73 results about "Single fault" patented technology

The invention relates to the technical field, and discloses a power distribution network multi-time scale fault scene deduction method comprising the following steps: obtaining meteorological and power grid operation data, establishing a time sequence fault tree model, and analyzing the trigger probability of multi-line disconnection and rainstorm short circuit faults in a target time period; extracting cross-level fault propagation features, analyzing a dynamic coupling relationship among multi-line disconnection, transformer substation flooding and cascading trip, forming a fault feature mode set, and identifying a single fault and a cascading fault in combination with time sequence analysis; historical fault data are analyzed, time sequence features and topological features of single and cascading faults are extracted, if a single fault propagation path is in a single level, a support vector machine is used for being combined with the features to judge fault types, and a classification result is output; and performing anomaly detection and confidence evaluation on a fault classification result, outputting a fault evolution path and risk evaluation, and analyzing the contribution degree of cascading trip to a large-area power failure risk in combination with historical blackout data to obtain power failure risk probability distribution.

The invention discloses a single-multiple fault combined diagnosis method and system for textile logistics equipment, and the method comprises the steps: obtaining equipment operation data, carrying out the preprocessing and feature extraction, and forming a standardized feature data set; performing single-fault diagnosis on the standardized feature data set, outputting a confidence result, completing confidence judgment according to a preset threshold value, and selectively outputting a single-fault conclusion or entering multi-fault combined diagnosis; in the multi-fault combined diagnosis stage, a fault relevance matrix is constructed through data relevance analysis, a causal relation graph is generated, the coupling relation between different faults is recognized, combined reasoning is completed, and a multi-fault combined diagnosis result is obtained. And finally, carrying out visual display on the diagnosis conclusion, and generating alarm grading and operation and maintenance auxiliary decision-making information. According to the method, self-adaptive switching between single-fault diagnosis and multi-fault combined diagnosis can be achieved, and the fault recognition precision and diagnosis reliability under the complex working condition are improved by combining correlation analysis and causal reasoning.

The invention provides an intelligent circuit breaker fault detection and maintenance method based on double MCUs, and the method achieves the automatic uninterrupted switching when a single MCU breaks down through the main and standby redundancy design, avoids the system breakdown, and greatly improves the usability and reliability. Quantitative scoring of the state of the main control MCU is achieved through a health assessment self-checking algorithm, and the accuracy of fault judgment is guaranteed. Through an intelligent switching arbitration mechanism, on the basis of switching probability calculation and confidence evaluation (health degree stability), a secondary confirmation mechanism is matched, and the error switching risk is effectively reduced. Line fault and MCU hardware fault detection is supported, and fault self-healing is achieved. And after the faulted MCU is recovered, the master and standby roles are automatically returned, so that the manual operation and maintenance cost is reduced.

The application provides a power distribution network fault disposal simulation training evaluation method based on a seven-layer track node tracking array. First, the simulation training operation result information of seven links, such as a sensing node, in the fault disposal process of a dispatcher is described by establishing a seven-layer track node tracking array model. Then, the fault disposal process of the dispatcher is quantitatively evaluated by establishing a sensing node evaluation index. Secondly, the whole process from the sensing node to the archiving node of the dispatcher in disposing a certain fault is evaluated by establishing a single fault disposal evaluation index. Finally, the comprehensive evaluation of all fault disposal conditions in the simulation training of the dispatcher is performed by establishing a power distribution network fault disposal simulation training comprehensive evaluation index. The scheme can comprehensively reflect the fault disposal process of the dispatcher, better reflect the fault disposal level of the dispatcher, the method is simple and reliable, can meet the field application requirements, and has good popularization value.

The present application relates to the technical field of fault prediction and computer big data processing, and particularly relates to a generalized zero-shot composite fault diagnosis method, device and system based on counterfactual reasoning. The generalized zero-shot composite fault diagnosis method based on counterfactual reasoning proposed by the present application constructs a two-stage generalized zero-shot composite fault diagnosis model based on counterfactual reasoning. The model firstly points out the internal causal components of fault data from the perspective of causality theory, and then constructs a structural causal model to describe the decoupling and generation of fault features under the guidance of counterfactual reasoning. On this basis, the model improves the generative model by strengthening the discriminator in the first stage to realize the binary classification of single fault and composite fault. In the second stage, the supervised training of the classifier is used to predict the single fault category, and a traditional zero-shot learning method is designed to classify the composite fault. The present application greatly improves the diagnosis accuracy of the model and solves the problem of model diagnosis deviation on visible and invisible classes.

