44 results about "Failure diagnosis" patented technology

The application discloses an auditing method and device for power transmission line fault reports and equipment thereof, relates to the technical field of report auditing, and comprises the following steps: obtaining an original fault report obtained after fault diagnosis on a power transmission line; performing data consistency auditing on the original fault report; when it is determined that the report data in the original fault report is consistent with the attachment materials corresponding to the original fault report, performing suggestion auditing on a preliminary fault report that passes the data consistency auditing; when it is determined that the treatment suggestion in the preliminary fault report meets the requirements of a preset judgment standard, performing multi-dimensional comprehensive auditing on a second-round fault report that passes the suggestion auditing, and obtaining a target fault report with procedure traceability. The method avoids the false parameters or misuse of professional terms caused by the pursuit of fluent text by a large model, reduces the burden of artificial auditing and the probability of misjudgment, and improves the auditing accuracy.

The system comprises a data access module, a power grid flood disaster field knowledge graph, a digital twin body environment, and a digital twin body agent (DTA), a monitoring and early warning agent (MWA), a fault diagnosis agent (FDA) and a case handling agent (CHA). The DTA provides simulation deduction services. The MWA generates a flood field and a device-level risk list using a physical model chain. The FDA predicts device failure probability using a GWO-BPNN model. The CHA retrieves cases based on the knowledge graph to generate a scheme, and requests the DTA to perform virtual deduction and iterative optimization. The application interaction layer integrates visual output. The application realizes a full-process closed-loop intelligent decision from disaster perception, risk diagnosis, scheme generation to virtual pre-performance, solves the problems of insufficient early warning accuracy, static risk evaluation and lack of forward-looking verification of the disposal scheme, and improves the emergency response capability and decision scientificity of the power grid in response to flood disasters.

The application belongs to the technical field of rotating machinery condition monitoring and fault diagnosis. A bearing failure evaluation method and system are provided. The bearing vibration signal is obtained and processed by mean removal and absolute value to obtain a to-be-processed signal. Then, the lower threshold of the tail part is determined, and the tail sample set with an amplitude greater than the threshold is screened out. Then, a soft-truncated power-law distribution model is constructed based on the tail sample set, and the distribution parameters including the power-law tail index, the truncated scale parameter and the truncated smooth index are solved by maximum likelihood estimation. Then, the analytical expression of the improved Gini index is constructed according to the distribution parameters, and the bearing degradation degree index is calculated. Finally, the bearing degradation curve is constructed according to the degradation degree index of different time periods. The application accurately describes the impact characteristics of the tail part of the vibration signal by the soft-truncated power-law model, and quantifies the degradation degree by the improved Gini index, which can effectively evaluate the health status and failure trend of the rolling bearing.

The application discloses a kind of unmanned plane launching device, comprising: support, barrel, driving part and monitoring component, barrel is movably connected to support, and with the first state of folding relative to support and the second state of unfolding relative to support, driving part is connected to barrel, and can be movable relative to barrel, for propelling unmanned plane launch in barrel, monitoring component is connected to barrel, for real-time monitoring the stress size that the lateral wall of barrel suffers.The application can effectively solve the problem that the health state of the launching barrel cannot be perceived in real time in the prior art, resulting in the lack of fault diagnosis based on real-time data for unmanned plane launching barrel.

This invention provides a time-causal graph-based fault diagnosis method for carrier-based aircraft in landing scenarios, addressing the technical problem that data-driven carrier-based aircraft fault diagnosis methods cannot meet the high-precision requirements of practical fault diagnosis. First, the basic structure and variable parameter table of the triplet time-causal graph model are defined, transforming the nonlinear mathematical model into a small-deviation form. The time-causal graph model of the carrier-based aircraft is determined using an equation method. Typical failure modes are classified according to the residual characteristics of the failure injection parameters, ultimately obtaining a failure feature vector table for subsequent fault diagnosis. Then, the residuals of the observable parameters of the carrier-based aircraft under fault conditions are calculated. Finally, the original failure feature vectors inferred from the time-causal graph model are corrected using the failure feature vectors trained from simulation data, resulting in a feature vector table of failure modes trained from data, thus completing the quantitative description of fault features. This method achieves carrier-based aircraft fault diagnosis based on the time-causal graph model in landing scenarios that meets the high-precision requirements of practical fault diagnosis.

