178 results about "Network tomography" patented technology

The invention discloses a network diagnosis method based on a software defined network (SDN). The method includes the steps that a switchboard sets the rule of debug option of a flow table item according to a flow table debug setting command sent by a controller; the switchboard matches the key field of the message heading with the matching field of the flow table item, and judges whether the flow table item matched with the message is set up with a debug option field or not; if yes, the switchboard executes relevant debugging operations according to the content of the debug option field, and the operations include, but not limited to, sending the matching message and the contextual information to the controller; and the controller proceeds network diagnosis according to the message and the contextual information. The invention further discloses a network diagnosis system and equipment based on the SDN. With the technical scheme provided by the invention, the cycle for positioning a network problem is accelerated, the quality of the network is improved, and the operating maintenance cost of the network is reduced.

The invention discloses a method for the fault diagnosis of wind turbines on the basis of a genetic neural network, in particular to a method for modeling the fault diagnosis of wind turbines on the basis of the genetic neural network capable of learning the operating data of the wind turbines in the history, more particularly a method for judging the probability that faults occur to a gearbox, a generator and a yaw system by reading the real-time operating data of the wind turbines online and calling the diagnosis model of the genetic neural network to carry out the analysis on the real-time data, thus judging the fault state of the wind turbines. Based on the method combining the genetic algorithm with the neural network, the invention can achieve the algorithm complementation, improve the model convergence and diagnostic capacity and ensure higher robustness; and the method capable of carrying out the online monitoring and fault diagnosis on the operating state of the wind turbines on a real-time basis to take maintenance measures as soon as possible can improve the reliability of the wind turbines and reduce the maintenance cost.

A system and method facilitating network diagnostics and self-healing is provided. The invention includes a data stream monitor component adapted to selectively copy protocol specific subset(s) of raw network data and provide the subset(s) of data to a diagnostics engine. The invention further includes a diagnostic engine adapted to facilitate network diagnostics and/or self-healing.

The invention further provides for protocol state compressor(s) to analyze the protocol specific subset(s) of data to abstract and/or analyze relevant information about the specific protocol without having to strictly process the protocol or preserve protocol state variable(s) in order to analyze the state of the specific protocol. Based upon this analysis, the protocol state compressor(s) can generate event(s) for undesirable state(s) (e.g., error(s) and/or failure(s)) and/or congested state(s) for use by the event correlator/inference engine. Additionally, the protocol state compressor(s) can provide information to the event correlator/inference engine regarding the state of the specific protocol (e.g., success(es)).

A network diagnostic device is provided, which comprises a passive real-time measurement tool that is useful for, among other things, expediting fault identification, isolation, and repair of a communication network or bus. The device also facilitates prediction of failures by identifying marginal operating conditions. The device analyzes data flowing through the communication network, including through an analysis of variations in bit waveform shape carried by the network physical interconnect media. In one embodiment, an implementation of the network diagnostic device is particularly useful in a DeviceNet-compatible network or, more generally, a Controller Area Network (CAN). The device identifies faults by comparing measurements made on the actual DeviceNet bus with worst-case acceptable criteria. The device interfaces with a remote monitoring computer via an Ethernet compatible medium to display parsed bit-level waveforms, network warnings and errors, as well as an overall network health index.

The principles of the present invention extend to accessing results of network diagnostic functions in a distributed system. A chassis allocates resources for performing a network diagnostic function directly to requesting computer system. The requesting computer system communicates directly with the allocated resources to initiate the network diagnostic function. The network diagnostic test continues to execute even if the requesting computer system subsequently malfunctions. Collected test results are stored at the chassis such that any network connectable computer system can access the collected test results. A monitoring computer system (which may or may not be the requesting computer system) requests collected test results corresponding to the network diagnostic function. The chassis identifies appropriate test results and returns the results to the monitoring computer system.

A computing device is configured to display a user interface. The user interface is configured to create a filter configured to be applied to network diagnostic statistics prior to aggregation of the network diagnostic statistics. The filter includes at least one device data limitation and at least one performance data limitation.