The invention discloses a multi-fault coupling spring operating mechanism stress calculation method, and relates to the technical field of power equipment mechanical simulation and fault analysis, and the method comprises the steps: constructing an N * N order fault coupling coefficient matrix of a spring operating mechanism; calculating stress field data of the component under a single fault working condition by adopting a stress exclusive simulation method; extracting a sub-matrix and a coupling coefficient of a corresponding order of the target composite fault from the N * N order fault coupling coefficient matrix, and performing weighted linear superposition on stress field data of a single fault in the target composite fault to obtain a preliminary coupling stress field; and constructing and training an attention enhancement-multi-scale feature fusion neural network model, correcting network parameters through an adaptive weight attenuation optimization algorithm, and carrying out accurate correction on a nonlinear distortion region in the preliminary coupling stress field. According to the method, the problem of large calculation deviation caused by stress nonlinear distortion under a composite fault in the prior art is solved.

The invention discloses a monitoring equipment data management system and method applied to user interaction, and relates to the technical field of equipment data management. Equipment names and types of monitoring equipment are marked, operation characteristics of the monitoring equipment are obtained, the operation characteristics are stored in a monitoring equipment operation characteristic database, and fault types of the monitoring equipment are obtained; analyzing the identification characteristics of the fault types, obtaining a secondary fault risk type from the fault types, establishing a secondary fault risk type database, obtaining the current operation characteristics of the monitoring equipment in real time, marking the risk of the fault type for a manager, and if the fault type is not the secondary fault risk type, judging whether the fault type is the secondary fault risk type; selecting recommended maintenance personnel according to the marked fault type; otherwise, a secondary fault risk type database is called, recommended maintenance personnel are comprehensively selected, and the database is updated in real time after fault maintenance is completed. According to the method, the identification logic of secondary fault risk types is introduced, and cascading fault hidden dangers caused by a single fault are pre-judged in advance.

The invention relates to a method for monitoring the temperature of modules in a battery of an electric or hybrid motor vehicle, comprising a temperature measurement step (E1) by each temperature sensor of each module; a fault detection step (E2) when at least one of the measured temperature values ​​is below a minimum threshold value or above a maximum threshold value; and a warning step (E3) during which the driver is warned when at least one of the modules has a single fault, or during which power is limited and authorization to open the battery contacts is requested when at least one of the modules has multiple faults. Figure 1

The invention discloses a single fault point distance measurement method based on a reflection coefficient spectrum period, and relates to the technical field of fault detection, and the method comprises the specific steps: 1, constructing a model, and building an incidence relation; 2, determining the frequency range and bandwidth of frequency sweeping; 3, collecting data and constructing a smooth interpolation curve; 4, detecting feature points to obtain a phase coefficient value; 5, calculating a period and solving a fault distance; according to the method, the improved reflection coefficient spectrum model integrated with the cable basic parameters is constructed, the correlation between the period and the fault distance is established, interference of a traditional method is avoided, the near-area fault distance measurement problem is solved, and accuracy and adaptability are improved; and meanwhile, data is processed by adopting segmented cubic spline interpolation, fuzzy feature points are eliminated, redundancy check of three cycle calculation modes is designed, the anti-interference capability is enhanced, the fault distance is stably output in signal attenuation and noise interference scenes, and the reliability and consistency of a distance measurement result are guaranteed.

The application relates to the technical field of electrical safety protection, and discloses a circuit breaker with multi-node power-off protection functions, which comprises a shell mechanism, the outer side of the shell mechanism is fixedly connected with a guide support plate, when a certain branch node appears temperature abnormality and other faults, a temperature measuring assembly is triggered, a moving guide block driven by an electromagnet links a limiting stop plate to remove the limiting of a guide rod mechanism, the guide rod mechanism is driven through the meshing transmission of a servo motor, a driving gear and a gear row assembly, a contact mechanism is separated from a contact assembly, the rapid power-off of a single fault node is realized, the diffusion of faults to other nodes is avoided, and the problems that the traditional circuit breaker can only protect single nodes or single type faults are solved; the protection structures of the nodes independently operate, the elastic reset actions of reset springs A, B, C and D are matched, the circuit can be rapidly cut off in response to faults, the connection can be stably restored after the faults are eliminated, and the protection logic can be flexibly adjusted according to the power consumption characteristics of different nodes.

