling constraint conditions; solving the multi-objective optimization model through a preset layered architecture to obtain an optimal scheduling strategy, and generating a scheduling instruction; and issuing the scheduling instruction to distributed resources in the virtual power plant, and executing and converting the scheduling instruction into an equipment action. The method solves the problems that in the prior art, the optimization target is single, the dynamic adaptive capacity is lacked, and the real-time fluctuation response speed of the power grid is limited to a certain extent.

The invention discloses a virtual-real fusion network communication performance real-time monitoring method, device and equipment and a medium, and belongs to the field of communication monitoring, and the method comprises the steps: monitoring a communication link performance test instruction issued by a user in real time; wherein the communication link comprises a real link, a virtual link and a virtual real link; when a first instruction of only performing performance test on one communication link is received, determining the type of the communication link according to the nodes at the two ends of the communication link, and selecting a corresponding test method to test the performance of the communication link according to the type of the communication link; and when a second instruction for testing the performance of all the communication links is received, testing the performance of all the real links and all the virtual links in parallel, and then testing the performance of all the virtual links in batches according to the path lengths of the virtual links. Therefore, by implementing the application, the problem of low communication performance monitoring efficiency under a complex virtual-real hybrid network structure can be solved.

A secure container framework is disclosed for executing embedded AI micro-models in hardware-constrained or hybrid network environments. The system includes a secure execution container configured to manage AI micro-model lifecycle stages, enforce symbolic constraints, evaluate runtime telemetry, and optionally invoke fallback behaviors through alternate models or rule sequences. Each container includes cryptographically verifiable components such as policy maps, fallback subgraphs, and execution metadata. The invention supports mesh or non-mesh deployments, peer coordination, and operation on CPUs, GPUs, microcontrollers, or other equivalent or similar functionality hardware. The framework enables verifiable, autonomous, and policy-governed embedded AI operation.

The invention discloses a multi-label website fingerprint identification method and system based on attribution analysis, and the method comprises the steps: firstly carrying out the model attribution analysis of a training sample, and constructing an average discrimination template of each website category; high contribution areas of all categories are extracted according to the average discrimination template, and a structured mask template used for guiding identification is formed; in the identification stage, sliding window matching is carried out on input hybrid network traffic, the position of a potential pseudo sub-stream is judged according to the similarity between a mask template and a window sub-sequence, and single-label identification is carried out on the extracted pseudo sub-stream, so that effective analysis of multi-label traffic is realized. The method has the advantages of being high in structure perception, high in template generalization and good in mixed flow adaptability, the website recognition capacity in a complex network environment can be remarkably improved, and the method is suitable for scenes such as encrypted communication monitoring and anonymous channel flow analysis.

The invention discloses a power load time sequence anomaly detection method and system based on a Mama and LSTM hybrid network, and belongs to the technical field of power system data analysis and artificial intelligence, and the method comprises the steps: inputting the preprocessed power load and related factor time sequence data into a Mama-LSTM hybrid encoder; performing time sequence data reconstruction and anomaly probability prediction in parallel by using depth features output by an encoder, and performing model training by jointly optimizing reconstruction error loss and anomaly detection loss; calculating a comprehensive abnormal score based on the trained model, and judging an abnormal point by adopting a dynamic threshold value; and outputting an anomaly detection result and providing an analysis report containing an unsupervised evaluation index and multi-dimensional visualization. Through deep series fusion of Mama and LSTM, long-term dependence and complex modes in a power load sequence are effectively captured, and the accuracy, robustness and interpretability of anomaly detection are significantly improved in combination with a joint training strategy and an unsupervised evaluation system of the system.

Multi-stage hybrid network integrates relationship regularization links and explainable elements to improve alignment with human values, explainability, robustness, and efficiency. The network comprises neural components, event prediction elements, and probability models across multiple stages, with relationship constraints enforcing structured knowledge representation. Explainable elements provide interpretable rationales for decisions, enhancing transparency. Training incorporates supervised learning, human-guided refinement, semi-automated knowledge engineering, and adversarial robustness techniques. A Socratic reasoning module detects contradictions and refines outputs for logical consistency. Indexed model elements enable dynamic memory optimization for improved efficiency. Candidate outputs may be scored, verified, or selected using neural and symbolic criteria. The invention supports retry loops and configurable subsystem pipelines to improve output quality. Applications include text generation, speech recognition, translation, and decision support. By combining structured constraints, human oversight, and modular architectures, the system improves the trustworthiness, safety, and adaptability of AI systems across diverse modalities and tasks.

