254results about How to "Implement fault detection" patented technology

The invention discloses a fault location method based on a residual and a double-stage Elman neural network for a hydraulic servo system, comprising the following steps of: obtaining the input/output signals of the hydraulic servo system in a normal working state, an electronic amplifier fault state and a leakage fault state, training a fault observer by virtue of the input/output signal in the normal state, and obtaining a real-time residual signal by the fault observer at first, and then training a state follower in real time and on line to obtain a network connection weight corresponding to the real-time signal, and training an RBF (radial basis function) fault locator by using the time-domain characteristic value of the residual signal and the network connection weight as the training input samples of the RBF fault locator. Both of the fault observer and the state follower are realized by the improved Elman network. Whether the system has a fault or not at present can be judged by comparing the time-domain characteristic value with a fault threshold, and the type of the fault can be obtained by the fault locator. The fault location method disclosed by the invention realizes fault location for the hydraulic servo system, and has high location accuracy and engineering applicability.

The invention discloses a fan fault detecting method based on a depth belief network model. The fan fault detecting method comprises that a fan flow forecast model is established by using depth beliefnetwork, state parameters related to the fan flow are selected to be used as the input variable of the model, and the flow of a fan is forecasted. The depth belief network is formed by staking multilayer continuous type limit Boltzmann machines, and an adaptive step length method is used to accelerate the algorithm training process. In addition, residual distribution characteristics are calculated according to a sliding window, when the mean value or standard deviation of the residual exceeds the threshold, alarm is issued. By means of the fan fault detecting method based on the depth beliefnetwork model, the flow of the fan can be accurately forecasted, meanwhile, the abnormal working state of the fan can be detected, and fault detection on the fan is achieved.

The invention discloses an intelligent LED street lamp monitor system based on the ZigBee and Wi-Fi technology. The intelligent LED street lamp monitor system comprises an upper computer, a wireless router, a Wi-Fi module, a ZigBee coordinator and a plurality of sets of monitor terminals, wherein the upper computer is in wireless communication connection with the Wi-Fi module through the wireless router; the Wi-Fi module is in bidirectional communication connection with the ZigBee coordinator through a serial port; the ZigBee coordinator is in wireless communication connection with each ZigBee terminal. Each set of monitor terminals at least comprise one ZigBee terminal, an LED street lamp driver, an LED street lamp and a detection module, wherein the ZigBee terminal is connected with the LED street lamp driver, the LED street lamp and the detection module sequentially in series. The intelligent LED street lamp monitor system has the advantages of energy conservation, intelligent control, convenient maintenance, easy on-spot wiring, low cost, high comprehensive function and the like.

The invention discloses a principal component tracking based industrial fault monitoring method and application thereof, and belongs the technical field of industrial process monitoring and diagnosing. The method includes decomposing industrial collected data into a low rank matrix including complete process operation information and a sparse matrix including sensor noise and process faults according to a principal component tracking method; performing fault detection in the low rank matrix by the aid of a statistical magnitude T2, and performing fault detection in the sparse matrix by the aid of a statistical magnitude of a mean value correlation coefficient. Compared with the prior art, the principal component tracking based industrial fault monitoring method has the advantages that according to the characteristic that the matrixes are decomposed by the principal component tracking method, different statistical magnitudes are adopted for the matrixes with different characteristics, effective information included in the data are fully utilized, and accordingly, high accuracy in industrial fault detection is achieved.

The invention provides an unknown input observer based realization method of fault diagnosis for a minitype unmanned aerial vehicle distributed formation. According to a hierarchical concept of a distributed control system, controller designs of the single unmanned aerial vehicle and multi unmanned aerial vehicle formation are studied to ensure the flight stability of the minitype unmanned aerialvehicle distributed formation. When a fault of a single unmanned aerial vehicle final controlling element occurs, an effective unknown input observer distributed system fault detection method is provided, which completely decouples interference and completely eliminates adverse effects of the external interference on a fault diagnosis process. Furthermore, a method to estimate the fault by extending a state vector and a fault vector into an augmented vector is provided. According to the invention, the conventional unknown input observer is combined with an augmented system to realize fault detection, separation and estimation of the minitype unmanned aerial vehicle distributed formation. According to known minitype unmanned aerial vehicle model parameters, a numerical simulation can be established to carry out fault diagnosis on the final controlling element. The fault diagnosis method is used for fault diagnosis of a minitype unmanned aerial vehicle distributed formation.

The invention discloses a network abnormal event sensing method and system. The network abnormal event sensing method comprises the following steps: inserting INT detection headers into all messages,sampling the messages, and labeling the INT detection headers of sampling messages; INT related operation is carried out on the message, the INT related operation comprises adding INT metadata to themessage, and the INT metadata records state information when the switch processes the message and is added behind the INT detection header; Screening a message containing the INT metadata of the at least one hop switch, and copying and uploading the message; Carrying out preliminary summarization on the uploaded message to generate a sub-event; And further summarizing the generated sub-events to obtain a final summarization of the events. According to the network abnormal event sensing method and system, full-amount, accurate and real-time network events are obtained, and the method and systemare used for fault diagnosis, topology assessment and the like.