This invention relates to the field of lithium-ion battery energy storage technology, specifically disclosing a fault diagnosis method and system for lithium-ion battery energy storage systems. Through a multi-level monitoring logic of cluster-module-cell, the fault range is quickly narrowed down before focusing on individual cell diagnosis, avoiding indiscriminate full-scale calculations and achieving accurate fault location and analysis for large-scale energy storage systems. Furthermore, through the collaborative calculation of spatial and temporal information entropy, real-time location of sudden faults and early warning of gradual faults are simultaneously achieved, effectively solving the problems of strong adaptability to single faults and weak collaborative diagnosis capabilities for multiple faults in existing technologies.

An electronic control unit (ECU) includes a first chip and a second chip, where the first chip includes a first fault information transmission circuit, the second chip includes a second fault information transmission circuit, the first fault information transmission circuit includes a single fault pin coupled with a fault pin of the second chip, and the single fault pin is coupled with the fault pin of the second chip. The fault sensor is used for transmitting and receiving fault information; the current detection circuit is used for detecting whether current exists in the first fault information transmission circuit; the voltage regulation unit is used for receiving voltage input in the first chip and outputting fault voltage only when the voltage input has a fault; a back-to-back protection circuit coupled between the single fault pin and the voltage regulation unit; and the fault monitoring circuit is used for monitoring the fault voltage output by the voltage regulating unit or the fault information received by the single fault pin from the second chip. The invention further relates to a fault information transmission circuit.

The invention discloses a DSM fault diagnosis test method and device and a medium, and the method comprises the steps: constructing a CANoe test environment, and generating a test case for testing a DSM fault diagnosis program; executing a fault clearing operation through a fault clearing program in the ECUTEST software to clear all historical fault codes stored in the VCU controller before the test case simulates a new fault state, so that the VCU controller is in a single fault code state; based on the single fault code state, running the test case through a CANoe test environment; and obtaining a fault diagnosis message sent by the DSM fault diagnosis program in response to the test case, and comparing an actual fault code in the fault diagnosis message with an expected fault code in the test case to generate a diagnosis test report.

The present application relates to the technical field of power supply and distribution training equipment, in particular to a power supply and distribution blind box training system, which is composed of an incoming line box, a node box and a quick connection line, a plurality of box bodies are connected head to tail through plug-in structures to form a 220V low-voltage power distribution circuit, and a domestic socket power supply scene is simulated. The incoming line box is integrated with a plug unit, a protection unit and an external interconnection unit, and is configured with a total air switch, a leakage protector and a fuse to form a hierarchical protection; the node box has a detachable closed structure with a cover, the system can freely combine the number of box bodies to adjust the training difficulty, support the training subjects of line searching and drawing, phase checking and line checking, insulation resistance detection, single fault and multi-fault combination troubleshooting, and the device can be repeatedly used and has low consumable loss, relies on a ladder type protection structure to ensure the safety of 220V mains training, solves the problems of poor intuitiveness, fault simulation distortion, complicated configuration and high use cost of traditional training equipment, and is suitable for skill training and examination of power supply and distribution maintenance personnel.

The invention relates to the technical field of pipeline systems, and discloses a pipeline system with an intelligent monitoring function, which comprises a pipeline body, an interface monitoring module, a data relay unit and a remote monitoring terminal, the pipeline body is formed by connecting a plurality of sections of pipe bodies through connectors, and the interface monitoring modules are embedded in grooves in the outer walls of the connectors; the data relay units are arranged at intervals in the length direction of the pipeline body and connected with the interface monitoring module in a wired mode. The remote monitoring terminal is connected with the data relay unit through a wireless communication network, the interface monitoring module comprises a leakage monitoring assembly, a radial displacement monitoring assembly and an axial pull-out monitoring assembly, and the leakage, the radial displacement and the axial pull-out monitoring are integrated through the interface monitoring module for monitoring the leakage, the radial displacement and the axial pull-out and a cooperative structure of the data relay unit and the remote monitoring terminal. Compared with a traditional single fault monitoring scheme, the fault coverage range is remarkably improved, the fault response time is remarkably shortened, and the fault removal precision and efficiency of communication pipeline faults are improved.