The invention provides a code recommendation method and device based on a double-flow hybrid network, relates to the field of code semantic analysis, and solves the technical problem that long-distance dependency capture and calculation efficiency improvement cannot be synchronously realized in the prior art. The method comprises the following steps: analyzing a source code to obtain a feature sequence; performing double-flow feature extraction on the feature sequence to generate a time sequence flow feature and a context flow feature; the time sequence flow features are used for capturing local grammar features; the context flow features are used for capturing long-distance dependence; and dynamically fusing the time sequence flow features and the context flow features, and outputting recommended code nodes based on the fused features. The method and the device are used in a user operation visual arrangement process.

The invention discloses a non-intrusive power grid wiring diagram switch state identification method and system based on deep learning, a processor and a medium. According to the method, electrical data and switching state data of a power grid are collected and marked, a '1D-CNN + BiLSTM + Transform 'hybrid network model is constructed after preprocessing and feature extraction, and the switching state of the whole network is recognized after training. Power grid equipment does not need to be transformed, an existing mutual inductor is used for collecting data, local mutation, time sequence dependence and global association of electrical data are effectively processed through multi-dimensional feature extraction and a hybrid network model, the accuracy and robustness of on-off state recognition are improved, and the method can be applied to power grid on-off state monitoring in real time. And reliable support is provided for intelligent power grid operation.

The invention discloses a power communication network end-to-end service quality intelligent prediction method based on artificial intelligence, and aims to realize accurate prediction and dynamic optimization of power communication network QoS (Quality of Service), the method comprises the following steps: firstly, comprehensively carding a physical architecture, determining a core node and a link, constructing a dynamic topology model containing a time dimension based on the core node and the link, and generating high-dimensional fusion embedding; carrying out down / up sampling on multi-source data, binding nodes, and constructing a tensor containing spatial-temporal characteristics; quantifying the node causal contribution degree based on the dynamic causal graph to position a root cause; building a TCN-DGAT hybrid network, and predicting QoS in combination with online element learning; and network configuration is optimized by means of digital twin Bayesian optimization verification. The problems of low data processing efficiency, inaccurate prediction and poor adaptability in the prior art are solved, accurate prediction and dynamic optimization are realized, stability and high efficiency of a power communication network are guaranteed, and a key technology is provided for communication support of an intelligent power grid.

The invention discloses an agent cluster path planning model training method and device, and the method comprises the steps: constructing a first state matrix of an agent at a current time step, inputting the first state matrix into an initial reinforcement learning model, and predicting the second motion information of each agent at a next time step; based on the second state matrix and the first state matrix, determining a reward score of executing the task by the agent cluster; constructing time sequence data formed by the target tetrad, and inputting the time sequence data into each local Q network to generate a local Q value; combining the local Q values into a global Q value through a mixed Q network; and continuing to train by using the updated local Q network and the mixed Q network to obtain an intelligent agent cluster path planning model. According to the scheme, the hybrid Q network has timing modeling and attention weight distribution capabilities, each agent makes a decision independently, and decentralized control is realized; time sequence dependence is learned by adopting time sequence data, so that path generation is more flexible.

A flood similarity intelligent analysis method based on multi-mode Transform and comparative learning comprises the steps that firstly, static features are processed through a grouping full-connection network, and the characterization capacity is enhanced through feature specific transformation; a CNN-Transform-Attention hybrid network is constructed to extract dynamic process line features, a convolutional layer captures local morphological features, a Transform encoder captures a global time sequence dependency relationship through a self-attention mechanism, key hydrological stages are adaptively focused through an attention weight, multi-modal features are adaptively integrated by adopting a gating fusion mechanism to generate unified embedded representation, and the dynamic process line features are extracted by adopting a convolutional neural network (CNN)-Transform-Attention hybrid network. A comparison learning and difficult sample mining strategy is introduced, discriminative characterization is learned in a low-dimensional embedding space through a comparison loss function training model based on the Euclidean distance, and the similarity is mapped into an interpretable probability of a [0, 1] interval; the technical problem that multi-source heterogeneous features are insufficient in utilization is effectively solved, accurate quantification and interpretable evaluation of flood similarity are achieved, and technical support is provided for flood forecasting, historical flood matching and flood control dispatching decision making.

The invention discloses a networked vehicle queue safe cruise method for coping with hybrid network attacks, the vehicle queue comprises a head vehicle and a following vehicle, the following vehicle collects the running state data of the vehicle, obtains the running state data of other vehicles through a communication network, continuously detects the state of the communication network, and sends the detected state to the vehicle queue. Detecting whether a network attack is currently suffered or not and the type of the suffered attack, and calculating the minimum characteristic value of the topological matrix in a normal communication state, a spoofing attack state or a replay attack state according to the identified attack type; and then solving the constructed linear matrix inequality which enables the vehicle closed-loop system to be stable to obtain a feedback gain, and generating a control input signal according to the feedback gain obtained by calculation to realize accurate control of the vehicle. The feedback gain is dynamically adjusted according to the real-time state of the vehicle, so that the safety cruise control of the vehicle queue system is more effectively realized.

