25 results about "Fault detection and identification" patented technology

The invention belongs to the technical field of fault detection, and relates to a high-voltage transmission line fault detection and identification method. The method comprises the following steps of: dividing candidate fault sections according to a topological structure by synchronously acquiring steady-state and transient-state traveling wave signals of key nodes of a power grid; identifying a fault by using a multi-feature fusion criterion and extracting traveling wave features; executing mode recognition-based steady-state section judgment and multi-terminal ranging and polarity verification-based transient positioning in parallel to generate two types of positioning result sets; and finally, carrying out intelligent fusion judgment on the two types of results under topological constraints. According to the method, the problems that a traditional single-point signal analysis method cannot determine a fault section, lacks space positioning capability and is insufficient in adaptability are solved, section-level accurate positioning of the fault is realized, and the positioning accuracy, robustness and fault processing efficiency are remarkably improved.

The invention provides a method and a system for improving the self-healing capability of a highway micro-grid in extreme weather, and relates to the technical field of power system automation. The method comprises the following steps: deploying a sensor to collect real-time operation data, and combining meteorological data to generate an integrated system state data set through fusion processing; the digital twin engine generates system state prediction data through state estimation and dynamic simulation; the random multi-objective optimization model solves and generates a preventive scheduling instruction according to the above, and controls a power generation unit, an energy storage unit and a load unit to adjust operation points; fault detection and identification are carried out through residual analysis, a self-healing control instruction sequence is generated by using a sequence decision model, the switch equipment is controlled to isolate faults and restore power supply, closed-loop management from prediction and scheduling to self-healing is realized, and the power supply reliability and rapid recovery capability of the highway microgrid in extreme climate are improved.

The invention relates to the technical field of power distribution. The invention discloses a power distribution cabinet wire fault detection and identification method, which is characterized in that a plurality of wires with different specifications are arranged in a power distribution cabinet, and the method comprises the following steps: obtaining real-time operation parameter data of the plurality of wires, and determining a fault wire based on a reference parameter set of normal work of a to-be-detected wire and a deviation characteristic value relation of real-time parameters; fault parameter data of the faulty electric wire are input into a multi-layer fault identification model, the model comprises a plurality of sub-identification units connected in sequence, each unit detects different types of faults, and finally a fault mode is obtained. According to the method, at least three parameters are acquired through distributed sensing, and data reliability is guaranteed through noise reduction and normalization processing. On the basis of a double-threshold criterion and dynamic weight calculation, faulty electric wires are accurately distinguished, and misjudgment and missed judgment are completely eradicated. The multi-layer model carries out progressive detection, an emergency fault is preferentially recognized, and the sub-recognition units are matched with an exclusive algorithm to improve the accuracy.

The application provides a weak fault feature extraction method for an autonomous underwater vehicle propeller, and belongs to the technical field of underwater vehicle fault diagnosis, and comprises two parts: fault feature enhancement and feature fusion. First, the application optimizes parameters by judging the Gaussianity of all modes of multi-source state signals and control signals through negative entropy, completes noise reduction, and extracts and enhances fault features based on a modified Bayesian algorithm. Then, the feature signals are divided into multiple time intervals, the faults occurring in each interval are taken as focal elements, all signals except the longitudinal velocity are subjected to first feature fusion, the first fusion result is subjected to second fusion with the feature signal of the longitudinal velocity, the fault features are further enhanced, and the monotonicity between the fault features and the fault degree is presented. The application can provide a basis for subsequent fault detection and identification, and is particularly suitable for state monitoring of autonomous underwater vehicle propellers.

The invention discloses a few-sample fault diagnosis method based on a multi-scale physical information neural network, and belongs to the technical field of fault diagnosis. The method comprises the following steps: step 1, constructing a bearing vibration signal data set containing multiple working conditions, and preprocessing an original vibration signal; 2, inputting the vibration signal samples in the training set into a CCSWGAN network, generating a high-quality synthetic sample, and carrying out normalization processing on the high-quality synthetic sample; step 3, mixing the original sample and the synthetic sample and randomly disrupting the original sample and the synthetic sample to form training data, inputting the training data into an MCB-PII module, and performing multi-scale feature extraction and fault diagnosis; and 4, deploying the trained model to production equipment, and carrying out fault detection and identification on vibration signals collected in real time. According to the method, the problems of unstable performance and insufficient adaptability of the model under complex working conditions are effectively avoided, so that higher accuracy and reliability are provided for bearing fault diagnosis.