This invention discloses a switchless redundant fault-tolerant memristor cross array circuit for resolving bridging faults, comprising a main array, two redundant word lines, two redundant bit lines, and a controller. The main array consists of N word lines, M bit lines, and cross-point memristor cells. The redundant word lines cross with all bit lines, and the redundant bit lines cross with all word lines. The controller is directly connected to all word lines, redundant word lines, bit lines, and redundant bit lines. This circuit does not contain any physical switches for fault isolation, has a simple structure, low hardware overhead, and is easy to integrate.

The application provides a rail vehicle fault early warning method, device, equipment and storage medium, comprising: collecting current and temperature signals of a low-voltage electrical appliance cabinet power supply loop; sending the current high-frequency component into an arc detection channel, performing time-frequency analysis and outputting an arc fault probability vector through a first neural network model; sending the current low-frequency component and the temperature signal into an overheating detection channel, extracting time sequence features and outputting an overheating fault probability vector through a second neural network model; calculating a fusion weight based on the correlation of the two types of faults, weighting and fusing the two probability vectors to obtain a final fusion probability vector, and determining a vehicle warning level accordingly. The above scheme ensures the recognition accuracy of a single fault type and improves the stability and accuracy of the overall fault determination.

The invention discloses an energy storage system protection function test method, system and device and a medium. Obtaining a configuration file, obtaining fault data and verification data, and carrying out analysis configuration on the configuration file to obtain a simulation test scene; based on the fault data, constructing a sending queue of data packets with timestamps; injecting the sending queues into a plurality of target energy storage subsystems in parallel in a multi-thread parallel mode, and starting to monitor the scheduling process of the target energy storage subsystems; and based on the monitoring content and the verification data, obtaining a test evaluation result from the response time, the collaborative protection gap, the success rate and the consistency evaluation. According to the method and the device, the real fault dynamic characteristics are simulated to simulate the virtual fault, the protection function test of intrinsic safety is realized in a lossless manner, and the full-scene automatic verification from the single fault to the system linkage is realized. The fundamental breakthrough is achieved, physical risks are eliminated, and the testing effect is improved when the protection function of the energy storage system is tested.

The invention discloses a ground fault feature fusion recognition processing method, system and device and a medium, and belongs to the technical field of power distribution network relay protection, and the method comprises the steps: collecting current data, and judging whether a ground fault exists or not based on the current data; if the grounding fault exists, extracting a first parameter and a second parameter generated by the fault, and setting a corresponding threshold value; dividing the grounding fault into an instantaneous grounding fault or a permanent grounding fault according to the first threshold value, the second threshold value, the current data and corresponding judgment conditions; a first closed-loop control or a second closed-loop control is performed for the instantaneous ground fault or the permanent ground fault. According to the method, the problems of high misjudgment rate and inaccurate processing of the grounding fault of the power distribution network caused by dependence on a single fault feature in the prior art are solved, and particularly under the conditions of distributed power supply access and high-resistance grounding, the fault identification precision and the processing reliability are improved, and instantaneous and permanent faults are distinguished and properly processed.

The invention discloses a traction system fault diagnosis method based on shape primitives and time-frequency mixed prompt. The method comprises the following steps: firstly, acquiring a monitoring signal sequence of a system; a time-frequency mixed prompt set is constructed according to the monitoring signal sequence; then determining a gating weight according to a preset prompt set and the monitoring signal sequence; then, based on the monitoring signal sequence, the time-frequency mixed prompt set and the gating weight, obtaining a shape primitive; performing reconstruction processing on the signal sequence according to the shape elements to obtain a reconstructed signal sequence; and obtaining a fault diagnosis result according to a preset fault threshold value and the reconstruction signal sequence. According to the method, the robustness of cross-domain fault detection is effectively improved and the abnormal time period and the shape type are accurately positioned by constructing the time-frequency mixed prompt, extracting the shape primitive and combining the synergistic effect of the gating weight, meanwhile, the efficient identification of a single fault and a composite fault is realized, and the false alarm rate and the missing report rate under the complex working condition are effectively reduced.

