2064 results about "Fault recognition" patented technology

A system and method for diagnosing one or more faults or one or more potential faults in a machine. The system and method has a communications module for communicating machine data between the machine and the system. It also has a fault recognition module for analyzing the machine data, which can determine one or more faults or potential faults in the machine. An expert system module having a fault tree is guided through only a truncated portion of the fault tree based upon output from the fault recognition module.

The invention discloses an internet log data-based software defect failure recognition method and system. The method comprises the following steps: in allusion to internet source system log data and user system source log data, taking the internet source system log data as a training set and extracting features from the training set, and generating a software defect failure log recognition prediction model through machine learning or similarity matching; and analyzing and recognizing the user system source log data to obtain log fragments which represent software defect failures, so as to a software defect failure types in allusion to user system logs. A cloud computing system failure recognition system comprises a multi-line log collection module, an internet source system log classifier and an online log analysis and failure recognition module. According to the method and system disclosed in the invention, the failures, caused by software defects, massive log information recognition can be realized, the failure reasons can be rapidly positioned, the failures during the operation can be recognized and the failure types can be diagnosed, so that the reliability and usability of the cloud computing system can be improved.

The invention relates to an adaptive extraction and diagnosis method for degree features of a mechanical fault through a stack-type sparse automatic coding depth neural network, and belongs to the technical field of mechanical equipment state monitoring and reliability evaluation. The method aims at a problem of intelligent diagnosis of the degree of the mechanical fault, and comprises the steps: carrying out the stacking of sparse automatic coding, adding a classification layer, and constructing the stack-type sparse automatic coding depth neural network which integrates the adaptive learning and extraction of the degree features of the fault and fault recognition; employing the advantage that the sparse automatic coding can automatically learn the internal features of data, and adding noise coding to be integrated in the sparse automatic coding for improving the robustness of feature learning; carrying out the layer-by-layer no-supervision adaptive learning and supervision fine tuning of the original input complex data through multilayer sparse automatic coding, completing the automatic extraction and expression of the degree features of the mechanical fault and achieving the intelligent diagnosis of the degree of the fault. The method is used for the diagnosis of the degree of faults of rolling bearings under different work conditions, and obtains a good effect of feature extraction and diagnosis.

A method of fault identification on a semiconductor manufacturing tool includes monitoring tool sensor output, establishing a fingerprint of tool states based on the plurality of sensors outputs, capturing sensor data indicative of fault conditions, building a library of such fault fingerprints, comparing present tool fingerprint with fault fingerprints to identify a fault condition and estimating the effect of such a fault condition on process output. The fault library is constructed by inducing faults in a systematic way or by adding fingerprints of known faults after they occur.

The invention discloses a rolling bearing fault identification method under variable working conditions based on ATT-CNN, and relates to a rolling bearing fault identification technology. The problemthat the generalization ability of an existing rolling bearing fault recognition method under variable working conditions is limited to a certain extent for a complex classification problem is solved.The method comprises the following steps: firstly, mapping vibration data to a nonlinear space domain through a convolutional neural network (CNN), and adaptively extracting rolling bearing fault characteristics under variable working conditions by utilizing the characteristic that the CNN has invariance on micro displacement, scaling and other distortion forms of an input signal; Secondly, an attention mechanism (ATT) thought is put forward to be fused into a CNN structure, and the sensitivity of bearing vibration characteristics under variable working conditions is further improved; And meanwhile, more abundant and diverse training samples are obtained through a data enhancement method, so that the network can be learned more fully, and the robustness is improved. The proposed fault diagnosis model based on the attention mechanism CNN (ATT-CNN) can realize multi-state recognition and classification of the rolling bearing under variable working conditions, and compared with other methods, higher accuracy can be obtained.

The invention provides a bearing fault diagnosis system which comprises an intelligent bearing provided with six output ports with a first output port and a second output port outputting vibration acceleration signals, a third output port and a fourth output port speed signals and a fifth output port and a sixth output temperature signals. The system is characterized in that: the six groups of signals output by the intelligent bearing are sent to the input port of an A/D conversion module, six groups of digital signals output by the A/D conversion module are sent to a processor internally provided with a status monitor and a fault recognizer, wherein, the status monitor monitors the status of the bearing according to the vibration acceleration digital signals, the speed digital signals and the temperature digital signals, and the fault recognizer utilizes a signal processing tool to get a fault judgment result. The system of the invention has the advantages of being capable of monitoring the status of the bearing in an on-line manner according to the three types of signals of the intelligent bearing on the basis of the current intelligent bearing provided with a compound sensor so as to judge which part a fault takes place in.

