37results about How to "Implement fault detection" patented technology

The invention relates to a circuit breaker fault diagnosis system. Relates to the technical field of high-voltage circuit breaker fault detection. The system comprises a control module, a switching value acquisition module, a current acquisition module and a displacement acquisition module. The input end of the control module is respectively connected with the output ends of the switching value acquisition module, the current acquisition module and the displacement acquisition module; the switching value acquisition module acquires opening and closing positions of the circuit breaker; based on the opening and closing position of the circuit breaker, a control module collects vibration information through a vibration sensor, and obtains vibration information, current information and stroke information of a circuit breaker touch stroke in the opening and closing process of the circuit breaker; and the control module extracts feature vectors corresponding to the vibration information, the current information and the stroke information, obtains a composite feature vector, and compares the composite feature vector with a preset value to realize fault detection of the circuit breaker. By adopting the system, the detection accuracy of circuit breaker fault detection can be improved.

The invention discloses a voltage fault detection device of a three-phase alternating current power supply, a motor controller and a voltage fault detection method thereof, and the device comprises a sampling unit which carries out the separation sampling of each phase of current in three-phase current from a rectification front end, and obtains the sampling voltage of each phase; the step-down unit is used for carrying out step-down on the sampling voltage of each phase to obtain the step-down voltage of each phase; the clamping unit is used for clamping the reduced voltage of each phase to obtain clamping voltage of each phase; the filtering unit is used for filtering the clamping voltage of each phase to obtain filtering voltage of each phase; and the control unit determines whether the phase voltage of each phase of the three-phase alternating-current power supply has a fault according to the filtering voltage of each phase so as to protect the three-phase alternating-current power supply and a load thereof. According to the scheme, the three-phase input current of the three-phase alternating-current power supply is separated and sampled from the rectification front end of the input side of the three-phase alternating-current power supply to obtain the sampling voltage, and fault detection is performed after voltage reduction, clamping and filtering, so that the accuracy of fault detection is improved.

The invention relates to the technical field of data analysis, and discloses a slurry pump fault detection and service life prediction system and method based on big data. According to the method, firstly, a slurry pump vibration signal is obtained, an abnormal vibration signal is detected and deleted, and then noise reduction processing is conducted on the slurry pump vibration signal; secondly, after the denoised slurry pump vibration signal is subjected to segmented aggregation approximation and Grubby angle field processing, a slurry pump vibration signal image is generated, the characteristics of the slurry pump vibration signal image are extracted, a convolutional neural network is trained, convolutional neural network parameters are optimized based on an electric eel foraging optimization algorithm, a convolutional neural network recognition model is obtained, and a recognition result of the convolutional neural network is obtained; fault detection of the slurry pump is realized; and decomposing the IMF component of the slurry pump vibration signal, training the LSTM neural network to obtain an LSTM neural network prediction model, and outputting a slurry pump life prediction value. The purposes of fault detection and service life prediction are achieved by processing the vibration signal of the slurry pump, and the method is accurate and objective.

The invention relates to a relay fault detection circuit and a fault detection method, the relay fault detection circuit comprises a relay driving circuit, a driving current sampling circuit, an amplifying circuit and a signal shaping circuit, the output end of the relay driving circuit is connected with a coil of a relay, and the other end of the coil of the relay is connected with the driving current sampling circuit; the output end of the driving current sampling circuit is connected with the amplifying circuit, and the output end of the amplifying circuit is connected with the input end of the signal shaping circuit; the output end of the signal shaping circuit is connected with a controller. The relay fault detection circuit is used for collecting the relay driving current signal and the relay pull-in current signal, the output square wave signal is combined with the relay fault detection method to carry out fault judgment on the relay, the relay does not need to be loaded, the safety is high, integration is convenient, and the universality is high.

