40results about How to "Improve fault detection speed" patented technology

When a failure occurs in the line of a communication network for transmitting packets using a tunnel, the disconnection messages of a plurality of tunnels which pass through the line are unified, and the occurrence of the failure is notified to an adjacent node for each line. Then, the tunnels are disconnected or switched based on a failure notice.

Embodiments of the present application provide a network equipment fault detection method and device. The packet loss rate of the network equipment is determined based on a first packet flow receivedby the network device and a second packet flow sent by the network device. Then, the fault detection threshold is obtained based on the fluctuation amplitude of the difference between the history received message flow and the history sent message flow of the network equipment. Finally, based on the packet loss rate and the obtained fault detection threshold, it is determined whether the network equipment fails or not. Compared with the prior art scheme in which the current packet traffic of the utilization port is compared with the historical packet traffic to detect whether a failure has occurred, the technical proposal of the embodiment of the present application can accurately and efficiently detect whether the network equipment fails when the network structure of the network equipmentis changed or other equipment for message transmission with the network equipment fails.

The invention discloses a fault detection method for Kalman filtering sensor information fusion. The method includes the steps of: 1. according to a Kalman filtering theory, establishing a state equation and an observation equation of a linear dynamic system; 2. according to the observation equation obtained in step 1, making use of a least square process to acquire state estimation, a corresponding mean square error matrix and an innovation sequence; 3. utilizing the known innovation sequence to acquire different channel-normalized new innovation sequences, and composing an innovation matrix of an m channel parallel sensor; 4. acquiring the spectral norms and spectral norm mean value of the innovation matrix according to the innovation matrix obtained in step 3; and 5. carrying out fault detection on the Kalman filtering sensor information fusion. The method provided in the invention adopts mathematical statistics and interval estimation, simplifies complex calculation, and substantially improves the fault detection speed.

The invention discloses a method and a device for carrying out hot backup on services, by which the service hot backup under the condition of RRU (radio remote unit) annular connection is realized quickly and effectively, and the problem of service interruption caused by that the time delay for realizing the service hot backup is long in the prior art is solved. The method comprises the following steps that: after an RRU accesses to a BBU (building base band unit), the BBU establishes a channel, and calculates and allocates a first delay measurement value and a second delay measurement value, wherein the first delay measurement value refers to a value of time delay that the RRU accesses to the BBU from a first link, and the second delay measurement value refers to a value of time delay that the RRU accesses to the BBU from a second link; after carrying out parameter configuration and cell configuration on the RRU, the BBU carries out service interaction on the first link; when determining that the first link is at fault, the BBU enables an IQ (intelligent) configuration corresponding to the first link and enables an IQ configuration corresponding to the second link; and after the RRU switches a clock from the first link to the second link and configures the time delay value from the first delay measurement value to the second delay measurement value, the BBU continues to perform the service above with the RRU.

The invention discloses a deep wavelet twin network fault diagnosis method for a modular multilevel converter. The method comprises the steps of firstly carrying out the fusion and enhancement of fault data in an MMC rectification mode and an inversion mode, enabling the data to be mapped to a low-dimensional space through the powerful feature extraction capability of a deep wavelet twin network, and carrying out the fault recognition based on the Euclidean distance, secondly, introducing incremental learning to carry out re-learning on the fault diagnosis model after MMC parameter drifting to update model parameters, and improving the generalization ability of the fault diagnosis model, and finally, building an MMC rectification and inversion simulation model, and verifying the effectiveness of the method. According to the method, the advantages of the twin network and incremental learning are combined, the fault can be rapidly diagnosed, the operation reliability of the converter is improved, and the fault diagnosis accuracy of the MMC under the condition of small sample and parameter drift is improved.

The invention discloses a photovoltaic array fault detection device and method, and belongs to the field of photovoltaic array monitoring. The device is mainly composed of a controller, an illumination temperature sensor, a voltage sensor, a current sensor and a relay module. Various detection values collected by the device are transmitted to an upper computer, and the upper computer establishes asuspected fault list through fault screening, selects a photovoltaic module with a suspected fault from the photovoltaic array, and removes the photovoltaic module from the array; then capacitors aremerged into the two sides of the suspected fault module, and a plurality of working point data on the characteristic curve of a module UI are collected, and the internal parameter normalization valueof the module is solved; the normalized value is input into an integrated CART classification tree model established in advance to judge the specific state of the module, and if it is determined thatthere is no fault, the corresponding module is re-connected to the system; and if a fault is judged, a fault list is established according to the fault index, so that workers can conveniently carry out maintenance. The device has the advantages of being simple in structure, relatively low in cost, rapid in diagnosis, timely in fault treatment and the like.

The invention provides an industrial equipment fault diagnosis system and method based on GA-BP-CBR, and the system comprises a GA-BP neural network module, a case-based reasoning CBR network module,a result correction module, and an output module. The input module inputs a fault training data set to the neural network module, and the GABP neural network module trains a pre-classification network. Meanwhile, CBR case reasoning is performed on the case description to form a case library file; indexes are established for the cases by utilizing output results of the trained pre-classification network, an original case library are divided into a plurality of sub-case libraries, test data are input into the trained pre-classification network during diagnosis, similar case sets are searched forin the corresponding sub-case libraries according to output of the network, and finally, the result correction module evaluates and corrects the obtained case set by referring to the output of the neural network to obtain a final diagnosis result. According to the invention, the fault diagnosis retrieval time is reduced, and the production efficiency is improved.

The invention discloses an online monitoring system for partial discharge of a high-voltage cable. The online monitoring system involves a terminal acquisition module, a network transmission module, adata management module and a user visual module, wherein the terminal acquisition module is connected with the network transmission module, the network transmission module is connected with the datamanagement module, and the data management module is connected with the user visual module. According to the online monitoring system, through cooperation between a terminal acquisition module sensorgroup and a distributed partial discharge acquisition terminal, efficient acquisition of data is completed, and the fault detection speed is accelerated; through the use of a wireless transmission technology of the network transmission module, the data transmission rate is greatly improved; through application of a central server of the user visual module, online monitoring is realized, so that adetection interface is more user-friendly; and a WeChat applet is developed at the mobile terminal of the user visual module, so that high sharing of information is realized.