The invention, which belongs to the technical field of electric power operation and maintenance management, discloses an operation and maintenance fault detection and identification system comprising a preparation analysis module, an acquisition module, an edge end and a cloud end. The preparation analysis module is used for performing preparation analysis on operation and maintenance fault detection and generating a corresponding equipment information graph according to target equipment; determining a target acquisition data type of each target device according to the device information graph, classifying each target device according to the target device information and the target acquisition data type to obtain edge classes, and configuring a corresponding edge end for each edge class; the acquisition module is used for performing data acquisition on each target device to obtain operation and maintenance acquisition data; the edge end is used for processing the operation and maintenance collection data to obtain target collection data and sending the target collection data to the cloud end; the cloud comprises a fault diagnosis module, and the fault diagnosis module is used for analyzing the received target collection data to obtain a fault diagnosis result.

The present invention provides a method and apparatus for processing equipment sensor data for generalized fault diagnosis, which relates to the field of data processing technology. It determines standardized calculation parameters for multiple source domains based on multiple equipment types or operating conditions, and performs standardized processing on the sensor data of the target domain equipment accordingly, eliminating the scale differences caused by the inherent characteristics of the equipment and the sensor configuration. Furthermore, a preset autoencoder is combined with a dynamic feature decoupling matrix to decouple the time-frequency features in the mixed signal, thereby improving the interpretability and separability of the feature space. In addition, the nonlinear transformation term is used to enhance the model's ability to express complex signals, thereby extracting more representative low-dimensional features. Based on this, it can ensure that accurate and reliable fault detection and identification can be achieved under different equipment and different operating conditions.

The invention discloses a multi-mode on-orbit component irradiation fault diagnosis method and a micro module. The method comprises the following steps: acquiring voltage and current data of a to-be-tested device through an analog end circuit module; performing data preprocessing on in-phase data input and orthogonal data input acquired by the ADC; building a neural network as a fault diagnosis module; the data source of fault diagnosis is the data preprocessing output of the preceding stage; the method comprises the following steps: establishing a reverse neural network, combining a data preprocessing module, establishing a neural network training platform, training and testing the neural network through a fault data set, adaptively adjusting the learning rate of each parameter in combination with an Adam algorithm, extracting weight and bias parameters of the trained neural network, and transmitting the weight and bias parameters to an FPGA-end feedforward neural network; and fault diagnosis: inputting the preprocessed data into an FPGA-end feedforward neural network to complete calculation and output of a fault result. According to the method, more irradiation fault types are detected, the detection period is shorter, the detection precision is higher, and after training is completed, irradiation fault detection and recognition can be independently carried out according to collected information.

The application belongs to the technical field of smart grid fault detection and identification, and relates to a power distribution network intelligent inspection and fault diagnosis method based on multi-source information fusion. The method comprises an unmanned aerial vehicle inspection platform, an airborne edge computing terminal, a cloud operation and management platform, a PMS system and a mobile terminal. The application synchronously collects visible light images, infrared thermal images and independent temperature sensing data through the unmanned aerial vehicle platform, and utilizes deep learning and multi-modal fusion technology to realize data complementation and collaborative analysis at a feature level, so that real-time and accurate identification of power distribution network lines and equipment faults is finally completed.

The present application belongs to the technical field of fault detection, and relates to a high-voltage transmission line fault detection and identification method. The present application synchronously collects steady-state and transient traveling wave signals of key nodes of a power grid, divides candidate fault sections according to a topological structure; further utilizes a multi-feature fusion criterion to identify faults and extract traveling wave features; performs steady-state section discrimination based on pattern recognition and transient positioning based on multi-terminal ranging and polarity verification in parallel, to generate two types of positioning result sets; finally, intelligently fuses and judges the two types of results under topological constraints. The method solves the problems that a traditional single-point signal analysis method cannot determine a fault section, lacks spatial positioning capability and is insufficient in adaptability, realizes accurate positioning of a fault section, and significantly improves positioning accuracy, robustness and fault handling efficiency.