The present application relates to the field of intelligent fault diagnosis, especially the intelligent fault diagnosis of rotating machinery, and discloses a rotating machinery generalized zero-shot coupled fault diagnosis method based on a double convolution network and dynamic semantic fusion and a medium, aiming to solve the problem that it is difficult to simultaneously identify known single faults and unknown coupled faults in the test stage when only a single fault sample is used for training. The method comprises the following steps: collecting a vibration signal and converting it into a time-frequency image; using a first convolution network to extract discriminative features, and realizing single / coupled fault separation through an improved support vector data description model; using a second convolution network to learn single fault semantics, and constructing coupled fault pre-defined semantics based on dynamic fusion of signal complexity; and finally mapping coupled fault samples to a semantic space for distance matching identification. Through the "two-stage separation-semantic reasoning" architecture and dynamic semantic fusion, the present application improves the accuracy and robustness of coupled fault diagnosis, and has great engineering application value.

The application relates to the field of intelligent management analysis, and proposes an electric locomotive maintenance practical training intelligent analysis method and system based on an AI model, which constructs an electric locomotive virtual practical training scene, avoids the problem that a large amount of manpower and material resources needs to be consumed during actual scene training, constructs an electric locomotive maintenance knowledge graph, generates dynamic operation risks, makes the practical training operation results and fault problems more consistent with the actual scene, avoids the problem that a single fault case cannot restore the complex problems and complex operations of the actual maintenance scene, is based on a double-base interaction mechanism, ensures the accuracy and reliability of the guidance information, further improves the accuracy of the guidance information through deep expansion, gives deeper information, avoids the problem that the depth of the guidance information in the field knowledge is insufficient, and objectively authenticates the practical training effect through automatic quantitative evaluation, and the application improves the practical training effect and the practical training quality of operation and maintenance personnel.

Systems and methods for fault simulation are presented to reduce computation processing. A system includes a memory and a processor, operatively coupled to the memory, to perform fault simulation by injecting a plurality of faults into an IC model, initiating a concurrent fault simulation for all of the plurality of faults injected into the IC model, identifying at least one fault of the plurality of faults that is unable to be implemented by the concurrent fault simulation, and initiating a single fault simulation to process the at least one fault unable to be implemented by the concurrent fault simulation without interrupting the concurrent fault simulation from processing other faults of the plurality of faults. The at least one fault from the concurrent fault simulation is immediately discarded and the fault results from the concurrent fault simulation and the single fault simulation are combined upon completion of both simulations.

This invention proposes a phototherapy device control system with a single fault response mechanism, comprising a cooling module, a light source system control unit, an interaction module, a light source, and a light source cooling module. The light source system control unit includes a main microcontroller, an auxiliary microcontroller, and a single fault response circuit. The single fault response circuit includes an electrically connected power supply control circuit, a controlled on / off control circuit, a closed-loop control circuit, and an operational amplifier drive circuit. The light source cooling module includes a water temperature acquisition unit and a water-cooling unit. Thus, water cooling replaces air cooling, and the water temperature acquisition unit is optimized to enhance acquisition stability. This ensures stable driving of the water-cooling unit, maintaining the water cooling effect and improving heat dissipation. The single fault response circuit addresses the anomaly of a single component malfunctioning and the light source becoming uncontrollably uncontrollable and unable to shut off, ensuring medical efficacy and improving equipment reliability.

This invention belongs to the field of mechanical health condition monitoring and fault diagnosis, and specifically discloses a method and system for diagnosing complex faults in wind turbine gearboxes based on zero-shot learning. The method includes the following steps: constructing a semantic knowledge base using the fault type of a single fault as a semantic attribute; constructing attribute vectors representing all fault types based on the semantic knowledge base; acquiring single fault data of the wind turbine gearbox, extracting the corresponding fault feature vectors, and mapping the fault feature vectors to the attribute vectors to form a single fault dataset; training a Bayesian model based on XGB using the single fault dataset to obtain a fault diagnosis model; acquiring complex fault data of the wind turbine gearbox and extracting the corresponding fault feature vectors; inputting the fault feature vectors and the complex fault attribute vector set into the fault diagnosis model to obtain the complex fault type. This invention enables the diagnosis of complex faults in wind turbine gearboxes even with only single fault samples.

