70 results about "Network error" patented technology

The invention relates to the technical field of positioning, in particular to a single Beidou positioning intelligent switching management system and method based on the 5G technology, and the method comprises the steps: obtaining key signal parameters of a 5G network and a Beidou system, and dynamically evaluating the communication quality of the 5G network and the Beidou system; obtaining the network load information of the 5G network and the Beidou system, and judging the congestion degree and response speed of the current 5G network and Beidou system; on the basis of evaluation and judgment results of the two steps, communication modes of the load are automatically switched in combination with the geographic position of the load; obtaining a load historical switching log and communication quality evaluation, analyzing a communication mode and communication preference of a user through a prediction model, predicting a communication demand of the user at a moment in the future, and formulating a communication switching strategy; based on the analysis of the pseudo-random noise code sequence of the 5G network and the pseudo-random noise code sequence of the Beidou network, the formulated communication switching strategy is optimized, and the Beidou network is prevented from being wrongly switched to the non-5G network.

The invention provides a rice irrigation online learning forecasting method and system, the method is realized according to a pre-constructed physical mechanism-neural network hybrid model based on physical mechanism model prediction and neural network error correction fusion, and the method comprises the following steps: S1, obtaining real-time environment data of a current decision period of a target rice field; s2, on the basis of the real-time environment data of the current decision period, forecasting a paddy field water layer depth predicted value of the next decision period through a physical mechanism-neural network hybrid model, and generating an irrigation drainage forecast in combination with a crop irrigation drainage mode; s3, real-time environment data of the target rice field in the next decision period after irrigation drainage forecast is executed are obtained, training samples are constructed and put into an experience playback pool, and the physical mechanism-neural network hybrid model executes online learning based on the experience playback pool; and S4, when the next decision cycle starts, returning to S2 until a preset stop condition is met.

Some embodiments provide a method for training a machine-trained (MT) network. The method propagates multiple inputs through the MT network to generate an output for each of the inputs. each of the inputs is associated with an expected output, the MT network uses multiple network parameters to process the inputs, and each network parameter of a set of the network parameters is defined during training as a probability distribution across a discrete set of possible values for the network parameter. The method calculates a value of a loss function for the MT network that includes (i) a first term that measures network error based on the expected outputs compared to the generated outputs and (ii) a second term that penalizes divergence of the probability distribution for each network parameter in the set of network parameters from a predefined probability distribution for the network parameter.

The invention provides a single event effect sensitivity evaluation method based on a cross-scale coupling mechanism, belongs to the technical field of electrical digital processing, and solves the problems that a traditional single event effect evaluation method cannot evaluate the function failure risk of an algorithm level and cannot position a key weight bit and a key network layer. The method comprises the following steps: acquiring key parameter information of a semiconductor device of an in-memory computing array, constructing a three-dimensional semiconductor device model, carrying out parameter calibration and inspection, and establishing a three-dimensional in-memory computing unit model; and establishing a single-particle fault injection model, performing single-particle effect fault injection transient simulation, mapping the single-particle multi-bit upset error pattern into the neural network to track a propagation path of an error in the neural network according to a mapping relation between the in-memory calculation array and the neural network, and identifying a key layer and a key weight bit in the neural network.

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 power transformer fault diagnosis method based on a particle swarm algorithm. The method comprises the following steps: 1, designing a BP neural network model for transformer fault diagnosis; 2, selecting the number of particle network layers of the BP neural network; 3, determining the number of input layer nodes of the BP neural network; 4, determining the number of output layer nodes of the BP neural network; 5, selecting and processing samples of the BP neural network; 6, making a BP neural network strategy improved by a particle swarm optimization algorithm; the method has the advantages that the accuracy of transformer fault diagnosis is improved, the network error precision is reduced, simulation and test results show that the convergence speed and the diagnosis accuracy of a system are obviously improved, and the method is suitable for large-scale popularization and application. And the system is trained by collecting a large number of representative samples, so that the reliability and the accuracy of the system are improved.