The present invention discloses an adaptive real-time multipath elimination and robust positioning method based on non-Gaussian distribution. The method does not make an assumption about the number of satellites that have faults or deviations, but modifies the Gaussian distribution assumption of errors in a traditional positioning model and converts it into a Gaussian mixture distribution, i.e., a non-Gaussian distribution. Parameters are solved by a maximum likelihood method based on real-time observation data, and the probability distribution of the deviation range of each satellite fault is adaptively calculated. The method can be used for identification and robust positioning under multiple faults, and can also be used for robust positioning and multipath elimination in a multipath environment. The present invention solves the shortcomings of existing RAIM and robust positioning methods. Currently, existing fault detection and identification methods have a large amount of computation, rely on a priori assumptions about the number of faults, and have a high misjudgment rate. The method provided by the present invention has a high fault detection success rate, a small amount of computation, high speed, high accuracy, and robustness.

This invention provides a method and system for detecting faults in distribution network lines based on unmanned aerial vehicle (UAV) inspection, belonging to the field of power grid fault detection and identification technology. The method includes: determining a target line based on line anomaly information and obtaining the path information of the target line; dispatching a UAV to inspect along the target line direction, obtaining magnetic field measurements, UAV position data, and the distance between the UAV and the target line, thus obtaining a magnetic field sampling sequence; constructing a magnetic field distribution map along the target line based on the preprocessed magnetic field sampling sequence; determining suspected anomaly locations, fault types, and fault location information based on the magnetic field distribution map, and outputting the magnetic field distribution map, fault type, and fault location information to a display terminal for display. This method enables rapid inspection of abnormal distribution network lines, achieving identification of suspected anomaly locations, fault type discrimination, fault location information determination, and visual display, thereby improving the efficiency of distribution network line fault inspection and maintenance.

The application provides a highway micro-grid self-healing ability improvement method and system under extreme weather, and relates to the technical field of power system automation. The method collects real-time operation data through the deployment of sensors, generates integrated system state data set through the fusion processing of meteorological data; the digital twin engine generates system state prediction data through state estimation and dynamic simulation; the random multi-objective optimization model solves the preventive scheduling instruction accordingly to control the generation, energy storage and load unit to adjust the operating point; the residual error analysis is carried out for fault detection and identification, and the sequence decision model is used to generate the self-healing control instruction sequence to control the switch equipment to isolate the fault and restore power supply, realizing the closed-loop management from prediction, scheduling to self-healing, and improving the power supply reliability and rapid recovery ability of the highway micro-grid under extreme climate.

The invention discloses a new energy direct current power distribution network fault identification method and system, and belongs to the field of new energy direct current power distribution network control and protection. After a fault occurs, controlling all the power electronic direct-current transformers to start a current limiting strategy, and selecting the power electronic direct-current transformers on two feeder sides to adjust phase shift angles so as to inject a dual-frequency detection signal; listing a network equation based on a one-mode circuit fault-free model, collecting voltage and current signals of each feeder line, and solving line parameters and tail end equivalent capacitance; line fault identification is realized by calculating the relative capacitance deviation and combining a preset criterion; and if all the feeders have no fault, identifying a bus fault in combination with the feeder current according to a bus criterion. The method does not need to depend on communication, adapts to multiple feeder types, can accurately recognize line and bus faults, and effectively improves the fault detection and recognition capability of the new energy DC power distribution network.

The invention belongs to the technical field of space antenna fault detection and identification, and relates to a space antenna fault detection and identification method based on three-dimensional Gaussian sputtering, which comprises the following steps of: performing coarse positioning on the position of a space antenna hinge by using an optimized YOLOv5 model; according to the position of the space antenna hinge, tracking of the space antenna hinge and calibration of a viewpoint pose are achieved through continuous image streams; constructing a 3DGS model of an intact space antenna hinge by using a three-dimensional Gaussian sputtering 3DGS technology, performing defect detection on the tracked and calibrated space antenna hinge, and quantitatively analyzing the size of the defect of the space antenna hinge; according to the invention, monitoring blind areas and fault omission can be reduced; shooting points are accurately estimated, and antenna details are restored with high precision; time resources are saved, and the detection efficiency is improved; three-dimensional Gaussian sputtering is combined with a loss function, a fault area is accurately recognized, and misjudgment and missed judgment are reduced.