The invention belongs to the field of engine fault simulation, and particularly relates to a hardware-in-loop test combination fault simulation method, which comprises the following steps: on the basis of the technical requirement of single fault test in a known fault mode, selecting n fault instructions from m known fault trigger instructions for combination, and traversing n from 1 to m; and assuming that each fault simulation instruction data is a switching value, 0 represents no fault, and 1 represents fault. In n selected fault instruction combinations, arranging all instruction elements in the combinations according to different sequences to obtain all arrangement schemes; cyclically selecting each arrangement from all the arrangement schemes to generate state input data of the fault simulation instruction; the problem of incomplete coverage of multi-fault combination is solved through a combination-permutation algorithm, the same combination fault is reinforced through time sequence matrix control, simulation is carried out in different triggering sequences of the fault, and finally, high efficiency, comprehensiveness and accuracy of combination fault simulation in the HIL test are achieved.

The application discloses a kind of security prediction index calculation method and system reflecting system stability level, comprising: obtaining typical mode data;Based on the typical mode data, time domain simulation is carried out, and the operating data when different types of faults occur is obtained;Based on the operating data, the system stability level value under the first single fault, the system stability level value under the second single fault and the system stability level value under multiple faults are calculated respectively;Based on the system stability level value under the first single fault, the system stability level value under the second single fault and the system stability level value under multiple faults, the system comprehensive stability level value is calculated, to determine the stability level of the system based on the system comprehensive stability level value.The stability state of the system under different fault scenarios is converted into a quantifiable numerical indicator in the application, solving the problem of qualitative and fuzzy evaluation in traditional evaluation method, so that the high and low of system stability level can be accurately reflected, and the comparison and analysis of evaluation results are facilitated.

The present application relates to the field of mechanical equipment fault diagnosis, and discloses a fault diagnosis method, system, medium and equipment based on part characteristic frequency, which comprises the following steps: obtaining part fault characteristic frequency from a mechanical equipment original fault data set, and constructing guidance information of physical knowledge based on the part fault characteristic frequency; splicing the generated fault characteristic frequency information and fault data to form double-channel data, inputting the double-channel data into a multi-output deep convolutional neural network for training to extract fault features; performing multi-output classification and diagnosis on the fault features by the multi-output deep convolutional neural network, each output corresponding to a fault type of a mechanical equipment, extracting fault features corresponding to the fault type from global features to complete diagnosis on whether the fault exists in the mechanical equipment. The present application can decouple composite faults and realize prediction of single fault types.

This invention discloses a method, apparatus, device, and storage medium for generating a knowledge graph. The method includes: acquiring a set of faults; acquiring single faults and combined faults from the fault set; determining fault entities based on the single and combined faults; determining relationships between fault entities based on the combined faults; and constructing a knowledge graph based on the fault entities, the relationships between them, and the target attribute values ​​of the fault entities. Through the technical solution of this invention, a knowledge graph is constructed. The knowledge graph can more intuitively display the relationships between fault entities, facilitating management and maintenance, and improving subsequent management efficiency. Furthermore, constructing test cases based on the knowledge graph constructed according to embodiments of this invention can save time and manpower costs in building test cases.

The invention discloses a hydropower station operation training method based on fault case reconstruction and reverse analysis, belongs to the technical field of hydropower station operation training and fault diagnosis, and aims to solve the problems of single fault scene, insufficient reverse thinking training, extensive evaluation and lack of personalized guidance in traditional training. According to the technical scheme, the method comprises the following steps: constructing a dynamic structured case library with a multi-dimensional label, reproducing a fault evolution process and generating a multi-sensory interactive virtual scene by using a digital twin model and a VR / AR technology, and embedding a graphical reverse analysis tool to guide students to construct and verify a fault hypothesis path. And finally, a multi-dimensional capability evaluation matrix is generated through an evaluation optimization module, and a student capability portrait is constructed based on a reinforcement learning algorithm module to match a personalized training sequence, so that closed-loop capability improvement is realized, and the method is mainly used for improving diagnostic analysis, logical reasoning and co-processing capabilities of hydropower station operators under complex faults.