17 results about "Fault modelling" patented technology

System (1) for predictive diagnosis of fault conditions of components (5) of the powertrain of a fleet (3) of electrically powered mobile working machines (4), wherein the system comprises: at least one working machine (4) with a communication module for sending operating data (BG); and a central unit (2) spatially separate from the working machine (4), which is designed to receive the operating data (BG) from the working machine (4) via a communication network, characterized by a data processing unit implemented in the central unit (2) with: a) an anomaly detection module configured to detect deviations from normal behavior in the operating data (BG) received from the working machine (4) that indicate an impending fault; and b) at least one hybrid fault model (24) configured to analyze the relevant operational data (OD) after detection of a deviation by the anomaly detection module, wherein the hybrid fault model (24) combines physical domain knowledge about the component (5) and data-driven models to specify a fault type and determine a fault severity.

The application discloses a camera fault determination method, device and computer readable storage medium. The camera fault determination method comprises the following steps: obtaining script data of a to-be-identified object; determining a fault identification threshold of the to-be-identified object according to a pre-trained fault model; and determining a fault determination result corresponding to the to-be-identified object according to the fault identification threshold and the script data. The to-be-identified object comprises a camera, a client and / or a video monitoring platform. The fault identification threshold of the to-be-identified object is determined through the pre-trained fault model, and the fault determination result of the to-be-identified object is determined based on the fault identification threshold and the script data. In this way, the offline troubleshooting efficiency of the camera and the accuracy of the fault determination are improved.

Methods, computing systems, and computer-readable media for a machine learning method of modeling fault-related properties of a geological region are presented. The techniques include: obtaining seismic geological data for a geological region; obtaining from a user identifications of a plurality of faults in the geological region; automatically generating values for descriptors of respective faults of the plurality of faults; automatically partitioning faults of the plurality of faults into a plurality of groups according to the values for the descriptors; obtaining a mapping of respective groups of the plurality of groups to modeling parameter values; applying the mapping to a fault in the geological region outside of the plurality of faults to obtain a modeling parameter value for the fault outside of the plurality of faults; and modeling a fault-related property of the geological region based on the modeling parameter value for the fault outside of the plurality of faults.

The invention provides a bearing fault detection method and device, equipment, a storage medium and a product. The method comprises the following steps: acquiring rotating speed data and vibration data of a target bearing in a running state; constructing a corresponding fault simulation model based on the structure parameters of the target bearing; based on the rotating speed data, inputting the rotating speed data into the fault simulation model for simulation to obtain a simulation signal, the simulation signal comprising potential fault features; a periodic signal in the simulation signal is analyzed and determined, a guidance information sequence is obtained, and the guidance information sequence is data of a feature area related to a fault in the identification signal; and extracting a fault feature signal according to the vibration data and the guidance information sequence to obtain a fault detection result. The physical condition of the target bearing obtained through simulation can stably capture features consistent with those of a physical fault model, and stable and accurate weak fault early warning is achieved.

The invention belongs to the technical field of motor fault simulation, and particularly relates to a single-phase open-circuit fault simulation method and system of a permanent magnet synchronous motor for a motor simulator. Steady-state switching ripples and a transient regulation process of the open-circuit phase current are avoided, and the open-circuit phase current is ensured to be zero all the time, so that the fault simulation precision is improved; meanwhile, in the fault cut-in process, through mutual cooperation of a fault control switch and a fault current buffer switch connected with the fault control switch in parallel, when the fault current buffer switch is closed, the fault control switch is switched off, and when current in the fault current buffer switch reaches a zero crossing point, single-phase open-circuit fault simulation is carried out, and open-circuit phase current is smoothly cut off. In combination with smooth switching between a normal model and a fault model, smooth switching of a single-phase open-circuit fault is finally realized, overvoltage caused by direct cutting off of an inductive current is avoided, and the simulation precision is further improved while the equipment safety is ensured.

The application provides a three-dimensional complex fault model construction method based on deduction and related equipment, including: determining fault data of a target area, and extracting and analyzing the fault data to determine attribute data, planar fault discrete points and profile elevation data; determining a first fault throw and a discrete point throw change type, and determining hanging wall discrete point coordinates and footwall discrete point coordinates according to the first fault throw and the discrete point throw change type; determining a stratigraphic layer spacing, determining a second fault throw change range and a second fault throw according to the stratigraphic layer spacing and the first fault throw; prioritizing the faults, determining a priority order, and performing intersection deduction according to the priority order to determine a first stratigraphic model; performing intersection deduction on the faults and special geological structures to determine a second stratigraphic model; encrypting the discrete points of each fault in the stratigraphic model to determine a discrete point set, and performing Delaunay triangular grid subdivision on the discrete points to generate a fault surface model.