The invention discloses a low-current arc fault detection method based on time-frequency domain disturbance and related equipment, and the method comprises the steps: recognizing a time point where disturbance changes occur through an improved CUSUM algorithm, positioning a current data standard deviation, and then achieving the arc fault detection according to the changes of even harmonics before and after the time point. The circuit breaker solves the problems that a traditional circuit breaker can only detect short-circuit faults and overload faults by means of a line current rigid threshold value, and small-current arc faults are often missed and falsely detected due to small current change amplitude.

The invention provides a direct-current floating ground system, a fault detection method and device, a medium and a program product. The direct-current floating ground system comprises a direct-current power supply which is not grounded; the load is electrically connected with the direct-current power supply; the first module is used for acquiring a first electrical parameter of a load and transmitting the first electrical parameter to the second module; the second module is used for acquiring a second electrical parameter of the direct-current power supply and determining whether the direct-current floating ground system breaks down or not according to the second electrical parameter and the first electrical parameter; wherein the second module and the first module are connected to form a common reference plane, the level of the reference plane is not equal to the grounding level, and the first electrical parameter and the second electrical parameter are both electrical parameters based on the reference plane.

The invention relates to the technical field of Tokamak magnetic probe fault detection, in particular to a real-time fault detection method for a Tokamak magnetic probe. According to the technical scheme, the method comprises the following steps that neural network model training data are collected to construct a training database, and physical parameters related to magnetic probe signals serve as model input; a neural network model with multiple coding layers and decoding layers is adopted to capture the evolution characteristic of the magnetic probe signal in time, and the magnetic probe signal in the subsequent time period is predicted based on the input time period; and inputting and transmitting the model to a trained neural network model to predict a magnetic probe signal in real time. According to the method, the fault detection of the magnetic probe diagnosis in the Tokamak device is realized by using the artificial intelligence algorithm, the calculation precision of the model is improved, and the calculation time of the model is greatly optimized, so that the real-time fault detection of the magnetic probe becomes feasible, and the method has relatively high universality.

The invention provides a fault detection method of slave station equipment and electronic equipment, and the method comprises the steps that a UPF network element receives a first data frame sent by master station equipment, determines a first addressing type of each slave station equipment according to command information in the first data frame, and determines a fault of each slave station equipment according to a first address value, a pre-designed numerical value and the first addressing type; generating first record information, sending a first data frame to each slave station device, receiving a returned second data frame, determining a second addressing type of each slave station device according to command information in the second data frame, generating second record information according to a second address value, the updated count value and the second addressing type, and sending the second record information to the slave station device. And sending the first record information and the second record information to a network management server, and when the first addressing type is consistent with the second addressing type and the first address value is consistent with the second address value, performing fault detection on each slave station device according to the pre-designed numerical value and the updated count value. And fault detection of slave station equipment is realized.

The present disclosure relates to a cloud edge end collaborative based digital twin system performance prediction and fault self-healing method, belonging to the field of digital twin, comprising: constructing a global performance prediction model of a digital twin body in the cloud; deploying a fault detection module in the edge node, detecting abnormal features in the sensor data stream using adaptive sliding window technology, and comparing the abnormal features with the prediction results through a multi-scale feature extraction algorithm; establishing a two-way authentication channel between the end device and the edge node; the edge node identifies the fault features and inputs a dynamic repair strategy code package to the end device; the cloud starts a virtual simulation engine to perform fault deduction, generates several repair schemes using the Monte Carlo tree search algorithm, and performs simulation verification to screen the optimal repair scheme; the optimal repair scheme is issued to the edge node through the blockchain and is synchronized to the end device for repair using the differential update mechanism; and the cloud dynamically reconstructs the loss function of the model. The performance prediction is accurate and the fault self-healing capability is strong.

The application discloses a fan fault detection board and a fan fault detection device. The fan fault detection board comprises a detection unit, a control unit, a state feedback unit, a current limiting unit, a main power input interface, a main power output interface, a fan input interface, a fan output interface, a feedback power input interface, a feedback power output interface, a state feedback power interface and a state feedback output interface. The application can feed back the running state of the fan to the upper computer through the state feedback output interface, for example, normal working of the fan or fault of the fan, so that the detection of the fan fault is realized.