The invention relates to the technical field of coupler design, in particular to a bi-directional coupler applied to a high-frequency RFID (Radio Frequency Identification Device) system, which comprises the following steps: S1, respectively constructing a series transformer, a parallel transformer and a Magic-T structure hybrid network, and forming an impedance self-matching coupler core framework by adopting a plurality of Ni-Zn ferrite double-hole magnetic rings; s2, inputting an original coupling signal output by the coupler core architecture into a phase-amplitude cooperative calibration module to generate a calibrated stable coupling signal; s3, inputting the stable coupling signal into a bridging T-type attenuation network group, respectively performing accurate power adjustment on a forward coupling path and a reverse coupling path, and finally outputting a high-directivity and low-fluctuation coupling signal; s4, monitoring the impedance state of an antenna port in real time, and feeding back and adjusting a matching network structure to realize stable control of the standing-wave ratio in a full frequency band range; according to the invention, the design of an external matching circuit is simplified, the coupling efficiency and directivity are improved, and the method has important engineering value.

The invention relates to the field of artificial intelligence, in particular to an intelligent obstacle avoidance method, system and equipment based on hybrid network attacks, and the method comprises the steps: constructing a system model containing hybrid attacks, dividing four types of obstacle regions, constructing a hybrid zero-sum game framework, and solving an optimal control strategy for obstacle avoidance. The state of the control system and the network weight error are consistent and finally bounded, and safe obstacle avoidance is realized; according to the scheme, the research blank in the field of obstacle avoidance under mixed attacks is filled, and the applicability and reliability of an autonomous system in an actual severe environment are improved.

The invention relates to the field of engineering construction, in particular to a construction cost analysis system and method based on big data. The method comprises the following steps: acquiring multi-modal construction data in a system, sequentially performing data preprocessing and standardization on the multi-modal construction data, aligning texts and numerical values in the initial multi-modal construction data, constructing a knowledge graph by using aligned text numerical value data and image spatio-temporal data, and connecting an LSTM-GRU hybrid network with an HMM hidden Markov model. The method comprises the following steps: establishing a construction cost prediction model, adding a space-time attention mechanism in the model, inputting feature multi-modal construction data into the model for prediction, iterating model training through a PPO algorithm, and carrying out unified scheduling management on materials and manpower in a construction project based on a minimum cost path and a risk plan library. Key space-time regions can be dynamically focused, so that the spatial resolution of a prediction result is improved to a section level, and a basis is provided for accurate scheduling.

The invention discloses an intelligent water quality monitoring and operation regulation and control method and system for a central air-conditioning system. The method comprises the following steps: collecting multi-dimensional data in real time; the method comprises the following steps: extracting short-term local features through a multi-layer LSTM gating mechanism, capturing long-term dependence by using a multi-head self-attention mechanism, establishing a hybrid network model, optimizing hyper-parameters of the hybrid network model by using an improved IWOA whale optimization algorithm, predicting multi-dimensional data through a target hybrid network model, and constructing a GNN graph neural network. Abstracting a water system of the central air conditioner into a topological graph of nodes and edges, and modeling a dynamic coupling relationship between equipment; and initially embedding the spatio-temporal feature vectors as nodes of a GNN graph neural network, aggregating neighbor information by using each node, updating node states through a GCN graph convolutional layer, and outputting an operation regulation and control scheme. And the control efficiency is improved while the resource utilization rate is improved.

Apparatuses and methods are disclosed for encoding and decoding data. Techniques disclosed provide for the encoding of a data region of a frame. The encoding includes training an INR network to produce the data region from latent variables. And, determining distributions of the latent variables using respective contexts, constructed based on latent variables located within a shaped context region. Then, coding into a bitstream the latent variables based on the determined distributions and further coding into the bitstream the parameters of the trained INR network. Techniques disclosed also provide for decoding the data region. The decoding includes decoding from the bitstream the parameters of the INR network, determining the distributions of the latent variables using the respective contexts, and decoding from the bitstream the latent variables based on the determined distributions. Using the parameters of the INR network, the INR network produces the data region from the latent variables.