The invention relates to a motor fault diagnosis system and method based on edge calculation and deep learning. Edge side equipment can configure an acquisition device, preprocesses vibration or current signals and then performs empirical mode decomposition (EMD), a built-in deep residual network diagnosis model of the diagnosis module inputs n IMF components to perform fault diagnosis, and a diagnosis result and fault data are uploaded to a cloud service center; and the cloud service center periodically trains the deep residual error network diagnosis model by using historical data and the fault data, issues the trained deep residual error network diagnosis model to each edge side equipment, and updates the deep residual error network diagnosis model in the edge side equipment. The motorequipment can be diagnosed in real time through the calculation of the edge side equipment, the motor state can be timely and quickly diagnosed, and only the processed data is transmitted to the cloudcenter, so that the time delay caused by the data transmission speed and bandwidth limitation is greatly reduced, and the data processing pressure of the cloud center is remarkably relieved.

The invention discloses a network failure diagnosis method based on a selective hidden Naive Bayesian classifier, comprising: (1), obtaining history data from a network history database, wherein the history data comprise a symptom variable set and a failure class variable set; (2), constructing a selective hidden Naive Bayesian classifier prediction model, determining corresponding most related symptom variable set according to every symptom variable in the symptom variable set; (3), automatically learning classifier parameters by the selective hidden Naive Bayesian classifier through training the history data; (4), in failure diagnosis, estimating the test data by using the selective hidden Naive Bayesian classifier so as to obtain corresponding final failure diagnosis result. Through executing the network failure diagnosis method of the invention, the problems in the existing network failure diagnosis that the operation complexity is high and the network diagnosis result is great in deviation are effectively solved; the network diagnosis accuracy is greatly improved; the operation complexity is further reduced, and better learning capability and fault-tolerant character are kept at the same time.

A network diagnostic component or device that is placed in-line between a first and second node. The diagnostic component or device is used to compress a random data signal. For example, the first node may communicate with the second node using a random data signal that includes random data units that represent a first data unit. In some embodiments, the random data signal may be of the SAS/SATA protocol. The network diagnostic component may receive the random data signal and associate at least one random data unit with identifier that is indicative of the first data unit. This random data unit may be recorded in a memory. A representation of the random data units that are different from the random data unit associated with the identifier is also recorded in the memory.

Certain embodiments provide systems, methods, and apparatus for playback network diagnostics. An example method includes facilitating a connection between a server and a first playback device, the first playback device connected with a plurality of playback devices via a network, the first playback including a network topology. The example method includes receiving, at the server, data collected at the first playback device. The example method includes receiving, at the server via the first playback device, data collected from each of the plurality of playback devices identified in the network topology of the first playback device, the data routed by the first playback device to the server. The example method includes analyzing the received data to determine a status of the playback devices in the network topology.

A combination and correlation of data from multiple sensors in a wireless digital network is described. Sensors such as spectrum monitors, access points, and wireless client devices provide spectrum data to one or more central stations connected to the network. Spectrum data from multiple sensors is combined and correlated to provide insight into network operation such as spectrum maps, detection-range maps, and for network diagnostics. Sensors providing spectrum data may be synchronized. Correlating spectrum data from synchronized sensors allows more accurate location of sources such as interferers. The known EIRP of certain wireless devices may be used to improve location estimates, and these devices may be used as calibrations sources for sensors in the wireless network.

The invention discloses an Internet-of-vehicles environment oriented network performance comprehensive testing and evaluating analysis method which comprises the following steps of 1, establishing a testing platform which comprises a first testing board, a second testing board and a background server, wherein the first testing board and the second testing board are respectively used for network performance testing and vehicle driving information acquisition, and the background server is used for data storage, analysis and processing; 2, in different testing scenes, testing a network performance index by means of an active measuring method and network tomography; 3, performing abnormal data processing on testing data according to a 3-sigma principle, and obtaining a testing result by means of Bootstrap estimation and maximum likelihood estimation; and 4, performing evaluation and comparative analysis on the testing result by means of an Internet-of-vehicles performance comprehensive index evaluation method. The Internet-of-vehicles environment oriented network performance comprehensive testing and evaluating analysis method can realize comprehensive network performance measurement on the Internet-of-vehicles and can more visually and more effectively reflect network performance and change.