The invention discloses a distribution network single-phase ground fault detection method using transient and steady feature fusion. When single-phase ground faults occur under different fault conditions of a resonant ground distribution network system, the steady and transient features of a normal feeder line and a fault feeder line have different time-frequency distribution characteristics, thetransient features are obvious under strong faults, and faults in the distribution network are accurately and reliably detected by using fault transient zero-sequence current time-frequency characteristics. Under weak faults, fault detection is achieved by a zero-sequence current steady quantity feature after the faults. The method solves the technical problem in the prior art that transient zero-sequence current sudden change amount, energy, amplitude and polarity are used for the transient quantity fault line selection method so as to improve line selection effects to different extents; however, after a ground fault, the effect of an arc suppression coil makes the zero-sequence current weak, especially when the intermittent arc grounding occurs, the arc extinguishing is uncertain such that the detection method in the prior art is no longer reliable.

The embodiment of the invention discloses a vehicle fault detection method and device, a vehicle and a storage medium. The method comprises the following steps of obtaining a vacuum pump starting state, a braking pedal state, the vacuum pressure of a vacuum pump sensor and the environmental pressure of an environment sensor; according to the vacuum pump starting state and the braking pedal state,determining a preset pressure change tendency, and according to the vacuum pressure and the pressure change tendency, detecting the faults of the vacuum pump sensor; and when the vacuum pump sensor isunder a normal working state, obtaining pre-stored vacuum pump ultimate pressure, and according to the ultimate pressure and the environmental pressure, detecting the faults of the environment sensor. By use of the technical scheme of the embodiment of the invention, the fault of a vacuum system is detected when the voltage of the vacuum sensor is under a normal range, the fault detection accuracy of the vacuum pump system is improved, and vehicle driving safety can be enhanced.

The invention discloses a fault detection method based on a dimensional variable type independent component analysis model. The method comprises the following steps: in an offline modeling phase, according to differences of values of various column vector elements of a separation matrix in a traditional independent component analysis (ICA) model, various variables are firstly and correspondingly endowed with different weights to reflect differences of dimensions; afterwards, because each column vector in the separation matrix represent a difference of the corresponding measurement variable in a projection direction, the dimensions have a plurality of variable forms, and a plurality of ICA fault detection models can be established correspondingly; and, when online monitoring in performed, the multiple ICA models are called to calculated corresponding monitoring statistics, and a final probability type monitoring index is obtained by utilizing Bayesian reasoning in order to provide convenience for fault decision-making. Compared with a traditional method, the method is advantageous in that modeling considers uncoordinated importance of the measurement variables, and fault detection is implemented by utilizing the multiple modes at the same time. According to the method, description for a normal data characteristic is comprehensive, and an excellent fault detection effect is obtained through utilization.

The invention belongs to the field of control, and provides a method and system for detecting and controlling a network control system. Based on a continuous time system model of a controlled object, a controller acquires output signals collected through a sensor and passing through an analog-digital converter and the sampling time delay of network transmission, and the controller and a fault detector are designed. The fault detector detects fault detection signals, and meanwhile the controller outputs control signals to achieve closed-loop control over the controlled object. Therefore, the method and system for detecting and controlling the network control system avoids the model error brought by discretization modeling, fault information is taken into consideration with the design of an initiative fault-tolerant controller, and the needs of detecting faults accurately of the fault detector are further taken into consideration. Preferably, a cone complementarity linearization technology is called in the integral design process of the fault detector and the controller depending on a time-lag network control system, the solution of designing the controller is translated into a nonconvex optimization problem under a linear matrix inequality, and conservative properties are reduced greatly compared with lag irrelevance. Therefore, the method and system for detecting and controlling the network control system achieves fault detection and fault tolerance control.

The invention discloses a method, a system and a medium for detecting faults of a modular multilevel converter sub-module. The detection method comprises the following steps of: aiming at a target bridge arm of the modular multilevel converter, sampling a voltage transformer of the target bridge arm at the beginning of a kth control period to obtain a voltage sampling value; obtaining a theoretical calculation value of the sum of output voltages of all submodules of the target bridge arm at the beginning of the kth control period; determining a fault judgment basis lambda according to the difference between the sampling value and the theoretical calculation value of the voltage transformer; and judging whether the absolute value of lambda is less than or equal to a preset threshold value so as to judge whether the target bridge arm has a sub-module fault or not, and the sub-module with the fault can be further positioned. According to the invention, the fault detection of the sub-module can be realized on the basis of not adding other hardwares under the condition that a single bridge arm of the modular multilevel converter is only provided with one voltage transformer.

