23results about How to "Implement fault diagnosis" patented technology

The application discloses a kind of SF6 circuit breaker fault prediction method and system considering the effect of breaking arc, collect breaking arc data and SF6 gas decomposition product content after breaking, in the process of operation and after fault, establish circuit breaker historical breaking data set, build cumulative arc energy-SF6 gas decomposition product content relationship model, obtain the SF6 gas decomposition product content corresponding to different breaking times, breaking current;Establish SF6 gas decomposition product content historical operation data set;Build SF6 gas decomposition product content prediction model based on LSTM, obtain the prediction result of SF6 gas decomposition product content;Establish SF6 gas decomposition product content historical fault data set, build SF6 circuit breaker fault diagnosis model;The prediction result of SF6 gas decomposition product is as the input of SF6 circuit breaker fault diagnosis model, obtains fault diagnosis result, realizes the fault prediction of SF6 circuit breaker.

The invention provides a dynamic multi-node atom magnetometer health management method and system. The dynamic multi-node atom magnetometer health management method comprises the following steps: acquiring original data of each atom magnetometer node in real time by using a data acquisition module; preprocessing the original data of each atom magnetometer node, and extracting health-related features; based on the extracted health-related features, identifying a single-node sudden fault based on an abnormal detection model of an isolated forest, and outputting a health state score of each node; predicting future health states of the nodes based on a performance degradation trend prediction model of the long-short-term memory network; analyzing health state propagation and coupling effects among nodes based on a multi-node collaborative health analysis model of a graph neural network; and executing a corresponding strategy according to the health assessment result of each atom magnetometer node to complete dynamic multi-node atom magnetometer health management. By applying the technical scheme of the invention, the technical problem that health status assessment in the prior art mostly depends on manual data analysis and lacks real-time performance and systematicness is solved.

This application provides a fault diagnosis method, apparatus, storage medium, and device. The method includes: acquiring the original vibration signal of a target mechanical device; filtering the original vibration signal through an initial filter to obtain an original filtered signal; determining an initial search direction and an initial update step size based on the dispersion of the original vibration signal, the original filtered signal, and the system response of the initial filter; iteratively updating the initial filter multiple times along the initial search direction and according to the initial update step size, with the goal of minimizing the dispersion, until a preset shutdown criterion is met, thus obtaining a target filter. In the multiple iterations, the target filter is iteratively updated along the direction that reduces the dispersion of the original filtered signal. This target filter filters the original vibration signal to obtain the target filtered signal. By focusing on the dimension of dispersion, interference from periodic noise is avoided, ensuring the accuracy of fault diagnosis.

The application discloses a kind of variable working condition equipment key component fault diagnosis method of class disequilibrium data driving. For the key rotating component in electromechanical complex equipment, obtain the vibration signal and its fault type under the normal and fault state operation of component, construct diagnostic data set and train model, so as to obtain the diagnostic result of the sensor data to be predicted using the trained fault diagnosis model. The application considers the complex situation that the current industrial monitoring data is under variable working condition and class disequilibrium, firstly applies channel-by-channel convolution to generate local feature enhancement weight matrix, and realizes feature enhancement in local feature space using fewer training parameters;Design and introduce wide-range convolution kernel considering the inherent physical characteristics of rotating components, fully and stably capture effective feature information under variable working condition, realize end-to-end fault diagnosis of key rotating components of electromechanical equipment. The application is simple and efficient, not only has theoretical innovation, but also has high practicability.

The application relates to the field of automobile electronics, in particular to a load driving circuit structure of a vehicle body controller and a control strategy thereof, which comprises a main control unit and at least one intelligent driving chip, the chip containing a power switch connected in series between a power supply and a load, a coupled current sampling circuit, a fault diagnosis protection circuit with a configurable threshold value, a communication interface connected with the main control unit and a load type identification module; the module determines the load type according to a current rising slope and a steady state establishment time within a power switch conduction starting point window, and adjusts the protection threshold value; the circuit does not contain an electromagnetic relay and a one-time fuse. According to the application, the load type is determined according to the transient waveform characteristics of the load current within the power switch conduction window, and the protection threshold value is adjusted, so that the problem that a fixed threshold value cannot distinguish between a resistive cold-state impact and a short-circuit fault, thereby causing false triggering or protection delay, is solved.