The present disclosure relates to a method and a system for managing one or more network errors occurred at a Network Data Analytics Function (NWDAF) module. The present disclosure encompasses: receiving, from the network data analytics function (NWDAF) module [302], a clear code data comprising a set of details related to the one or more network errors occurred at the NWDAF module [302]; decoding the clear code data; analysing the decoded clear code data to identify a historical code data parameter which indicates a number of occurrences of the clear code data in a historical data; detecting a first condition based on the historical code data parameter and a predefined threshold; and sending to a network function (NF) module [314] or the NWDAF module [302], a correction indication based on the detection of the first condition, for correcting the one or more network errors.

This invention discloses a method and system for intelligent diagnosis and optimization of network anomalies in iOS device apps. The method specifically includes: parsing system logs to identify network error patterns, and temporally associating the identified network error patterns with user operation event sequences to form a preliminary diagnostic event chain; extracting features and performing semantic understanding on interface screenshots and voice descriptions, and matching them with a preset fault knowledge base to obtain preliminary fault inferences; constructing a relationship graph based on the preliminary diagnostic event chain and preliminary fault inferences, calculating the probability of each node as the root cause of the network anomaly, and outputting the root cause location result; and generating a targeted personalized configuration optimization suggestion sequence based on the root cause location result through interactive exploration. This invention achieves accurate diagnosis and personalized optimization of network anomalies in iOS device apps, enabling rapid location of the root cause of the problem, reducing the time and cost of manual troubleshooting, and improving fault handling efficiency and user experience.

A device, communication system, and method are provided. In one example, a system for reducing latency in out-of-order data transfers is described that includes circuits to detect a network error; and in response to detecting the network error, transmit a notification to at least one of a plurality of connected nodes that the network error was detected, wherein the notification causes each node that receives the notification to change at least one transport layer parameter.

The application relates to a control method for dynamic walking of a biped robot and the biped robot, and belongs to the technical field of robot control, which comprises the following steps: 1, a self-recurrent cerebellar model neural network is used to establish a dynamic model of the biped robot with a disturbance term, and dynamic robust walking of the biped robot is converted into a problem of realizing stability of a multi-input multi-output nonlinear system with a bounded uncertain term; 2, an adaptive self-recurrent cerebellar model neural network error observer is designed to estimate an error upper limit; 3, an adaptive law of network weight is designed to realize real-time updating of the network weight space and to adjust parameters of each learning factor; and 4, a boundary value estimation algorithm is used to compensate for an estimation error and feedback to a robot walking system, so that the biped robot can realize asymptotic stable walking. The application enables the control system to adapt to time-varying characteristics of the biped walking system on line, and has continuous learning and adaptive capacity for unknown dynamics.

The present application relates to the technical field of network error monitoring, and is a kind of network NO_SOCKET error monitoring and analysis method, comprising the following steps: user state program initializes two eBPF programs and storage structure;Two eBPF programs are respectively mounted to socket release function and skb release function;First eBPF program reports sock event entry to user state program;User state program stores it to storage structure;User state program carries out aging treatment to sock event entry;When kernel calls skb release function and second eBPF program judges that the reason is NO_SOCKET error, second eBPF program reports skb event entry to user state program;User state program finds sock event entry from storage structure based on skb event entry, and obtains error processing information, to realize the monitoring and analysis of NO_SOCKET error.

The invention provides a cogeneration system active environment coordination control method based on distributed reinforcement learning, and belongs to the technical field of power system operation and control, and the method specifically comprises the following steps: S1, building an active scheduling model of a cogeneration system; s2, determining a solution strategy based on distributed reinforcement learning; and S3, iteratively updating the performance index and the neural network error. The distributed control strategy is adopted, the cogeneration units are regarded as independent agents, the neural network is used for estimating the performance index of each unit, the units are relatively independent, the sensitivity to the connectivity of the control signal paths is low, the problem that the optimization algorithm is interrupted due to the fact that one or more control signal paths are broken due to faults is solved, and the optimization efficiency is improved. And the robustness and safety of the active environment scheduling method are improved.