The invention discloses a redundancy signal deviation fault diagnosis delay threshold calculation method based on difference joint distribution and a channel switching control process thereof, and solves the problem of redundancy signal deviation identification by constructing a new fault identification method. And performing modeling calculation on the redundant system according to the statistical characteristic parameters of the signals. Based on a joint normal distribution theory of redundant signal difference values, according to actual operation requirements of equipment, a corresponding false alarm rate and a corresponding omission ratio are respectively calculated by difference value conditional probabilities, an optimal deviation fault threshold value is determined, and a corresponding program algorithm is compiled. Accordingly, a novel and optimized fault detection switching process is constructed, the functions of fault identification and signal channel switching are achieved, and the stability and reliability of operation of the water-turbine generator set are improved.

The present invention provides a satellite navigation fault detection method based on motion state prediction, which obtains historical GNSS navigation information and performs smoothing to obtain smoothed navigation information, establishes an n-order motion state function model, brings the smoothed navigation information into the n-order motion state function model, and solves the motion state model parameters by the least square method; performs extrapolation of the navigation information at the current moment to obtain the extrapolated navigation information, and uses the extrapolated navigation information to determine whether the navigation information output by the GNSS at the current moment fails. The present invention uses a smoothing algorithm to smooth the historical motion state information, uses the smoothed motion state information and time to solve the parameters of the established motion state function model, and further extrapolates the motion information at the current moment through the solved motion state function, which can be used as a benchmark to realize fault detection of the navigation information output by the GNSS, and the method can realize fault detection of the GNSS without other auxiliary information.

The application discloses a meter reading method, device, equipment and medium for an electric energy meter. The method comprises the following steps: obtaining electric energy meter data of a to-be-read electric energy meter, wherein the electric energy meter data comprises service attribute data, communication state data and user power consumption data; determining a priority score of the to-be-read electric energy meter based on the electric energy meter data; determining a meter reading strategy of the to-be-read electric energy meter based on the communication state data and the priority score, and performing a meter reading operation on the to-be-read electric energy meter based on the meter reading strategy; when the meter reading operation is abnormal, obtaining signal feature data of the to-be-read electric energy meter, determining an abnormal reason based on the signal feature data, and generating a corresponding abnormal repair strategy. The method calculates a priority score through multi-dimensional electric energy meter data, determines a meter reading strategy based on the communication state data and the priority score, and performs a meter reading operation, thereby realizing dynamic matching of communication resources and meter reading demands, and improving meter reading execution efficiency and communication resource utilization efficiency.

The invention provides a CNN three-phase rectification circuit fault detection method based on a CBAM attention mechanism. The method comprises the steps of receiving time domain feature vector samples corresponding to a rated number of simulation sample data; converting the collected sample into a two-dimensional grayscale image, and substituting the two-dimensional grayscale image into a network for learning; a CNN network combining a multi-scale convolutional layer and a CBAM attention mechanism is designed, and an improved depth separable convolutional layer is used to replace a traditional convolutional layer. The method and the system are suitable for rectification power supply fault detection tasks and have universality. On the basis, circuit fault detection is achieved, and the technical problem that in the prior art, a rectifying circuit fault detection method is lacked is solved.

The utility model relates to a battery management system and battery equipment, if an over-limit alarm circuit detects that the temperature of a to-be-monitored battery cell exceeds the limit based on the temperature of the battery cell, a first signal is output to indicate that the temperature of the to-be-monitored battery cell exceeds the limit; and if the fault alarm circuit detects that the temperature monitoring circuit breaks down based on the cell temperature, a second signal is output to indicate that the temperature monitoring circuit breaks down. According to the scheme, the temperature monitoring circuit can be monitored through the fault alarm circuit while the temperature of the to-be-monitored battery cell is monitored through the temperature monitoring circuit, so that identification can be carried out when the temperature of the to-be-monitored battery cell exceeds the limit, and indication can be carried out when the temperature monitoring circuit breaks down. Therefore, the fault of the temperature monitoring circuit can be found in time, the condition of temperature over-limit false alarm caused by the fault of the temperature monitoring circuit is relieved, and the temperature monitoring accuracy of the battery cell is improved.