The invention discloses an infrared image automatic fault identifying method for high-voltage equipment. Firstly, electric equipment in need of detection is selected and a temperature image of the electric equipment is obtained; secondly, a heating point, heating a point temperature T1 and a normal phase temperature T2 of the electric equipment are obtained through processing of the temperature image; thirdly, a relative temperature is calculated in combination with an environment reference temperature T0 to judge a running condition and fault information of the electric equipment. In the infrared image automatic fault identifying method for the high-voltage equipment, the running condition and the fault information of the electric equipment on a high-voltage transmission wire are monitored on the basis of an infrared image processing technology, a temperature heating abnormal point is detected according to an infrared temperature image processing technology, a heating temperature, a normal temperature, an environment temperature and the relative temperature of an abnormal point are calculated and then the running condition and the fault information of the electric equipment are automatically judged according to a relative temperature difference judging method; in this case, quick on-line detection of the running condition of the electric equipment is realized.

The invention discloses a multi-terminal flexible DC grid DC line quick protection method and system based on single-terminal voltage. The method comprises the following steps: collecting the voltagesignals on the two sides of DC positive and negative line current limiting reactors in real time; forming a low voltage starting criterion; performing wavelet transform on the calculated line mode voltage on the current limiting reactors and calculating the wavelet transform modulus maximum; performing the data validity test and recording the size and the symbol of the first wavelet transform modulus maximum meeting the data validity condition; establishing the fault identification criterion to identify the fault based on the symbol and amplitude difference of the single-terminal voltage traveling wave wavelet transform modulus maximum; and constructing the fault pole identification criterion to identify the fault pole based on the size difference of the voltage traveling wave transient energy. According to the line protection method, the fault direction can be reliably and quickly identified under various initial fault conditions, and the transition resistance, the fault location andthe fault of the AC system and other factors have little influence on the protection criterion so as to have high reliability and sensitivity.

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 invention provides a fault detection system in a photovoltaic system (1), which uses a first measurement characteristic curve and optionally a second measurement characteristic curve to record the system status, and can thus distinguish malfunctions from the normal system operating state.

The invention discloses a bearing fault diagnosis method based on improved EMD decomposition and sensitive characteristic selection. The method comprises steps of: performing wavelet noise reduction and EMD decomposition on the original vibration signals of a bearing in different fault states to obtain a plurality of IMF components; selecting, by quantitatively computing the correlation of each IMF component and the corresponding original vibration signal, the first h IMF components including the main fault information of the bearing as an object from which fault characteristic information is extracted, and extracting the characteristic parameters from the IMF components to form a original characteristic set; determining the sensitivity factor of each characteristic in the original characteristic set according to a distance evaluation method and constructing a sensitive characteristic set; inputting the sensitive characteristic vector of a training sample in the fault sample of the bearing into a SVM to be trained, optimizing the kernel function parameter g and the penalty factor c of the SVM according to a genetic algorithm, and identifying the fault of a tested sample. The method may reduce the dimensionality of the fault characteristic vector and the computational scale of a classifier, and increasing fault diagnosis accuracy of the antifriction bearing.

The invention relates to a fiber link fault recognition method, a device and a system. The method comprises the following steps: detecting power of one or a plurality of optical network units in real time; when detecting a fault in the fiber link corresponding to a certain optical network unit, extracting at least two upstream optical power values in the fiber link fault occurrence process; and according to the upstream optical power values in the fiber link fault occurrence process, recognizing the fault type of the fiber link corresponding to the optical network unit. The fiber link fault recognition method of the embodiment of the invention detects whether a fault exists in the fiber link corresponding to the optical network unit in real time by detecting the power of the optical network units in real time. When detecting a fault in the fiber link corresponding to the optical network unit, the upstream optical power values in the fiber link fault occurrence process are extracted, and the fault type of the fiber link is recognized in real time according to extracted power values.

The invention discloses a new method for RAIM (receiver autonomous integrity monitoring) based on a satellite selecting algorithm in a multimode satellite navigation system. The method comprises the steps of first determining space position information of satellites according to a navigation message and eliminating satellites with a small elevation angle according to a shielding angle; determining an observation matrix including only one clock correction item according to clock correction conversion factors in the navigation message; selecting p satellites from N visible satellites so as to be used for positioning calculation of a receiver, acquiring a satellite combination, which enables the GDOP (geometric dilution of precision) to be minimum, through the satellite selecting algorithm to act as calculating satellites, and determining a weight matrix in WLS (weighted least squares) according to parameters such as the carrier-to-noise ratio, the loop bandwidth, pre-check integral time and the like of satellite signals; carrying out RAIM availability detection according to a false alarm rate and a missed alarm rate which are preset by the receiver, and calculating a pseudo-range residual error threshold value after positioning according to the false alarm rate and a degree of freedom in Chi-squared distribution; carrying out global detection at first, then carrying out local monitoring in a circumstance that a fault satellite exists, determining calculation satellites again through satellite selection, and finally carrying out positioning calculation through selecting satellite combinations within the threshold value. The method disclosed by the invention is simple, high in fault recognition rate, not only applicable to multi-mode and multi-fault satellite navigation systems, but also applicable to single-mode and multi-fault satellite navigation systems, thereby providing new ideas for carrying out RAIM by a modern GNSS (global navigation satellite system).