This disclosure pertains to systems and methods to detect network errors in a parallel redundant protocol (PRP) network. A node-level redundancy error subsystem of an intelligent electronic device (IED) maintains records (e.g., counts) of information associated with missing duplicate frames expected from node devices on the PRP network via redundant first and second local area networks (LANs). Non-zero counts of missing duplicate frames may be identified as network errors.

A device, communication system, and method are provided. In one example, a system for reducing latency in out-of-order data transfers is described that includes circuits to detect a network error; and in response to detecting the network error, transmit a notification to at least one of a plurality of connected nodes that the network error was detected, wherein the notification causes each node that receives the notification to change at least one transport layer parameter.

A modular architecture is provided for denoising Monte Carlo renderings using neural networks. The temporal approach extracts and combines feature representations from neighboring frames rather than building a temporal context using recurrent connections. A multiscale architecture includes separate single-frame or temporal denoising modules for individual scales, and one or more scale compositor neural networks configured to adaptively blend individual scales. An error-predicting module is configured to produce adaptive sampling maps for a renderer to achieve more uniform residual noise distribution. An asymmetric loss function may be used for training the neural networks, which can provide control over the variance-bias trade-off during denoising.

Computer systems and computer-implemented methods train a neural network iteratively training, through machine learning. The iterative training comprises imposing a first is-not-equal-to regularization link between first and second nodes, where imposing the first is-not-equal-to regularization link between the two nodes comprises adding, during back-propagation of partial derivatives through the neural network for a datum in a training data set, a first regularization cost to a network error loss function for the first node that is inversely proportional to a difference between an activation value for the first node for the datum and an activation value for the second node for the datum.

The application discloses a network error page display method and device, equipment, storage medium and product, and relates to the technical field of computers, which comprises the following steps: when an error occurs in accessing a website, obtaining a network error page corresponding to the error; generating explanation information corresponding to the network error page based on a large language model; modifying the content of the network error page according to the explanation information, obtaining a new network error page, and displaying the new network error page. Since the application generates explanation information corresponding to the network error page based on a large language model when an error occurs in accessing a website, modifies the network error page according to the explanation information, obtains a new network error page, and displays the new network error page, compared with the existing method of directly displaying the network error page when an error occurs in accessing a website, the above-mentioned method can display explanation information of the network error page that is easy for users to understand, helps users quickly analyze and locate network problems in the browser, and improves the user experience.

The application provides a new energy output scene generation method and system based on a deep belief network, comprising: performing forward training on new energy historical output data in a constructed deep belief network, initializing a network learning rate, and generating new energy output training data; inputting the new energy output training data and feature data labels into a logistic regression layer of the deep belief network, correcting the feature data in the new energy output training data based on the network learning rate using a gradient descent method, and outputting new energy output training result data; and calculating a network error, when the network error is less than a network error threshold, outputting the new energy output training result data as a new energy output scene; the application deeply mines various characteristics of new energy historical output data, the obtained output scene is more scientific and reasonable, and is applied to generation of multiple new energy output scenes, thereby reducing difficulties in modeling faced in generation of new energy medium and long term output scenes.

The application discloses a kind of equipment high-risk operation risk assessment method based on normal process, it is extended to the combination form of normal and normal process by traditional normal process, to better adapt to the evaluation needs of equipment high-risk operation;Thus the multiple sub-equipment involved in equipment high-risk operation is respectively solved by state monitoring data sub-equipment state failure time estimate value, and further solves risk assessment value;Finally, a kind of radial basis neural network with normal function and two normal functions as base function is established, and the network error is obtained by the existing equipment risk assessment historical data, and the adaptive weight adjustment law based on error feedback is further designed, and the neural network weight is trained until the error converges;Finally, the state monitoring value of the equipment to be evaluated is substituted, and the high-risk operation process risk assessment total score of the equipment to be evaluated is solved, and the risk assessment is completed.