The invention relates to the field of rail transit, and relates to a rail transit troubleshooting method and system, and the method comprises the steps: constructing a tree fault model, setting a plurality of nodes for the tree fault model, each node representing a fault, and setting a logic relation between the nodes; acquiring a fault occurring in real time in the train, and selecting a corresponding tree fault model; dividing the nodes in the tree fault model into different types of nodes according to the logical relationship among the real-time vehicle-ground wireless signals, the real-time manual detection data and the nodes, and deleting the nodes of which the faults do not occur; and arranging the remaining nodes in the model, and generating a troubleshooting guide flow chart corresponding to the real-time fault of the train according to the arrangement sequence. According to the method, the real-time vehicle-ground wireless signals and the real-time manual detection data are combined, screening and updating of the tree fault model are rapidly completed, troubleshooting guidance is performed according to the updated model, the problem of low troubleshooting efficiency is solved, and the troubleshooting accuracy is improved.

The application provides a composite fault model library construction method and device, electronic equipment and a storage medium, which are applied to a pumped storage power station. The method comprises the following steps: obtaining multiple types of basic fault elements and historical fault reports; performing coupling relationship analysis on the multiple types of basic fault elements based on the historical fault reports, constructing a fault coupling graph atlas with the basic fault elements as nodes and the coupling relationship between faults as directed edges, and assigning a coupling probability to each directed edge; performing sub-atlas activation processing on the fault coupling graph atlas based on a current simulation working condition to obtain an activated sub-atlas associated with the current simulation working condition; performing weighted sampling on the activated sub-atlas based on the coupling probability to generate a composite fault combination; and mapping the composite fault combination to a real-time digital simulation platform through a high-fidelity injection mechanism and modifying corresponding model parameters to complete the construction of a composite fault model. In this way, a high-fidelity composite fault scene is generated, and the comprehensiveness and authenticity of fault simulation are significantly improved.

The invention discloses an AR-based spacecraft electronic system diagnosis and maintenance system, solves the problems of fault diagnosis and auxiliary maintenance, and belongs to the technical field of spacecraft comprehensive test and diagnosis. Comprising a closed-loop control measurement system, an embedded diagnosis and maintenance management system, a fault injection system, a fault diagnosis and maintenance knowledge system and an AR fault maintenance interaction system. The closed-loop control measurement system achieves on-orbit real-time state monitoring of a spacecraft electronic system, the embedded diagnosis and maintenance management system completes diagnosis algorithm configuration and fault injection control, the fault injection system achieves fault injection, and the fault diagnosis and maintenance knowledge system provides fault model and maintenance knowledge support. The AR fault maintenance interaction system realizes virtual-real fusion maintenance guidance, and each subsystem realizes a data flow closed loop through a standardized communication protocol.

A method for vehicle fault management includes generating, for a vehicle system, a fault model including a plurality of faults using design failure mode and effect analysis information and parsing each of the faults of the plurality of faults by subsystem of the vehicle system. The method also includes determining, for a respective fault of the plurality of faults, whether the respective fault is associated with at least one existing diagnostic trouble code based on fault code requirement information. The method also includes, in response to a determination that the respective fault is associated with at least one existing diagnostic trouble code, associating, in a fault database, the at least one existing diagnostic trouble code with the respective fault.

The invention discloses a permanent magnet synchronous motor broken tooth fault diagnosis and fault-tolerant control system based on multi-source signals in the technical field of automatic control and adjustment. The system comprises a multi-source signal acquisition module, a fault diagnosis module, a disturbance estimation module and a fault-tolerant control law module. The multi-source signal acquisition module acquires a real-time operation signal; the fault diagnosis module processes the real-time operation signal and extracts a fault feature signal, and the fault diagnosis module adopts a coupling broken tooth fault model to calculate the fault feature signal; the disturbance estimation module obtains an estimated value of total disturbance based on the fault characteristic signal; the fault-tolerant control law module generates a permanent magnet synchronous motor system control instruction based on the estimated value of the total disturbance; according to the method, an FMAESO fault-tolerant control strategy is provided, disturbance and specific faults are subjected to integrated estimation and compensation, and an independent diagnosis unit is not needed; the stability and the control precision of the motor in wide speed range operation are improved, the robustness is high, and the system development period is shortened.