This application discloses a train fault diagnosis system based on a wireless sensor network, applied in the field of rail transit technology. The system includes: a wireless sensor installed at the detection location on the train to detect signals at that location and transmit the detection data to a repeater; a repeater installed in the train and communicatively connected to the wireless sensor to receive the detection data and add a timestamp; a speed signal acquired through a train control and management system and / or through a speed sensor, and a timestamp added to the speed signal; and a fault diagnosis device communicatively connected to the repeater for fault diagnosis based on speed signals and detection data with the same timestamp. Applying the solution of this application can effectively realize train fault diagnosis, simplify the system structure, reduce the wiring complexity of the train fault diagnosis system, and ensure implementation flexibility.

The application discloses a bearing weak fault feature extraction method based on a parameter dictionary and an OMP algorithm, and establishes a sparse representation model of a rolling bearing vibration signal according to collected rolling bearing vibration data; the rolling bearing vibration data comprises rolling bearing vibration signals with useful fault information and useless background noise information; according to a Laplace wave parameter dictionary, an orthogonal matching pursuit algorithm is adopted to solve a sparse coefficient matrix of the signal sparse representation model of the rolling bearing; the sparse coefficient matrix is reconstructed with the Laplace wave parameter dictionary, envelope analysis is performed on the reconstructed signal, weak fault features are extracted, and bearing fault diagnosis is realized. The application can not only effectively reduce the algorithm complexity of the original method, but also more accurately extract bearing weak fault features under strong background noise, and can simply and effectively perform rolling bearing fault diagnosis in engineering practice.

The application is suitable for the technical field of solar cells, and provides a photovoltaic junction box, a cell module and a photovoltaic system. The photovoltaic junction box is used for a cell laminate, and the photovoltaic junction box comprises: a diode, a negative electrode connected to a positive bus bar of the cell laminate, and a positive electrode connected to a negative bus bar of the cell laminate; a detection circuit connected to a positive electrode of the diode and a voltage detection lead of the cell laminate, the voltage detection lead being insulated from the positive electrode of the diode; the detection circuit comprises a detection element, a communication module and a processor, the detection element and the communication module are connected to the processor, and the detection element comprises a shunt, the shunt is connected to the positive electrode of the diode, the processor and a module output interface of the cell laminate. In this way, fine operation and maintenance can be realized, and the monitoring accuracy of the cell module can be improved.

The invention discloses a fault diagnosis method based on a multi-source domain refining comparison self-distillation industrial robot. The method comprises the following steps: firstly, acquiring a multi-source domain data set and a target domain data set; thirdly, constructing an initial multi-source-domain loop network, and training the initial multi-source-domain loop network according to the multi-source-domain data set and the target-domain data set to obtain a target-domain integrated network; and on this basis, a target fault diagnosis model is constructed according to the target domain integration network, and fault detection is carried out on a fault-label-free target domain sample in the target domain data set by means of the target fault diagnosis model to obtain a fault diagnosis result of the target domain sample. According to the method, model construction and training are carried out by using the multi-source-domain data set and the target-domain data set, the source-domain effective information matched with the target-domain sample can be fully mined, and the fault detection accuracy of the target-domain unlabeled sample is effectively improved. Therefore, the constructed target fault diagnosis model can efficiently realize fault detection of the target domain data, and the diagnosis precision is effectively improved.

The invention provides a radar fault diagnosis and self-tuning method based on deep reinforcement learning, and relates to the technical field of radar fault diagnosis. Comprising the steps of constructing a simulation environment, a single-photon laser radar system model, a teacher strategy network model and a student strategy network model; a target training data set is obtained through simulation of the single-photon laser radar system model; training a teacher strategy network model based on a particle resampling algorithm through the target data set to obtain a target teacher strategy network model; training the student strategy model through the teacher strategy network model to obtain a target student strategy model; and through interaction between the student strategy network model and the real radar, fault diagnosis information and equipment health degree information are generated, and a control strategy and self-tuning are output according to the information. According to the method, the target student strategy model can be obtained through training to realize early prediction and accurate classification of radar potential faults, and the optimal parameter adjustment strategy can be automatically executed when the faults occur or before the faults occur.