This invention provides a gear power transmission device for a speed reducer, relating to the field of gear reducer technology. The device includes a speed reducer body and an intelligent monitoring and self-cleaning system mounted on a base plate. This invention, through real-time monitoring of multiple parameters such as oil viscosity, abrasive particle concentration, and morphology, can accurately capture early anomalies and effectively distinguish wear types. After diagnosing anomalies, it can automatically purify the lubricating oil online, removing harmful abrasive particles without stopping the machine, effectively extending the lifespan of the oil and equipment. The highly integrated multi-functional modules within a unified detection box result in a compact structure, improving the overall reliability of the system and avoiding the looseness and unreliability issues of external structures in harsh industrial environments, thus enhancing the intelligence level of fault diagnosis. The introduction of machine learning-based automatic particle morphology recognition technology replaces offline analysis relying on professionals, lowering the technical threshold and making fault diagnosis more intuitive and efficient.

This invention discloses a method for tracing and diagnosing faults in large-scale eVTOL motors and electronic speed controllers (ESCs), belonging to the field of eVTOL fault diagnosis technology. This method collects operational data of different fault types from both the motor and ESC sides, and constructs a coupled fault feature library through preprocessing, feature extraction, and sample annotation. Based on this feature library sample set, a fault tracing and diagnosis model is constructed and trained, with parameters optimized to achieve the required recognition accuracy. Real-time operational data is simultaneously collected, preprocessed, and input into the model to obtain fault tracing and diagnosis results. Finally, a preset fault handling rule library is matched to generate corresponding handling suggestions, which are then transmitted to the flight control system and the ground maintenance platform. This method achieves precise tracing of the fault source, type, and severity, overcoming the limitations of traditional methods that can only detect the existence of faults, improving fault investigation efficiency and diagnostic accuracy, and providing technical support for eVTOL flight safety.

By converting various types of data into data in a more easily usable format, failure diagnosis can be performed more efficiently using the data.A failure diagnosis system includes: an edge system which is an electronic system; a failure diagnosis device configured to diagnose a failure of the edge system; and a computer which is an external device. The failure diagnosis device distinguishes data acquired from the edge system and the computer according to a type of the data, extracts a data element included in the data based on predetermined interpretation processing for the data, converts the data element into a predetermined data code corresponding to an item of a common data format regardless of the type of the data, and generates diagnosis intermediate data in which the data code is assigned to the corresponding item, and performs diagnosis analysis of a failure in the edge system using the diagnosis intermediate data.

A fault diagnosis procedure for detecting faulty components in a vehicle, wherein, for at least one identifiable fault cause of a faulty component, a system parameter of the vehicle that is influenced by the fault cause is determined and compared with a target value of the system parameter, and a determined signal deviation between the determined system parameter and the target value of the system parameter is compared with a stored fault characteristic signal deviation, and if the determined signal deviation matches the fault characteristic signal deviation, the fault cause and / or faulty component associated with the fault characteristic signal deviation is uniquely identified, wherein the entire development process for the fault diagnosis procedure essentially consists of the following six individual steps, which are executed sequentially: - Selection of faults to be diagnosed, whereby in this first step the various components of the vehicle are analyzed in such a way that the possible causes of faults are listed for each component; - Structural analysis, whereby in this second step it is checked whether there is a possibility in principle of model-based diagnostics of the system; - Creation of a nominal model, whereby in this third step, so-called nominal models are created for those system parameters that are used and evaluated for the identification of a faulty system component, in which a normal operation of the system component is depicted; - Sensitivity analysis, in which, in this fourth step, defined causes of failure are imprinted into the system and their effects on the relevant system size(s) are considered using the nominal model, thereby identifying a unique assignment of a cause of failure or a faulty system component to its effect on the relevant system size; - Creation of fault models, whereby in this fifth step the knowledge about the effect is stored in a reference source onboard in the vehicle, whereby, based on this reference source, a statement can be made at any time valid for the diagnosis as to whether this cause of fault is present or not and - Integration into a diagnostic system, whereby in this sixth step the developed diagnostic procedure is transferred to a corresponding target control unit in the vehicle.