The invention discloses a power cable fault positioning platform, including a cable fault detector arranged on a power cable, a signal back-transmission mechanism, a mobile monitoring station and a mobile monitoring unit. The mobile monitoring unit comprises an overhead track and a mobile mechanism wherein the mobile mechanism is provided with a monitoring terminal; the signal back-transmission mechanism comprises a communication line arranged in a cable conduit and a number of wireless receivers; the fault detector is provided with a first wireless communication module; the monitoring terminal comprises a control module, a second wireless communication module, a storage module, a sensor module, a video monitoring module and wireless emitters arranged correspondingly to the wireless receivers; and the mobile mechanism is provided with a plurality of fault positioning mechanisms through an ejection mechanism. The platform of the invention performs comprehensive monitoring to the cable fault through the real-time acquisition of online current by the fault detector and through the fault point positioning, allows the workmen to quickly find the specific fault position so as to realize the rapid maintenance to the fault point.

The invention discloses a fault detection method and a device, including that a detection message is transmitted to a second device according to the preset message transmit cycle; the source address and the destination address of the detection message are the device address of the device which transmits the detection message; the next hop address is the address of the second device; when no detection message returns within the preset detection cycle, the communication between the device which transmits the detection message and the second device fails. In the fault detection method and the device, both of the BFD session sides are not needed to support the BFD bilaterally; the BFD session can be created on one side for the BFD fault detection, realizing the fault detection between the device which supports the BFD and the device which can not support the BFD.

The invention discloses a method for detecting faults of an integrated circuit. The method comprises the following steps of: obtaining an output probability density function (of each element) within a nominal parameter tolerance range through Monte Carlo simulation one by one; respectively calculating together with an output probability density function of a tested integrated circuit under each element nominal parameter so as to obtain a mutual entropy value, wherein the maximum value of the mutual entropy value is used as the maximum mutual entropy of the circuit, and the minimum value of the mutual entropy value is used as the minimum mutual entropy of the circuit; subsequently calculating an actual measurement output probability density function of a non-fault tested integrated circuit with an actual measurement output probability density function of an uncertain fault tested integrated circuit so as to obtain an actual measurement mutual entropy value; and finally comparing the actual measurement mutual entropy with the maximum mutual entropy and the minimum mutual entropy of the circuit so as to determine whether the integrated circuit has faults or not. Compared with the prior art, the method has fewer testing nodes and is simple and convenient in testing process, low in testing cost and insensitive to noise.

The invention relates to an information fusion-based series battery pack SOC (state of charge) estimation method and belongs to the technical field of battery management. The method comprises the following steps that: S1, a series battery pack to be tested is selected, the technical parameters of the series battery pack to be tested are acquired, and the CMM+CDM model of the series battery pack isestablished, and model parameters required by the SOC estimation of the series battery pack are determined; S2, a trickle current charge/discharge test and an HPPC (hybrid pulse power characterization) test are carried out, so that a database of charge/discharge OCVs (open-circuit voltage) and circuit model parameters with respect to SOCs is established, and a DST (dynamic stress test) and a UDDSare simulated, and a working condition test experiment database is established; S3, an OCV-SOC relation curve is obtained, and the electrical characteristic parameters of the CDM+CDM model are obtained; and S4, the CDM+CDM model is combined with a decentralized filter, and a CMM and the SOCs of single cells are obtained on the basis of an optimal algorithm and the quantitative relation of the charge/discharge characteristic parameters with respect to the SOCs, and the SOCs of each cell are fused through weight distribution, so that the SOC of the series battery pack is realized.

The application relates to a digital radio-frequency signal device. The digital radio-frequency signal device comprises a monitoring device and a signal conversion device; and a control terminal is connected to a digital processing device and a loop switching device of the monitoring device separately. The loop switching device is used to sequentially control the self-loop of the digital processing device and the signal conversion device according to the control of the monitoring device. The digital processing device is used to perform self-inspection on a first self-loop when the loop switching device controls a transmitting port and a receiving port to be connected to form the first self-loop link according to the control of the monitoring device, and is used to perform self-inspection on a second self-loop link when the loop switching device disconnects the self-loop of the digital processing device and controls a downlink output port and an uplink input port of the signal conversion device to be connected to form the second self-loop link, so as to generate respective self-inspection results corresponding to the self-loop links. The monitoring device is used to determine whether the respective self-loop links are faulty or not according to the respective self-inspection results. Therefore, the efficiency of signal link self-inspection is improved.

The invention discloses a grey fault diagnosis method applied to a telecom bearing network. The grey fault diagnosis method comprises the following steps: step 1, acquiring information of all paths inthe whole telecom bearing network; step 2, sending UDP detection packets on all the paths to measure the packet loss conditions of the paths; and step 3, for each interface, link and equipment in allthe paths, respectively analyzing the packet loss condition of all the paths passing through the interfaces, links and equipment, and diagnosing the gray fault occurrence position in the telecom bearing network according to the packet loss condition. The method does not need any hardware update, can be quickly deployed in a telecom bearing network environment, and can quickly find and position gray faults in the network.