The invention relates to the technical field of pipeline weak current driving automatic control systems, in particular to a pipeline weak current driving automatic control system. The technical problems are as follows: when a pipeline weak current driving automatic control system is used, a centralized control architecture is generally adopted, all control logic and data processing are completed in a control unit in a centralized manner, and the architecture has limitations in the aspects of expansibility and flexibility; according to the technical scheme, the pipeline weak current driving automatic control system comprises a data analysis module and a block valve execution module; compared with a traditional pipeline weak current driving automatic control system, the pipeline weak current driving automatic control system generally adopts a centralized control framework, all control logics and data processing are completed in a control unit in a centralized mode, the framework has limitation in the aspects of expansibility and flexibility, and the pipeline weak current driving automatic control system has the advantages that the pipeline weak current driving automatic control system is easy to operate. The system not only has the basic functions of a traditional system, but also can achieve the functions of remote monitoring, fault diagnosis, automatic adjustment and the like, and the reliability and stability of the system are improved.

The invention relates to a single diode open-circuit fault diagnosis and positioning method for an aviation multi-pulse transformer rectifier, which can effectively solve the problem that the early-stage single diode open-circuit fault detection methods of rectifier bridges in different types of aviation multi-pulse transformer rectifiers are not unified. Acquiring a direct-current component in primary / secondary side current of the phase-shifting transformer by using a low-pass filter, defining a direct-current component residual error of the primary side current, and judging whether a single diode open-circuit fault occurs in a rectifier bridge in the aviation multi-pulse transformer rectifier or not; if a fault occurs, comparing absolute values of direct-current components of any two phases of primary side current, and simultaneously obtaining a maximum value of absolute values of direct-current components of secondary side current so as to judge a rectifier bridge where the fault diode is located and a phase where the fault diode is located; furthermore, whether an upper bridge arm diode or a lower bridge arm diode is in an open circuit state is judged by calculating the difference between the absolute value of the maximum value and the absolute value of the minimum value of the secondary side current in one period, and finally the functions of diagnosis and positioning of the open-circuit fault of the single diode of the rectifier bridge in the aviation multi-pulse transformer rectifier can be achieved. The diagnosis and positioning method is high in universality, simple and easy to implement, the direct-current component of each current can be obtained only through the low-pass filter, early faults can be found, and safe operation of the aviation secondary power supply system can be maintained.

This invention discloses a gateway fault diagnosis method, apparatus, electronic device, and gateway, belonging to the field of gateway technology. The method includes: obtaining the gateway's message reception time and message status; when the message status is "message not sent," calculating the message routing time based on the current time and the message reception time; when the message status is "message sent," obtaining the gateway's message transmission time and calculating the message routing time based on the message transmission time and the message reception time; and obtaining the gateway's fault diagnosis result based on the message routing time. Thus, fault diagnosis of the gateway can be achieved.

The invention relates to the technical field of rolling bearing fault diagnosis, and discloses a target domain data set construction method, a rolling bearing fault diagnosis method and a computer program product, and the target domain data set construction method comprises the steps: selecting an amplitude spectrum of an actual measurement sample as a fitness function of a CS-GWO algorithm; taking the minimum value of the amplitude spectrum entropy as a fitness function, and searching an optimal parameter combination in the VMD algorithm; decomposing the actually measured samples in the original data set by using the VMD algorithm of the optimal parameter combination to obtain K modal components; and calculating the correlation between each modal component and the actually measured sample, retaining the high-correlation modal components, and carrying out summation reconstruction to obtain target domain data in the target domain data set. According to the method, the fault features are accurately extracted by using the CS-GWO optimized VMD algorithm, the fault feature coefficient and the signal-to-noise ratio are remarkably improved, noise interference in an actual measurement sample is effectively inhibited, and thus the accuracy and reliability of target domain data are improved.