This invention belongs to the field of natural gas transmission metering technology, and discloses a method, system, and storage medium for fault diagnosis of natural gas sales metering instruments based on deep learning. First, multiple diagnoses are performed based on the metering values ​​of the natural gas sales metering instruments, the input values ​​of the gas source pipeline, and the output values ​​of the terminal pipeline, resulting in multiple sub-diagnostic results. Then, these sub-diagnostic results are weighted and fused to obtain the final diagnostic result. This invention significantly improves the accuracy of fault diagnosis for natural gas sales metering instruments.

The application discloses a kind of diagnosis method, device, equipment, unit and medium of fan yaw system, belong to wind power generation technical field.This application embodiment comprehensively considers the yaw data of fan yaw system and the associated data associated with fan yaw system from multiple dimensions, can more accurately identify the fault of fan yaw system.Moreover, for the data of different dimensions, the yaw state of yaw system and the feathering state of blade and other features can be further determined, the fine processing of yaw data and associated data is realized, so that the fault of fan yaw system can be diagnosed according to different working conditions, so that the fault component can be accurately located, without further investigation of operation and maintenance personnel, improve the efficiency of fault diagnosis.

This application discloses a method, device, terminal, and medium for multi-condition fault diagnosis of equipment based on the Industrial Internet of Things (IIoT). The method includes: acquiring operational monitoring data of the equipment under various operating conditions; obtaining a real-time operating condition health coefficient, an operating condition degradation trend coefficient, and a fault risk prediction cycle for the equipment based on the operational monitoring data using a preset multimodal fusion model; and obtaining a target diagnostic result based on the real-time operating condition health coefficient, the operating condition degradation trend coefficient, the fault risk prediction cycle, a preset standard health coefficient corresponding to the real-time operating condition health coefficient, and a preset fault level threshold. This application aims to improve the accuracy and timeliness of fault diagnosis under multiple operating conditions and solve the problems of misdiagnosis and missed diagnosis of faults under complex operating conditions.

This invention discloses a fault diagnosis method, apparatus, device, and medium for a transmission shifting system. Specifically, the fault diagnosis method for the transmission shifting system may include: upon receiving a diagnostic activation command for the shifting system to be diagnosed, determining the current vehicle state corresponding to the shifting system to be diagnosed; if the current vehicle state meets the vehicle power-on condition, performing a first fault diagnosis on the shifting system to be diagnosed; and if the current vehicle state meets the vehicle start-up condition, performing a second fault diagnosis on the shifting system to be diagnosed. The technical solution of this invention can accurately diagnose faults in the transmission shifting system, thereby improving the stability of the transmission shifting system.

The application discloses a function diagnosis method, device and equipment and a storage medium. The method comprises the following steps: if a vehicle fault is detected, a fault diagnosis code is acquired, and a target record is determined in an operation log according to the fault diagnosis code; a target application program interface is determined according to the target record, and a target function matched with the target application program interface is determined; a function category of the target function is determined according to a function clustering result determined in advance based on a vehicle function; and all functions associated with the function category are diagnosed. The technical scheme solves the problems that it is difficult to analyze and diagnose a function fault of an automobile and the function fault is difficult to be completely eliminated, can improve the function fault diagnosis efficiency, increase the reliability of eliminating the function fault, and avoid the function fault from repeatedly occurring.

This invention relates to a method for diagnosing rotor faults in marine propulsion motors, belonging to the field of motor fault diagnosis technology. The method first acquires labeled source domain data and unlabeled target domain data; then, it constructs a diagnostic model consisting of a feature extractor, a classifier, and a domain discriminator; model training aims to minimize a joint loss function, which integrates class-weighted focus loss, adversarial domain adaptation loss, and class center constraint loss. Through adversarial training between the feature extractor and the domain discriminator, the model can learn domain-invariant and fault category-sensitive feature representations even under class imbalance conditions; finally, the trained model is used to diagnose faults in the target domain data. This invention provides an innovative fault diagnosis method that effectively solves both domain adaptation and class imbalance problems, enabling accurate and robust identification of marine propulsion motor rotor faults in complex real-world scenarios.