The invention relates to the technical field of cross-platform application communication, in particular to a cross-platform sky-map component bidirectional communication method and device based on a message queue, and the method aims at the bidirectional communication requirements of an application layer and a WebView layer in a cross-platform sky-map component, manages concurrent requests through the message queue, generates a unique identifier for each instruction, and transmits the unique identifier to the application layer through the WebView layer. Accurate matching of messages is realized; data serialization and deserialization are combined to ensure that cross-layer data formats are uniform, main thread blocking is avoided through an asynchronous calling mechanism, and quick result feedback is achieved through timing polling; meanwhile, an error retry mechanism is designed for temporary faults such as network errors and WebView abnormity, and the communication reliability is guaranteed. According to the invention, a communication closed loop from the application layer to the communication layer to the WebView layer to the communication layer to the application layer is realized, the problems of concurrence processing disorder, easy blocking and weak fault recovery capability of the existing communication scheme are solved, the method is adaptive to a unit-app X framework and multiple mobile platforms, and the communication efficiency and stability of a cross-platform sky map component are improved.

The invention discloses a fusion processing system and method for multi-source heterogeneous data of an electric power system under a 5G network, and relates to the technical field of fusion processing of the multi-source heterogeneous data of the electric power system.The fusion processing method comprises the steps that phase angles, active power, voltage and time synchronization deviation of adjacent nodes are collected on a unified time axis, and paired phase angle difference observation and relative time deviation estimation are generated; an electrical expected phase angle difference is approximately obtained according to the small-angle power flow, and the relative time deviation is mapped into a 5G network projection phase angle according to the power frequency; subtracting the three values, normalizing according to a noise equivalent standard deviation to obtain an inconsistent quantity, finishing pairwise network removal correction and generating a weight matrix; and under the participation of the weight, performing weighted least square to obtain a state vector, and performing consistency back-check by using residual measurement, thereby realizing reliable fusion calculation under the condition of time delay fluctuation. According to the invention, network errors can be separated, and fusion precision and robustness are improved.

Techniques for capturing device state information from multiple network devices when a network error occurs are described. A network controller determines a trigger event and a trigger action. The trigger action is an action to be taken by a network device in response to the trigger event occurring, and the trigger event is an unexpected network event or network error. The network controller determines a method usable to configure the network devices to perform the trigger action in response to detecting the trigger event. The network controller configures, according to the method, the network devices to perform the trigger action in response to detecting the trigger event.

The application provides a train close tracking adaptive control method and device and a computing device. The method comprises the following steps: acquiring the position and reference speed curve of a front vehicle in a virtual marshalling train at a current time; combining the reference speed curve of the front vehicle at the current time to calculate a reference speed curve of the train; combining the position of the front vehicle at the current time and the position of the train to calculate an adjustment speed, and correcting a network error index by using the adjustment speed; training a radial basis function neural network by using the network error index to obtain a control force of the train; and controlling the train to run according to the control force. The method can realize adaptive control of the train, and further realize close tracking control of the marshalling train, and has the advantages of high real-time performance, high safety, high punctuality and high anti-interference performance.

The application provides a kind of neural network enhanced mechanical arm safety control method and system, the application constructs safety function for joint and workspace obstacle;Robust compensation term is designed by combining network weight error and inherent approximation error, and high-order safety constraint is converted into robust differential inequality;Single integrator auxiliary system and auxiliary barrier constraint are configured for each safety constraint channel, to maintain the feasibility of quadratic programming solution;According to stability driving item and safety driving, weight update law is constructed;And nominal joint torque, auxiliary reference input is used as optimization goal to construct quadratic programming problem, different working modes are switched by mode selection switch and solved, and the optimal control is obtained.The application can compensate system uncertainty, suppress various network errors and external disturbances, maximize trajectory tracking accuracy under the premise of ensuring that the joints of the robot arm do not exceed the limit and the body does not collide, effectively improve the robustness, stability and comprehensive performance of the control system.