The application relates to a semiconductor refrigeration device and temperature control system with built-in NTC and TCO, which comprises a cold-end ceramic substrate, a hot-end ceramic substrate, a first NTC temperature sensor and a TCO temperature control controller. A thermoelectric element is arranged between the cold-end ceramic substrate and the hot-end ceramic substrate. The first NTC temperature sensor is built in the cold-end ceramic substrate or the hot-end ceramic substrate, and the heat-sensitive part of the first NTC temperature sensor is directly coupled with the ceramic substrate. The TCO temperature control controller is built in the cold-end ceramic substrate or the hot-end ceramic substrate, and the temperature-sensing part of the TCO temperature control controller is directly coupled with the ceramic substrate. The signal lead-out wire of the first NTC temperature sensor and the electrode lead-out wire of the TCO temperature control controller are respectively led out to the external pins of the semiconductor refrigeration device through the ceramic substrate. The application directly builds the NTC and the TCO in the TEC module, forms good thermal coupling with the ceramic substrate, and reduces the hysteresis and deviation of temperature sensing.

The invention discloses a fault diagnosis method, device and system for an aircraft, and the method comprises the steps: obtaining a plurality of vibration signals, the plurality of vibration signals come from a plurality of vibration signal collection parts, the plurality of vibration signal collection parts are disposed on a fixed platform, the aircraft is fixed on the fixed platform, and the plurality of vibration signal collection parts are connected with the fixed platform; the plurality of vibration signal acquisition parts are used for acquiring the plurality of paths of vibration signals under the condition that a rotor system of the aircraft is started; and performing fault diagnosis on the rotor system of the aircraft based on the acquired multiple paths of vibration signals. Therefore, fault diagnosis of the rotor system of the aircraft is realized.

The invention provides a miniaturized environment-friendly gas ring main unit which comprises a closed box body based on dry air insulation, the closed box body is provided with an emergency interface, and the internal space of the closed box body is divided into a closed gas box, a mechanism chamber, a cable chamber, a pressure relief chamber, a mounting compartment and an instrument chamber according to functions and purposes; wherein a three-fracture combined switch is designed in the closed gas tank, and a sprocket transmission structure is adopted between the three-fracture combined switch and the PT operating mechanism and the emergency power supply operating mechanism of the mechanism chamber, so that the miniaturization design requirement is met. The PT unit is integrated with the incoming and outgoing line unit, the instrument chamber is integrated with the automatic terminal DTU, and a cabinet does not need to be arranged independently. By reasonably distributing the positions of the functional rooms, the occupied space of the ring main unit is reduced, an original old high-voltage cable branch box is replaced, or a state grid standardized ring main unit is replaced in a narrow site, the power supply reliability is improved, and the power failure range of an abnormal accident is minimized.

The application provides a spacecraft fault diagnosis processing method and device, and relates to the technical field of measurement and control. The method comprises the following steps: acquiring telemetry result data, and performing data preprocessing on the telemetry result data; a relationship between the telemetry result data and a spacecraft fault is represented through a spacecraft fault rule based on time sequence logic; fault rule calculation based on a state transition sequence is performed on the telemetry result data after the data preprocessing, and the spacecraft fault is diagnosed according to a fault rule calculation result. The device executes the above method. The spacecraft fault diagnosis processing method and device provided in the embodiment of the application can realize spacecraft fault diagnosis without programming by a developer, and improve the universality of the spacecraft fault diagnosis processing method.

This invention belongs to the field of power line fault detection technology and discloses a method, system, equipment, and medium for diagnosing power distribution line faults. The method includes: acquiring initial fault signal data corresponding to the power distribution line, preprocessing the initial fault signal data, and outputting fault signal data; decomposing the fault signal data using joint decomposition technology to obtain intrinsic mode components (IMCs); introducing information mining technology to extract the distribution change feature vector of the fault signal and fusing it with the IMCs to obtain a change image; extracting local features of the change image through a convolutional neural network and combining it with a strategy function optimized by a Huffman tree for fault classification, and outputting the fault diagnosis result. This invention applies the Softmax strategy of Huffman trees, improving the efficiency and accuracy of judgment, enabling early identification and warning of fault signals in power distribution lines, and improving the efficiency of power distribution line fault diagnosis.