A fault identification system consisting of multiple reasoning engines and the blackboard analyzes alarm information and the associated contextual information to identify faults. The contextual information associated with an alarm is derived by analyzing the alarm along four spaces, namely, transaction-space, function-space, execution-space, and signal-space. The reasoning engines associated with these spaces infer and/or validate the occurrences of faults. Transaction reasoning engine, using the associated knowledge repository, processes the generated alarms to infer and validate faults. Monitor reasoning engine, using the associated knowledge repository, processes domain specific monitor variables to infer faults. Execution reasoning engine, using the associated knowledge repository, processes execution specific monitor variables to infer and validate faults. Function reasoning engine, using the associated knowledge repository, reasons to infer and validate faults. Signal reasoning engine, using the associated knowledge repository, processes hardware specific and environment variables to infer and validate faults. Global reasoning engine moderates the inferences and validations by other reasoning engines to provide consolidated fault inference. The invention also provides a process, "design for diagnosis," for designing electronic systems with maximum emphasis on fault diagnosis.

An apparatus, system, and method are disclosed for reinitializing serialization data in a file server. The apparatus includes a failure recognition module, a discard module, and a serialization module. The failure recognition module recognizes a file system serialization failure on a file server. Upon recognition of the serialization failure, the discard module discards existing serialization data located in a first memory address space, such as a file server address space. In certain embodiments, the entire file server address space may be destroyed by the operating system. The serialization module then generates new serialization data from existing connection/position data. The connection/position data is located in a second address space, such as a client address space, that is maintained during the serialization reinitialization process. Containing and rebuilding the serialization data in this manner beneficially prevents system outages, reduces downtime, and decreases the likelihood of subsequent serialization deadlocks.

A failure identification part identifies a switching element pair having off-failure, in which a FET of the switching element pair in a first inverter part is disabled to turn on. A failure-time control part controls other switching element pairs and of the first inverter part based on failure-time phase current command values calculated as a function of a rotation position and a q-axis current command value. The failure-time control part controls a second inverter part normally. A motor is persistently driven with the minimum reduction in motor torque, even when the FET fails.

The invention particularly discloses an automatic rapid protection control method of a novel feeder. The automatic rapid protection control method comprises the following steps of: 1, mounting an STU (smart terminal unit) on each circuit switch and each interconnection switch in a network distribution structure, configuring a protective element into each STU, connecting the adjacent STUs, forming an annular network, and finally, connecting the annular network to an automatic main station of the feeder; 2, configuring each element in network distribution; 3, rapidly identifying a fault by the STUs according to local and adjacent current information and switch position information; 4, transmitting the fault identifying result to the adjacent STUs and the automatic main station of the feeder through a communication network by the STUs, and 5, carrying out isolation and power supply restoration on the fault. The automatic rapid protection control method has the beneficial effects that: an FTU (feeder terminal unit) in an original feeder is upgraded into the STU with intelligent judgment ability; and the fault section can be rapidly located by the local and adjacent current information and switch position information, so that isolation of a fault area and the power supply restoration of a non-fault area are achieved.

The present invention discloses post-wavelet analysis treating method and device for electric power transient signal. The treating method for electric power transient signal after wavelet analysis and before feeding to the electric power monitoring center includes the following treatment on wavelet coefficient: the extraction of module maximum and the detection of irregularity; the statistics and cluster analysis of wavelet coefficient; neural network classification; energy analysis; and wavelet entropy calculation. The present invention can extract the characteristic of electric power transient signal for the application in traveling wave ranging, fault recognition, electric energy quality analysis and equipment fault diagnosis in the transmission line of power system.

A fault identification system analyzes alarm information and the associated contextual information to identify the occurred faults. The contextual information is based on usecases, transactions, and functions associated with the electronic system under consideration. Multiple detectors that form part of knowledge repositories are used in the process of fault identification.