The application provides an elevator rotating part fault detection method, an electronic device and a program product. The method comprises: obtaining to-be-detected vibration data of a to-be-detected elevator rotating part; performing frequency domain feature extraction on the preprocessed to-be-detected vibration data to obtain to-be-detected features; mapping the to-be-detected features from a target domain to mapping features of a source domain based on a pre-established cross-domain mapping relationship through a self-encoder model; inputting the mapping features into a trained classification model to obtain a detection result of the to-be-detected elevator rotating part, the classification model being trained through a first vibration data set of a source structure, and the first vibration data set comprising a fault data set and a non-fault data set of the source structure. In this way, the fault detection of the elevator rotating part can be realized without using the fault data of the elevator rotating part for model training, and the problems of false positives and false negatives caused by the lack of fault data of the elevator rotating part and the failure of the model to learn fault features are avoided.

The invention discloses an oil-immersed transformer fault detection method. The method comprises the following steps: acquiring gas dissolution analysis data of an oil-immersed transformer in an early fault stage and constructing a training data set; constructing a decision tree model by taking the acquired data as input, calculating information gain and an information gain ratio, and selecting nodes; a gradient enhancement model is constructed and initialized; performing hyper-parameter optimization on the gradient enhancement model by adopting a Bayesian optimization scheme; training the gradient enhancement model to obtain an oil-immersed transformer fault detection model; and adopting the oil-immersed transformer fault detection model to carry out actual fault detection on the oil-immersed transformer. The invention also discloses a system for realizing the oil-immersed transformer fault detection method. According to the invention, the fault detection of the oil-immersed transformer can be realized, the reliability is higher, and the accuracy is better.

The present invention provides a method for detecting insulator faults of transmission lines based on artificial intelligence, comprising the following steps: obtaining historical insulator images of several transmission lines through a drone, and marking the status of the insulators in each of the images; preprocessing the images and using them as training data sets; the preprocessing includes Gaussian blurring, Gaussian noise addition, and image sharpening; constructing a fault detection model based on YOLO, inputting the training data set into the model for training, and updating the hyperparameters of the model; inputting the transmission line insulator images to be detected into the trained fault detection model, and obtaining the corresponding insulator status detection results. The present invention detects insulator faults based on artificial intelligence technology, effectively solves the technical problem of many types of insulator defects in the prior art, realizes the automatic detection of insulator faults, and significantly improves the efficiency and accuracy of insulator fault detection.

The invention relates to the technical field of rule matching, and discloses a fault detection method, device and equipment based on rule matching and a storage medium, and the method comprises the steps: obtaining sound information and vibration information corresponding to a vehicle when a fault signal of the vehicle is detected; obtaining vehicle image information of the vehicle from a preset vehicle image database, wherein the preset vehicle image database stores a global image of the vehicle collected in real time; determining a target fault component corresponding to the vehicle based on the sound information, the vibration information and the vehicle image information; and determining component information of the target fault component, and matching and determining target fault information corresponding to the vehicle based on the component information and a rule tree in the rule engine. According to the invention, the target fault information of the vehicle is determined based on the fault information of the target fault component of the vehicle and the rule tree in the rule engine, and the technical problem of low vehicle fault detection efficiency caused by long reasoning time of fault detection based on rule matching in the prior art is solved.

The invention provides a protection circuit, a digital quantity input module and electronic equipment, which are applied to the technical field of automation control, the circuit comprises a current limiting circuit, a diagnosis circuit and a controller, the current limiting circuit is connected between a contact power supply of a DI module and a first contact, the diagnosis circuit is connected with the current limiting circuit in parallel, and the controller is connected with the diagnosis circuit. The controller comprises a diagnosis port and an acquisition port, the diagnosis port is connected with a control end of the diagnosis circuit, the acquisition port is connected with a second contact of the DI module, and the controller outputs a diagnosis signal in a diagnosis mode, so that the current limiting circuit fails and detects the DI module according to a preset corresponding relation between the diagnosis signal and a feedback signal; the fault detection of the DI module is realized, and the controller outputs an operation signal in a working mode to control the diagnosis circuit to be switched off, so that the current limiting circuit limits the current flowing through the DI module. According to the circuit, fault diagnosis can be carried out on the DI module, current limiting protection can be provided, and the safety and reliability of the DI module can be effectively improved.