The application provides a high-speed switch valve fault recognition method based on fluid noise and mechanical noise characteristics, which can recognize the fault of the high-speed switch valve in the hydraulic system, first uses a PWM wave to drive the high-speed switch valve, measures the time-domain sound pressure signal of the high-speed switch valve through the sound pressure sensor placed on the side of the high-speed switch valve, and the time-domain sound pressure signal contains the characteristics of the mechanical noise and the fluid noise; compares the maximum value point, the time when the maximum value point appears, the maximum value point and the maximum value point of the theoretical time-domain sound pressure signal with those of the time-domain sound pressure signal of the high-speed switch valve to be tested to determine whether the fault occurs in the high-speed switch valve; and the application can recognize the fault according to the time-domain sound pressure characteristics of the mechanical noise and the fluid noise generated by the movement of the internal components of the high-speed switch valve in the hydraulic system, can analyze the cause of the fault, and improves the fault recognition efficiency.

This invention relates to a safety early warning method for coal mining equipment based on real-time industrial data, belonging to the field of fault diagnosis technology. The method includes: acquiring real-time frequency domain feature sequences at multiple monitoring times and obtaining reference frequency domain feature vectors; obtaining real-time potential feature vectors for each monitoring time using a SafetyCAE feature extraction network; calculating the Mahalanobis distance between the real-time potential feature vectors and the reference frequency domain feature vectors; calculating the prediction uncertainty factor for each monitoring time; calculating a comprehensive safety early warning factor based on the Mahalanobis distance and the prediction uncertainty factor; performing component-level and whole-machine-level risk diagnosis on the coal mining equipment based on the comprehensive safety early warning factor; inputting the comprehensive safety early warning factor into the fault diagnosis isolated forest iForest model, and outputting the anomaly score and anomaly label for each monitoring time. This invention has stronger forward-looking capabilities, realizing a shift from traditional post-event diagnosis to pre-event safety early warning.

The application provides a mechanical rotating part acoustic emission fault diagnosis method based on bidirectional weighted cyclic stationarity, which comprises the following steps: collecting an acoustic emission signal to be diagnosed, obtaining a cyclic spectrum coherence function, and obtaining a baseline discrete spectrum coherence mapping and a diagnosis discrete spectrum coherence mapping; based on the baseline discrete spectrum coherence mapping and the diagnosis discrete spectrum coherence mapping, a spectrum frequency weight redistribution vector is obtained; based on the cyclic spectrum coherence function, a difference spectrum coherence matrix is obtained; and based on the spectrum frequency weight redistribution vector and the difference spectrum coherence matrix, a bidirectional reweighted difference spectrum coherence matrix is obtained. The application integrates healthy baseline data as prior information into a cyclic stationarity analysis framework, innovatively combines the difference and weighting ideas, deeply excavates the unique advantages and potential of the acoustic emission technology in the field of fault diagnosis, fully meets the needs of complex and variable industrial application scenarios, and has practical application value.

The application discloses a rocket engine fault diagnosis method, device, equipment and medium, and relates to the technical field of rocket engines, to solve the problem that the standard value is difficult to determine due to state drift and test difference of the rocket engine, and misdiagnosis of fault diagnosis is easily caused.A rocket engine fault diagnosis method comprises the following steps: obtaining measurement data; based on the measurement value of the covariant, a probability prediction neural network is used to predict the probability distribution of a target parameter; an abnormal threshold range is determined according to the probability distribution of the target parameter; it is judged whether the measurement value of the target parameter exceeds the abnormal threshold range, if yes, the measurement value of the target parameter at the last moment is input into an autoregressive neural network to obtain a standard value; a measurement residual is obtained according to the standard value and the measurement value of the target parameter, an observer is used to observe a fault factor, and fault detection is realized.The rocket engine fault diagnosis method provided by the application is used for real-time determination of the standard value, and the accuracy of rocket engine fault diagnosis is improved.