The invention discloses a wind turbine gear box fault recognition method. The method comprises the following steps: historical wind turbine gear box operation data in a certain time range are acquired; autocorrelation analysis is adopted for carrying out wavelet de-noising processing on the historical data; through fast Fourier transform, time domain and frequency domain characteristic parameters in the historical data after de-noising are extracted; a kernel principal component analysis method is adopted to carry out dimensionality reduction on the characteristic parameters, and several nonlinear principal elements with the maximum variance cumulative contribution rate are extracted; the nonlinear principal elements extracted by the historical gear box normal operation data are used for building a normal model, a support vector machine is used for training to guide the nonlinear principal elements extracted by later gear box operation historical data to the model after training, and thus, the gear box fault is recognized. The vibration signal processing ability is improved, and an important role is played in gear box fault recognition.

The invention discloses a method and a system for track traffic failure recognition based on improved Bayesian algorithm. The method comprises the following steps of: 1) determining various failure modes and corresponding monitoring values of each traffic device according to circuit structure of the traffic device, and building a failure model aiming at each failure mode and corresponding monitoring value; 2) recognizing a parent child relation among the monitoring data according to the failure model, thus obtaining a standard failure sample data; 3) training with the standard failure sample data through a Bayesian algorithm to obtain a failure recognition model, wherein weight of a parent node in the failure recognition model of each failure mode is greater than that of a child node; 4) monitoring and acquiring various monitoring values of the traffic device in real time, and recording time sequence of the monitoring values; 5) recognizing data through the failure recognition model, and determining corresponding failure. By the method and the system, accuracy of failure recognition is improved, failure repair time is reduced, the device can perform failure self-diagnosis, and traffic safety is guaranteed in the operation and maintenance aspect and the device aspect.

The invention relates to a high-voltage transmission line fault identification method based on computer vision, which relates to the technical field of high-voltage transmission line running state monitoring. The invention aims at solving the problem of high false alarm rate of the existing high-voltage transmission line on-line monitoring system. 11) carrying out edge detection on the transmission line image according to the edge detection algorithm, a strong edge image is obtained, and edge endpoints and edge directions are obtained from the strong edge image. Since the gradient direction ofthe edge endpoints is perpendicular to the edge direction, an edge connection window is selected according to the gradient direction of the edge endpoints, and edge connection points are selected inthe edge connection window according to a Hough transform method, and the edge connection points are connected into an edge image. Step 2, screening the transmission lines from the edge images of thetransmission line images by adopting a transmission line detection algorithm based on phase grouping; Step 3, the transmission conductor is processed to identify the fault on the transmission line. Itis used to identify transmission line faults.

The invention provides a feature-processing-based complex equipment fault diagnosis method. The method comprises the following steps: step one, collecting an action current signal in real time; step two, carrying out segment division on the action current curve; step three, carrying out segment division on an action curve; step four, constructing a high-dimensional feature representation data setof an equipment action current curve; step five, carrying out feature selection on the high-dimensional feature representation data set; step six, carrying out feature extraction on the high-dimensional feature representation data set; step seven, carrying out division on the feature representation data set; step eight, carrying out optimizing solution on parameters of an SVM; step nine, carryingout SVM supervision learning to obtain a fault diagnosis model; and step ten, verifying the diagnosis accuracy rate of the fault diagnosis model by using testing set data. Therefore, the feature-processing-based complex equipment fault diagnosis method is realized; and the fault diagnosis classifier is realized by the parameter-optimized SVM method and thus the fault identification and analysis ofthe feature number of the working current curve of the equipment are completed.

An apparatus, method, and system are provided for determining a location of an error source. Equalization coefficients may be retrieved and an average period of time between localized peak amplitudes may be determined. The average period of time may be multiplied by a velocity of propagation associated with a communication channel to determine an approximate location of the error source. The equalization coefficients may correspond to the inverse of the frequency response associated with the communication channel and may be updated over time using replacement or combination (e.g., convolution) techniques.

The embodiment of the invention provides a photoelectric system battery pack string fault identification method, device and equipment. The method comprises the steps that at least two sets of I-V values of a first battery pack string in a photoelectric system are acquired; fitting processing is performed by adopting a predetermined pack string physical model according to the at least two sets of I-V values so that at least one feature parameter of the first battery pack string is obtained; and the at least one feature parameter is compared with a standard feature parameter which is acquired in advance and whether the first battery pack string fails to work is determined, or curve fitting processing is performed on the acquired data through the pack string physical model so that the method can be widely applied, the feature parameters obtained through integrated processing of all the actually measured data of the battery pack strings are compared with the standard feature parameters when failure does not occur, misjudgment caused by test error of few points does not occur and judgment does not depend on the environment, and thus the scheme is not influenced by the inconsistent environment and processing efficiency and accuracy of pack string fault identification can be effectively enhanced.