This disclosure provides a method, system, and storage medium for diagnosing short-circuit faults in a pre-charging circuit, relating to the field of electric vehicle technology. The method includes: acquiring current multi-dimensional operating parameters of the pre-charging circuit during the pre-charging process; generating theoretical values ​​corresponding to diagnostic parameters in the multi-dimensional operating parameters under the current operating condition when no short-circuit fault occurs in the pre-charging circuit; determining whether a short-circuit fault has occurred in the pre-charging circuit based on the diagnostic parameters and their corresponding theoretical values; and executing preset short-circuit protection measures when a short-circuit fault occurs in the pre-charging circuit. This method can be used to quickly detect whether a short-circuit fault exists in the pre-charging circuit during the pre-charging process, and ensures the accuracy of the diagnostic results through a multi-parameter fusion diagnostic approach, enabling timely protective measures to be taken, shortening the diagnostic time while preventing the fault from escalating.

The present invention relates to diagnosing a failure of and providing maintenance information about an ATM. When a failure occurs in the ATM, a node at which an abnormal sensor value is initially measured during a failed transaction is identified on the basis of sensor values measured by various sensors provided in the ATM. A failure cause providing module that provided an abnormal operation cause for the failure is predicted and information about a failure occurrence module in which the failure actually occurred and information about the failure cause providing module are provided to a maintenance worker on site, supporting the maintenance worker so that the maintenance worker can, during a failure recovery process, repair the failure occurrence module along with the failure cause providing module that caused the failure.

The application discloses a device troubleshooting method, device, equipment and program product, solves the problems of insufficient information utilization, fixed diagnosis process and inability to automatically execute long-chain reasoning in the existing troubleshooting scheme. The scheme includes: performing device entity recognition on the multi-modal description information of the user input device for reporting a fault, obtaining the device attribute information of the device for reporting a fault. Retrieve the standard working state information corresponding to the device attribute information from the device knowledge base, and compare the multi-modal description information with the standard working state information to obtain the abnormal description information of the device for reporting a fault. Retrieve the diagnosis knowledge corresponding to the abnormal description information from the fault diagnosis knowledge base and / or the fault diagnosis historical case base to generate the diagnosis process of the abnormal description information. Configure the diagnosis process as a diagnosis chain cascaded by at least two diagnosis task nodes, execute the diagnosis task nodes in the diagnosis chain in path order, obtain all diagnosis results, generate and output a fault diagnosis report for the device for reporting a fault.

The present disclosure relates to the technical field of vehicles, and particularly relates to a fault diagnosis method, device, equipment and storage medium. The method comprises the following steps: according to a fault diagnosis sequence corresponding to a fault event set, before diagnosing a first fault event, acquiring first diagnosis state information according to a first inhibition mask of the first fault event and a first state mask corresponding to a second fault event, the second fault event being a fault event of a previous diagnosis of the first fault event, and the first state mask being a state mask acquired according to first diagnosis information of the second fault event; in a case where the first diagnosis state information indicates diagnosing the first fault event, diagnosing the first fault event, acquiring second diagnosis information of the first fault event, and updating the first state mask. The present disclosure can reduce the complexity of fault diagnosis code while reducing the accuracy of fault diagnosis, and improve the implementation convenience of fault diagnosis and the convenience of code maintenance.

The application discloses a failure diagnosis method of a steer-by-wire device. The working states of various functional units in the steer-by-wire device are monitored by a plurality of function monitoring sensors in a sensor network. When a failure of a functional unit is monitored, the functional unit is identified in the form of failure identification data, and the working state of the steer-by-wire device is evaluated according to a steering function failure evaluation parameter obtained from the failure identification data of the functional unit, so as to give a prompt for repairing or maintaining the steer-by-wire device. The failure identification data of the functional unit is obtained according to a unique mass value of each function monitoring sensor that discovers the failure. The failure identification data can not only identify the failure state of each functional unit of the steer-by-wire device, but also identify the failure position, so that the failure identification mode is greatly simplified, and the failure position of the function unit with a redundant design can be accurately identified.