The present application relates to quantum magnetic sensing and intelligent detection technical field, specifically a kind of non-contact electronic equipment ultrafast electromagnetic fault detection identification device and identification method based on diamond NV color center.This identification device includes efficient excitation microstrip array antenna module, electromagnetic fault detection identification main control board, laser modulation and coupling interface unit, photoelectric detection control interface unit, laser heat management copper-based heat dissipation assembly, voltage follower circuit control switch unit, pixel-level quantum magnetic sensing unit group, laser control circuit mainboard and photoelectric detection control mainboard;Wherein each pixel-level quantum magnetic sensing unit group includes three narrow linewidth laser excitation source, three diamond NV color center quantum magnetic sensitive element, three narrow-band optical filter and three photoelectric detector.The identification device has the characteristics of fast detection speed, high sensitivity, strong real-time, low power consumption and no need to contact the measured target, etc., can effectively improve the efficiency and accuracy of complex electronic equipment electromagnetic fault diagnosis.

The present invention discloses a multi-source fault detection and identification method for a DC power supply cable of a submarine observation network. The multi-source fault detection and identification method for the DC power supply cable can achieve the purpose of detecting and identifying multiple types of faults and multi-point faults of the DC power supply cable, including the connection of the multi-source fault detection loop of the submarine observation network cable, the detection and data acquisition of the DC power supply cable, the establishment of a fault model for a long-distance power transmission cable, and the judgment of multi-source fault detection results, etc. The beneficial effect of the present invention is that it can accurately, safely, real-timely, and efficiently detect and identify multiple types of faults and multi-point faults of the DC power supply cable, provide scientific and reliable data for the maintenance and repair of the energy supply network of the submarine observation network, and realize its long-term reliable operation.

The present invention discloses a tunnel three-dimensional fault detection and identification method and system, which relates to the technical field of tunnel defect detection, and comprises the following steps: acquiring tunnel three-dimensional data, tunnel 2D image data and current positioning information in real time; associating the tunnel three-dimensional data, tunnel 2D image data and current positioning information to form a current identification, and recording the current identification in real time; extracting suspected defects from the tunnel three-dimensional data and tunnel 2D image data respectively, and generating a corresponding tunnel three-dimensional suspected defect list and tunnel 2D image defect list; associating and reviewing the tunnel three-dimensional suspected defect list with the tunnel 2D image defect list through the current identification to confirm the authenticity of the three-dimensional suspected defect; performing ellipse fitting calculation on the tunnel three-dimensional data corresponding to the real three-dimensional suspected defect to obtain suspected defect tunnel parameters, and comparing the suspected defect tunnel parameters with the reference parameters to generate a tunnel parameter comparison report.

The invention discloses an open-circuit fault diagnosis method and device for a driver of an electric excavator, and the method comprises the following steps: firstly, obtaining a three-phase current signal of an inverter; filtering and smoothing the current signal; performing positive and negative half-wave separation on the current signal to obtain an odd symmetric component and an even symmetric component; calculating an integral mean value, constructing a phase current characteristic vector, and comparing the maximum value of the integral mean value with a detection threshold value to judge whether an open-circuit fault occurs or not; calculating a positioning threshold value in real time, comparing the phase current characteristic vector with the positioning threshold value, and separating an abnormal value; and finally, obtaining a fault positioning result according to the index relation between the abnormal value and the inverter switching tube. According to the method, information containing fault characteristic essence can be extracted only by using three-phase current data, a phase current vector is constructed through odd-even symmetric components, and a distributed adaptive threshold algorithm is constructed, so that open-circuit fault detection and identification of the inverter module under a complex working condition can be realized without complex calculation.

This invention proposes a sensor fault monitoring and failure information reconstruction method and system. First, it uses a robust improved principal component analysis method for sensor fault detection and identification in nuclear power plants. Then, it reconstructs the failure information of nuclear power plant sensors based on maximum mutual information coefficients, convolutional autoencoders, long short-term memory networks, and self-attention mechanisms. Finally, it uses an improved particle swarm optimization algorithm for automatic hyperparameter optimization. This method achieves more robust sensor fault detection and faster, more accurate sensor failure information reconstruction. It can accurately detect abnormal readings from steam generator water level sensors, accurately determine whether the abnormality is caused by a "false water level" or a sensor malfunction, and accurately and quickly reconstruct the abnormal water level information of the steam generator, ensuring the normal operation of the control system and improving the safety and economy of nuclear power plants.