The utility model discloses a portable multifunctional machine tool fault detection device, and relates to the technical field of machine tool maintenance. The device comprises a mounting plate, a detection assembly is arranged on the upper surface of the mounting plate, and a grip assembly is further arranged on the lower surface of the mounting plate; the detection assembly comprises a detection shell fixedly connected to the upper surface of the mounting plate. According to the utility model, the odor sensor and the visual camera in the detection shell are used for carrying out fault detection on the machine tool in various modes, and the driving rack drives the gas collecting hood to rotate in a reciprocating manner, so that air on the machine tool is guided into the detection shell through the gas collecting hood for detection; the problems that in the prior art, the function is single, and fault detection cannot be conveniently conducted on the interior of the machine tool are solved, meanwhile, the mounting plate and the detection structure are conveniently held through the holding rod, the position and angle of the detection structure are adjusted through the second lead screw, the second U-shaped frame and the third U-shaped frame, and the problem that in the prior art, carrying is not convenient is solved.

The invention discloses a server fault detection testing device, and relates to the technical field of server fault detection. The server fault detection testing device comprises a bearing mechanism, a moving mechanism, a mounting bracket and a detection mechanism, the moving mechanism is installed on the bearing assembly, the moving assembly comprises a first moving assembly and a second moving assembly, the first moving assembly is movably arranged in the first direction, and the second moving assembly is movably arranged in the second direction; the mounting bracket is driven by a moving mechanism to move; the mounting bracket is provided with a plurality of mounting positions which are distributed at intervals along a third direction; the detection mechanism is installed at the installation position. According to the server fault detection testing device provided by the invention, the moving mechanism is arranged, so that the detection mechanism can be driven to move to different positions, fault detection of different positions of the server is realized, and the correctness of fault detection is effectively improved; in addition, the server can be conveniently placed on the bearing mechanism or taken out by the bearing mechanism.

The application discloses a current probe for non-contact cable fault detection, two flange connectors are arranged on a ring-shaped shielding shell, a first flange connector is used as a current injection probe, and a second flange connector is used as a current detection probe, a core wire of the first flange connector is connected with one end of a copper band, the other end of the copper band is fixed in the first half-circular ring-shaped shielding shell after being wound around a first half-circular magnetic ring and a second half-circular magnetic ring once, one end of a wrapped wire of the second flange connector is connected with a core wire, and the other end of the wrapped wire is fixed in the second half-circular ring-shaped shielding shell after being wound around a third half-circular magnetic ring and a fourth half-circular magnetic ring eight times. The original connection of the contact type cable fault detection needs to be disconnected, and the technical problem that the cable is damaged twice.

The application provides a battery pack fault detection method and device and a vehicle, and the method comprises the following steps: obtaining characteristic data combinations of each battery cell in the battery pack, wherein the characteristic data combinations comprise a plurality of data characteristics and a characteristic value time sequence corresponding to each data characteristic; for each data characteristic, comparing the characteristic value time sequence corresponding to the data characteristic in each characteristic data combination, and extracting difference characteristic data of each battery cell in the data characteristic and other battery cells; for each battery cell, combining all difference characteristic data corresponding to the battery cell to obtain difference characteristic combination data of the battery cell; and based on an anomaly detection algorithm, determining whether the corresponding battery cell has a fault according to the difference characteristic combination data. The technical scheme of the application improves the accuracy of battery pack fault detection and can accurately detect battery cells with a fault risk.