A communication network device that selectively provides dynamic feedback information is described. When an error associated with the communication network device occurs, the communication network device may provide a beacon with the feedback information associated with the error, where the feedback information includes an error message that indicates the error in human-readable form. Notably, the feedback information may be included in a secondary attribute associated with the communication network device. Notably, the feedback information may be included in Passpoint information associated with a wireless local area network (WLAN) provided by the communication network device. Alternatively or additionally, the feedback information may be included in an SSID associated with the communication network device. For example, when the error occurs, the communication network device may dynamically change the SSID of a wireless local area network (WLAN) provided by the communication network device to include the feedback information.

The present invention proposes an industrial equipment status detection method based on an autoregressive graph adversarial neural network, which mainly solves the problem that the prior art graph structure representation is inaccurate. The data feature extraction is not comprehensive, and it is easily affected by noise and pseudo-anomalies and misdetected. The steps of the present invention are: constructing a graph structure learning subnetwork to correctly learn the graph structure; using a sequence feature extraction subnetwork and a latent variable feature extraction subnetwork to comprehensively extract the features of the input space and the latent space; using an autoregressive regularization subnetwork and an adversarial regularization subnetwork to suppress overfitting. The present invention reduces the network error detection rate; the operating status of industrial equipment can be detected in real time through the trained network.

The invention relates to the technical field of network error monitoring, in particular to a method for monitoring and analyzing network NOSOCKET errors, which comprises the following steps that: a user mode program initializes two eBPF programs and a storage structure; the two eBPF programs are mounted to the socket release function and the skb release function respectively; the first eBPF program reports the sock event entry to a user mode program; the user mode program stores the data in a storage structure; the user mode program carries out aging processing on the sock event entry; when the kernel calls the skb release function and the second eBPF program judges that the reason is NOSOCKET error, the second eBPF program reports the skb event entry to the user mode program; and the user state program searches for the sk event entry from the storage structure based on the skb event entry and obtains error processing information so as to realize monitoring and analysis of the NOSOCKET error.

The present invention belongs to the technical field of electromagnetic wave absorption materials, and specifically relates to a self-calibration design method for multi-layer honeycomb absorbing materials based on neural networks. First, the present invention conducts modeling and simulation on the multi-layer honeycomb absorbing materials, and establishes a sample data set composed of material characteristic structure parameters and corresponding reflection loss curves; secondly, a neural network model is established, and a high-performance forward prediction network and a reverse mapping network are obtained through training; then, on the basis of the two neural networks, combined with the self-calibration design method, through the method of optimizing condition screening, combining the translation of the reflection loss curve and CST simulation calibration, the rapid design of multi-layer honeycomb absorbing materials with the reflection loss value as the target is realized within any frequency range covered by 0.5 GHz - 18 GHz. By introducing a self-calibration step into the design process, the present invention greatly reduces the influence of neural network error superposition on the result accuracy.

This invention discloses an adaptive network data acquisition method and system based on error detection, belonging to the field of power distribution communication network operation monitoring and data acquisition technology. The method includes: acquiring error detection results based on a preset multi-error detection algorithm and pre-acquired power distribution network data; triggering frequency adjustment when a network error is detected; acquiring the number of errors based on a preset sliding time window and the error detection results; acquiring the error severity based on the number of errors and a preset anomaly threshold; acquiring a target acquisition frequency based on preset frequency adjustment parameters when a preset frequency adjustment condition is met; updating the current acquisition frequency to the target acquisition frequency, and acquiring the current power distribution network data based on the target acquisition frequency, thus achieving adaptive network data acquisition. This invention discloses an adaptive network data acquisition method and system based on error detection, which can solve the technical problem of the lack of adaptive capability in existing acquisition strategies.

The present invention discloses a method for correcting the synchronization error of the entire network of a power transmission terminal, comprising the following steps: collecting fault information, uploading fault information, marking the fault information at a master station, comparing the fault information, obtaining the correction error, and correcting the error of the entire network. The technical solution of the present invention solves the problem of inaccurate positioning of the fault position due to a small timing error, eliminates the influence of the random error of the timing module, synchronizes the timing module error of the entire network, and enables workers to accurately locate the location where the fault occurs.