The invention relates to a fault detection and identification method and device for a current collection line of a new energy field station, and the method comprises the steps: determining a fault phase of the current collection line, inputting an external power supply based on the fault phase, and obtaining a parameter value of a sensor in the current collection line; based on the parameter value and a preset error value, judging whether the line to which the sensor belongs has a fault, and if so, obtaining fault data corresponding to the fault; and matching the fault data with fault features stored in a fault information database, and if matching succeeds, judging and identifying the fault data based on a matching result. By executing the above method, fine positioning inspection is performed on the fault section based on the parameter values obtained by the sensor, the fault range is given to find the fault point, and the fault finding time can be shortened, so that power transmission is recovered as soon as possible after tripping, and the lost generating capacity is reduced as much as possible.

The invention discloses a rudder control driving system current sensor fault detection and identification method based on coordinate transformation. The method is suitable for permanent magnet synchronous servo and the situation that only two-phase current sensors are used. According to the method, the phase current of the rudder control driving system and the reference current of the control loop are converted into the first static coordinate system space and the second static coordinate system space which meet fault decoupling by adopting specific coordinate conversion, so that the fault of a certain phase current is only represented in a specific variable and is prevented from being confused with phase current faults of other channels; through designing a reasonable detection statistic and a fault detection threshold, identification of a fault channel current sensor is realized.

The application discloses a kind of improved hybrid kernel auxiliary stationary variable analysis fault detection and identification method, steps include: using hybrid kernel to explore typical stationary variable (CSVs), singular value decomposition (SVD) and iterative modeling process, stationary subspace analysis (SSA), the contribution of two statistics and index difference is calculated;First, consider past, future matrix and the multi-view nonlinear mapping of hybrid kernel, explore the time correlation and weak stationarity of typical stationary variable;The efficiency improvement of singular value decomposition and iterative modeling process is proposed to reduce the calculation cost and accurately estimate typical stationary variable.In addition, by retaining the smooth information in the residual that has no autocorrelation, to further analyze the stationary variable (SSVs) generated using stationary subspace analysis.By intuitive explanation of dynamic and static stationary information, the corresponding two statistics and index difference contribution are calculated to detect and identify faults.

This invention discloses a method for fault detection and identification in a navigation system cluster based on common-mode combination of cooperative navigation information. It utilizes the cooperative system to construct common-mode pseudorange residuals to improve the fault detection sensitivity of the GNSS receiver, and leverages the cooperative characteristics of the cluster system to enhance the efficiency of identifying faulty satellites. By combining and modeling the observations of auxiliary sensors in the cooperative navigation system with the pseudorange observations of the GNSS receiver, the method can detect whether auxiliary sensors have malfunctioned after monitoring the integrity of the GNSS receiver. This method can address various factors that induce pseudorange faults in complex environments, employing decentralized fault handling to improve the fault detection and identification rate of the GNSS receiver in the cooperative navigation system. Furthermore, it detects and identifies faults in auxiliary sensors within the cooperative navigation system, improving the overall integrity of the cooperative navigation system and ensuring its accuracy and robustness.

The invention provides an equipment sensing data processing method and device oriented to generalization fault diagnosis, relates to the technical field of data processing, and aims to determine multi-source domain standardized calculation parameters based on multiple equipment types or operation conditions and perform standardized processing on sensor data of target domain equipment according to the parameters. And scale difference caused by inherent characteristics of equipment and sensor configuration is eliminated. Furthermore, a preset auto-encoder is combined with a dynamic feature decoupling matrix to decouple the time-frequency features in the mixed signal, and the interpretability and separability of the feature space are improved. In addition, the expression ability of the model to complex signals is enhanced by means of nonlinear transformation terms, so that more representative low-dimensional features are extracted. Based on this, it can be ensured that accurate and reliable fault detection and recognition can be achieved under different equipment and different working conditions.