The invention relates to the technical field of fault detection, in particular to an integrated circuit fault detection method based on artificial intelligence. Comprising the following steps: acquiring and preprocessing multi-modal signal data and multi-modal historical signal data of an integrated circuit, and performing feature extraction on the preprocessed multi-modal signal data and multi-modal historical signal data by using a multi-dimensional time domain-frequency domain-nonlinear feature fusion extraction algorithm, multi-modal signal feature data and multi-modal historical signal feature data are obtained; constructing and training an intelligent fault detection model based on the multi-modal historical signal feature data; performing optimization processing on the intelligent fault detection model by using an intelligent fault detection optimization algorithm to obtain an optimized intelligent fault detection model; and processing the multi-modal signal characteristic data to obtain a fault detection result. The technical problem that in the fault detection process of the integrated circuit, signal data processing is not accurate enough, and consequently the precision is not high in the fault detection process is solved.

The invention relates to a power transmission line fault detection method and device, computer equipment, a computer readable storage medium and a computer program product, and relates to the technical field of power grids. The method comprises the following steps: acquiring a power transmission line image of a power transmission line and a fault detection task for the power transmission line image; inputting the power transmission line image and the fault detection task into a pre-trained fault detection model to obtain image features of the power transmission line image and text features of the fault detection task; performing fusion processing on the image features and the text features through a fault detection model to obtain cross-modal features of the power transmission line image; and based on the fault detection model and the cross-modal features, determining a target area associated with the fault detection task in the power transmission line image, and taking the target area as a fault detection result of the power transmission line image under the fault detection task. By adopting the method, the fault detection accuracy of the power transmission line can be improved.

The invention discloses a method for diagnosing the spatiotemporal root causes of abnormal quality in a hot rolling process, including: establishing a hot rolling process history database; aligning data samples according to the percentage of steel rolling position, and dividing the entire hot rolling process into multiple levels and sub-blocks; constructing fault detection models corresponding to each sub-block respectively, and training each fault detection model based on the history database to achieve real-time detection of quality-related faults in each sub-block; when a fault occurs, locating the spatial position of the abnormal quality according to the fault detection results corresponding to each sub-block, and determining the time position of the fault by reverse mapping the percentage of steel rolling position of each rack; calculating the size of the disproportionation coefficient of each process variable in the faulty rack, locating the fault root cause variable, determining the root cause variable causing the fault, locating the equipment where the fault occurs, and achieving spatiotemporal root cause diagnosis of the fault. The invention can better guide enterprise production and further improve the economic benefits of the enterprise.

The present invention is applicable to the field of light bar driving technology, and provides a redundant light bar driving circuit and method, the redundant light bar driving circuit includes: a power conversion circuit; a backlight driving controller; a light bar switch switching circuit; a current back-testing circuit; and a dual redundant light group connected to the power conversion circuit, the light bar switch switching circuit, and the current back-testing circuit, respectively, the dual redundant light group can be controlled to switch; the power conversion circuit is respectively connected to the backlight driving controller, the light bar switch switching circuit, and the current back-testing circuit, and the light bar switch switching circuit and the current back-testing circuit are respectively connected to the backlight driving controller. The present invention solves the problems of low reliability and low life of the liquid crystal screen in the prior art, thereby achieving high reliability and long life of the liquid crystal screen.

The invention relates to a fault detection method and device, computer equipment, a storage medium and a program product. The method comprises the following steps: acquiring a node information set of each Redis node in a remote dictionary service Redis cluster in a first control environment, aiming at each Redis node, determining a node type of the Redis node identified by each Redis node according to each node information set, and then determining a fault detection result of the Redis cluster according to the number of first nodes of which the Redis nodes are identified as the same node type.

The embodiment of the present application discloses a method for handling faults in a vehicle-mounted integrated navigation system and a vehicle-mounted integrated navigation device. The method comprises: obtaining fault information in the vehicle-mounted integrated navigation system, wherein the fault information comprises a source, state information and a cause; determining a detection object in the vehicle-mounted integrated navigation system according to the fault information; setting a fault detection strategy for each detection object; and performing fault detection on the vehicle-mounted integrated navigation system using the fault detection strategy.