This invention discloses a method for diagnosing hidden damage in marine bearings using a hybrid attention and Inception graph convolution approach, belonging to the field of marine rotating machinery fault diagnosis technology. It aims to solve the problem of low accuracy in existing bearing diagnosis methods for identifying hidden damage. This invention employs a Min-Max normalization algorithm to process vibration signals, converting one-dimensional vibration signals into two-dimensional images through Gram angle difference fields, Markov transfer fields, and continuous wavelet transforms. A Hatt-GCN-Inception model is constructed, embedding a differential attention module within the model to enhance the sensitivity of damage features. The model's end fuses GCN to capture feature topological correlations. A dual optimizer combined with gradient accumulation and FP16 mixed-precision training techniques are used to achieve efficient model training. Pre-training is conducted using the CWRU dataset, and transfer validation is performed on the MFPT variable load dataset containing four types of noise. This invention offers high diagnostic accuracy and fast detection speed, with a single sample detection time of only 0.005 seconds. The accuracy under variable load and noisy conditions still reaches 99.95%, making it suitable for real-time and accurate fault diagnosis in marine bearings.

The application belongs to the technical field of sensor fault diagnosis and error compensation, and particularly discloses a digital weighing sensor error self-diagnosis method. The application improves the early detection sensitivity and diagnosis reliability of the sensor mechanical structure hidden fault through sound vibration and electrical signal double baseline fusion and multi-stage trigger diagnosis. The application realizes quantitative evaluation of the measurement error caused by the hidden fault through the establishment of a fault coupling model and an error influence mapping model. The application can diagnose the fault and suppress the measurement error in real time online through an adaptive compensation algorithm, thereby improving the temporary measurement accuracy and system usability of the sensor in the unhealthy state. The application realizes fault severity grading and predictive maintenance support through the calculation of a comprehensive health index and a predicted maintenance window.

The invention provides a refrigeration device and a fault diagnosis method and system thereof, and belongs to the technical field of fault diagnosis. According to the method, when key data in first operation data of a refrigeration device to be diagnosed is different from corresponding key data in second operation data of normal operation of the refrigeration device in a preset environment, the key data in the first operation data is corrected to be the same as the corresponding key data in the second operation data; the operation data of the refrigeration device to be diagnosed are corrected to be close to the operation data of the refrigeration device in the preset environment to a certain extent, and then the fault diagnosis model obtained by training in the preset environment is called for diagnosis, so that the diagnosis accuracy of the model can be improved. When the operation condition of the refrigeration device to be diagnosed is judged to be inconsistent with the operation condition of the refrigeration device in the preset environment, the operation data of the refrigeration device to be diagnosed and the operation condition of the refrigeration device in the preset environment are close through correction, and then the fault diagnosis model is called for fault diagnosis, so that the diagnosis accuracy of the fault diagnosis model can be improved.

This application discloses a method, apparatus, computer device, and medium for diagnosing faults in a memory management unit. The method includes: intercepting error events in the hardware processing flow of the simulated input / output memory management unit in an emulator, and extracting standardized error information before executing an error notification process dependent on the guest operating system; adding error records containing standardized information to a circular error buffer independent of the guest operating system address space, the circular error buffer being located in the memory space of the emulator process and configured to store error records in chronological order; responding to query requests from outside the emulator through a management protocol interface provided by the emulator, and obtaining error records from the circular error buffer to generate a diagnostic report.

This invention discloses a method and system for diagnosing temperature compensation faults in inertial measurement units (IMUs). The method achieves highly reliable fault detection by introducing a redundant temperature source T2 and a functional safety-oriented diagnostic logic. Instead of directly comparing temperature signals, the method substitutes the primary temperature T1 and the redundant temperature T2 into the IMU error compensation model to calculate two sets of compensation results B. compT1 and B compT2 The difference between residual offset Only if the difference is residual offset A functional failure is only identified when the threshold is exceeded by reverse engineering based on application safety requirements. This method effectively solves the shortcomings of traditional diagnostic methods, such as high cost, cold start failure, and high false alarm rate, and meets functional safety requirements.