This invention discloses an automated control method for the operating mechanism of a molded case circuit breaker (MCCB), specifically relating to the field of MCB technology. By monitoring electrical parameters in real time and transmitting them to the control system, and performing comparative analysis based on preset thresholds and fault models, the system can promptly detect faults and generate control commands. The system can identify and prioritize multiple fault scenarios, automatically executing closing or opening actions to ensure the reliability and stability of the power system. Furthermore, this invention introduces a judgment mechanism based on circuit recovery status. After the circuit is disconnected, the system rationally determines whether to perform a recovery operation based on the status of the circuit breaker and the recovery status of the power system, effectively improving the self-recovery capability and fault diagnosis capability of the power system. This method can adapt to the effects of high loads, complex environments, and power grid fluctuations, significantly improving the reliability and accuracy of the automated control system.

This invention provides a multi-sensor fault diagnosis method for hydropower units, belonging to the field of mechanical fault diagnosis technology. The method includes collecting vibration signals from multiple sensors of a hydropower unit at different sampling frequencies; preprocessing the vibration signals to obtain standardized three-dimensional data; and enhancing the three-dimensional data. A multi-sensor fault model for the hydropower unit is constructed and trained. Based on the enhanced three-dimensional data, the trained multi-sensor fault model is used to diagnose faults in the multi-sensor system of the hydropower unit. This invention solves the problems of heterogeneous sampling frequencies, multi-scale distribution of fault features, and difficulty in capturing time-series dependencies in multi-sensor hydropower unit vibration signals. This invention is applicable to intelligent fault identification in multi-sensor monitoring scenarios such as hydropower units.

This application provides a method, system, apparatus, and storage medium for simulating and resolving fault shadow zones. The method includes: establishing a two-dimensional geological model and a physical model; performing laser excitation and flume excitation on the established physical model. The present invention utilizes numerical simulation for two-dimensional imaging and physical simulation for three-dimensional acquisition to image fault shadows. This is mainly achieved by improving the accuracy of velocity modeling and the imaging method. The application of Gaussian beam velocity modeling and migration effectively solves the problem of shadow zone imaging, avoiding insufficient velocity accuracy, imprecise velocity characterization of fault shadow zones, and velocity errors leading to the pull-down of the in-phase axis. In this study, a simple inverse fault model was created through flume physical simulation (closer to marine acquisition) and laser excitation (similar to land acquisition), which can reveal the reason why faults are not imaged under accurate experimental strata velocities.

This invention discloses a fault detection system and method for hydropower station equipment based on multi-source information fusion, including a central control host, a fault management server, an inspection robot, environmental monitoring sensors, and vibration sensors. The fault management server includes a historical record database and a fault detection module. The fault detection module is used for fault diagnosis of hydropower station equipment. The equipment classification module is used to classify hydropower station equipment according to fault phenomena. The inspection frequency setting module is used to set the inspection frequency of the inspection robot. This invention sets different detection methods for different categories of equipment, improving the targeting of fault detection. This invention adjusts the inspection frequency according to the historical fault situation of the equipment, making it easier to find high-frequency faults and avoiding repeated inspections of low-frequency faults, thus saving resources. This invention can effectively ensure the consistency of the frequency of multiple input data of the associated equipment fault model, ensuring the normal operation of the fault model.

The invention relates to a fault analysis method for the unmanned driving state of a monorail crane, and belongs to the field of unmanned driving control analysis of monorail cranes. According to the technical scheme, the method comprises the steps that a locomotive running state model is established, a locomotive unmanned driving state model is established, locomotive unmanned driving operation behaviors are monitored, the relation between the unmanned driving state model and the locomotive running state model is established, and the relation between the speed, the acceleration and the locomotive unmanned driving state is established. The method comprises the following steps: collecting locomotive fault data, establishing a fault model, listing a fault occurrence number and a serial number according to each type of faults, and sorting the types of the faults into a fault tree; and after a locomotive fault occurs, comparing the fault sequence number and the fault number with the actually measured data, and recording the specific position of the fault. According to the locomotive running state model and the locomotive driving state-running state model, the locomotive fault type is judged. The fault detection efficiency of unmanned driving of the monorail crane is improved, and more data support is provided for unmanned driving.

The application relates to the technical field of power information physical system, in particular to a power CPS interlocking fault modeling simulation analysis method and related equipment, which comprises the following steps: collecting voltage data, active power, reactive power of each power node in the power CPS at each collection time and data exchange amount between each information node; obtaining related power nodes of each power node; obtaining active power difference between each power node and other power nodes at each collection time; calculating the trend similarity of each power node at each collection time; then obtaining each power community and each information community; calculating the overlap degree of each information node at each collection time; and then re-dividing the power community and analyzing the interlocking fault of the power CPS. The application improves the analysis and processing efficiency of the cascading fault.