The invention relates to a spatio-temporal data rule extraction method based on spatio-temporal Fourier expert mixing, belongs to the technical field of urban spatio-temporal data processing, solves the problem that global stability characteristics and local disturbance characteristics driven by real physical rules are difficult to effectively describe in the prior art, and comprises the steps that S1, a spatio-temporal data acquisition module acquires historical data information; s2, establishing a space-time Fourier expert hybrid network, and carrying out expert mixing to obtain mixed features; s3, using adaptive group normalization as a conditional fusion module to obtain fusion features; s4, establishing a space-time Fourier attention mechanism module to obtain output features; s5, establishing a diffusion model for performing back diffusion on the noisy data in combination with the noise estimation network to obtain predicted denoised data, and performing training to obtain a trained diffusion model; and S6, performing sampling to obtain spatio-temporal data, inputting the spatio-temporal data into the trained diffusion model, and obtaining an extracted causal law for urban traffic flow prediction.

The application relates to an Ethernet node data sending method based on a hybrid network of Ethernet and FC-AE-1553, belongs to the technical field of FC-AE-1553 and Ethernet hybrid network communication, and solves the problems of complex FC-AE-1553 and Ethernet communication network structure, large volume and high cost in the prior art. The Ethernet node data sending method comprises the following steps: receiving an Ethernet data frame sent by a source Ethernet node, determining the node type to which a destination node of the Ethernet data frame belongs; if the node type to which the destination node belongs is an FC-AE-1553 node, analyzing the Ethernet data frame to obtain all valid data contained in a data packet and determining whether the destination node is an NC node or an NT node; encapsulating the valid data contained in the data packet according to an FC-AE-1553 protocol format to obtain a command data sequence or a state data sequence corresponding to the data packet, and sending the command data sequence or the state data sequence to the destination node. Data transmission from Ethernet to FC-AE-1553 is realized.

The invention relates to the technical field of industrial intelligent control and predictive maintenance, in particular to a multivariable time sequence prediction and closed-loop control method based on digital twinning and deep learning fusion, which comprises the following steps: constructing a multi-level data architecture based on a digital twinning five-dimensional model; data preprocessing and SMOTE resampling are carried out; time sequence feature extraction based on the 1D-CNN; virtual twin data generation based on Bi-LSTM (Bidirectional Long Short Term Memory) and an attention mechanism; performing multi-mode fault diagnosis based on the RNN-LSTM hybrid network; carrying out adaptive feedback control based on Lyapunov stability; a multi-task learning mechanism is adopted, and virtual twin data generation and fault diagnosis are jointly optimized. According to the method, excellent prediction precision and control performance are verified on a semiconductor etching process data set, and the fault diagnosis effect and the autonomous optimization capability of the system in the complex industrial process are remarkably improved.

The invention discloses an MASs consistency logic security control method under hybrid attacks, and relates to the technical field of multi-agent system security control, the method comprises the following steps: firstly initializing MASs system parameters, and realizing data confidentiality protection and information tampering detection by an LSPM through a two-layer key mechanism of symmetric key encryption and asymmetric key signature; designing a segmented consistency controller for a mixed scene of eavesdropping, information tampering containing content and identity source tampering and DoS attack, and deriving a linear matrix inequality LMIs through a time-varying Lyapunov function LKFs to solve controller parameters; and finally, continuously executing data security transmission and state adjustment to ensure that the MASs realizes leader-follower LF consistency. According to the method, when the MASs face mixed network attacks such as eavesdropping, tampering and denial of service, a comprehensive guarantee with confidentiality, integrity and authenticity is provided, and the reliability that the system finally realizes a consistent control target is ensured.

The invention provides a distributed cooperative control system for a safety inspection robot of a long-distance heat supply pipe network, which comprises a central coordination layer, a module control layer and an execution sensing layer, and is characterized in that the central coordination layer is used for global task planning, module state monitoring and fault arbitration; the module control layer comprises a plurality of independent control nodes which are respectively responsible for mobile control, detection control, communication control, energy management and storage control; the execution sensing layer comprises a plurality of actuators, and each actuator has independent parameter acquisition and instruction execution capabilities and feeds back a state code to the module control layer; through a three-level distributed architecture and hybrid network communication design, the problems of overweight load of a core controller, high module coupling degree, poor expansibility, weak environmental adaptability and the like of an existing centralized control system are effectively solved.

This invention discloses a method, equipment, storage medium, and program product for precise detection of slope sections. Through preprocessing and feature extraction using a CNN-LSTM hybrid network, interference such as noise, spikes, and numerical drift is effectively suppressed, enabling accurate identification of slope sections even in low signal-to-noise ratio environments. A two-level strategy of "AI coarse positioning + boundary statistical refinement" controls the positioning error of the slope's start and end points within 1-2 sampling points, achieving micron-level boundary positioning accuracy. This invention has advantages such as strong versatility, good engineering applicability, and convenient operation.