A network diagnostic device or component such as a network analyzer or a jammer that is placed in-line between two nodes in a network to perform a flow control operation transparently without the requirement of a separate link layer implementation. The network diagnostic device may include a diagnostic module configured to perform network analyzer operations, a memory a first flow control module a second flow control module. In some embodiments, when performing the flow control operation, various modules and/or components may cause the network diagnostic device to enter a first pass-through mode and to then enter into a first flow control handshaking mode from the first pass-through mode. The various modules and/or components may also cause the network diagnostic device to enter a second pass-through mode from the first flow control handshaking mode and to then enter into a second flow control handshaking mode from the first pass-through mode.

Conventional network tomography techniques do not allow the location or cause of a failure to be specified, and false positives are common due to lack of information. Using aggregation flow mining (AFM) or a similar method, an IMF (102) acquires, from each router (105) to be tested, information in relation to each flow. The IMF, in relation to each of the routers, obtains distributions of statistical information such as throughput or difference for each flow; calculates, in relation to each of the distributions, a Mahalanobis distance in relation to the expected value of a reference distribution; and makes a comprehensive assessment of the distributions to perform a fault determination. When the fault determination is performed, a normal value of the distribution used for comparison is acquired from AFM and updated through feedback as needed. After the results of fault determination in relation to other routers are assessed, the expected value of the standard deviation and the average value of the reference distribution used for comparison are updated.

Systems and methods are presented for partitioning end-to-end performance effects using network tomography. In one embodiment, a method for partitioning end-to-end performance effects within a network is presented. The method includes determining a network topology between at least two test points, obtaining an unrelated approximation of edge effects between the test points, measuring end-to-end performance data between the test points corresponding to a target application, regularizing an estimate of edge effects for the target application using the unrelated approximation of edge effects, and computing the estimate of edge effects for the target application to partition the end-to-end effects.

A network diagnostic module coupleable to a distributed process control network that controls an industrial process via field devices coupled to the network includes a power block coupleable to the network and configured to power the network diagnostic module with energy received from the network, a communications block coupleable to the network and configured to bi-directionally communicate over the network, and a diagnostics block coupleable to the network and configured to make diagnostic measurements of network and protocol parameters of the network. The network diagnostic module is not itself a field device that detects or controls any process variable of the industrial process, enabling the network diagnostic module to be placed essentially anywhere along the network to permanently monitor the network.

The invention discloses an elevator fault prediction method based on a BP neural network. The method comprises the following steps that 1, real-time data of the movement of an elevator are collected through a sensor set installed on an elevator car; 2, the collected historical data and standard data of the movement of the elevator are preprocessed and characteristic parameters are extracted, wherein a part of the characteristic parameters serves as a data sample, and the other part serves as a test sample; 3, a bp neural network diagnosis model is built, and the collected data sample is inputfor training; and 4, then the test sample is input to the trained bp neural network, the recognition accuracy of the trained sample and the test sample is determined, a training algorithm is optimized, the optimized neural network parameter configuration is used, and the elevator is subjected to fault detection. The elevator fault diagnosis method has the advantages of being high in real-time performance and diagnosis precision, capable of judging whether the elevator has potential safety hazards or not in real time, reducing the cost for manually maintaining the safety of the elevator, and finally achieving the balance of the safety performance and the economic benefit.

The system comprises: mobile agent group used for executing end-to-end measurement task, collecting the delay information about detecting packet and the packet-lost information about the detecting packet between different nodes, and sending the collected information to the agent control center, in procedure of network tomography end-to-end measurement; and agent control center used for generating and initializing the mobile agent, assigning task to the mobile agent, managing the execution of mobile agent, and according to the message from the mobile agent group, getting the restraint condition of the network tomography.