28 results about "Fault correction" patented technology

The invention discloses an intelligent fault diagnosis method, device and equipment and a storage medium, and relates to the technical field of new energy automobile thermal management, and the method comprises the steps: obtaining a sensor collection parameter, vibration feature information and a heat source coupling parameter; inputting the sensor acquisition parameters, the vibration characteristic information and the heat source coupling parameters into a reinforcement learning model to predict a potential fault, and determining a fault type, a fault confidence coefficient and fault evolution trend information; performing fault identification based on the fault type and the fault confidence, and determining fault type information; and generating a corresponding fault correction report based on the fault category information and the fault evolution trend information. According to the method, the potential fault is predicted in advance through the reinforcement learning model, the type, confidence and evolution trend of the potential fault are accurately deduced, a dynamic fault correction report is generated, the fault is intervened in advance, the diagnosis accuracy is improved, and fault diagnosis from passive response to active prevention and considering reliability and energy efficiency is realized.

Systems and methods for detecting and diagnosing machine faults are discussed. An exemplary system includes at least one sensor node to sense a signal indicative of an operation status of a machine part, and a machine health analyzer circuit to generate a computational machine fault model comprising an autoencoder (AE) network and an associative module. The AE network encodes the sensed signal into signal features in a latent feature space, and decodes the signal features to produce a reconstructed signal. The associative module transforms the encoded signal features into an associative output using a dynamically updatable codebook. The machine health analyzer circuit detects a presence or absence of fault in the machine part based on reconstruction losses determined respectively from the reconstructed signal and the associative output. The detected fault can be presented to a user or to a process such as fault diagnosis or fault correction.

The invention discloses a distribution network fault processing method based on self-learning time synchronization and a distribution network fault processing system thereof, and relates to the technical field of distribution network faults. In order to solve the defects that time difference exists in existing distribution network terminal data interaction, fault misjudgment is serious, and time synchronization precision is insufficient, the method comprises the steps that whether satellite signals meet preset conditions or not is judged firstly; when the satellite signal meets a preset condition, establishing a self-learning model of a temperature excursion-frequency offset relationship according to the acquired clock data and the temperature data of the chip; when the satellite signal does not meet the preset condition, performing dynamic compensation on current clock data by adopting the self-learning model; cooperative time keeping is carried out through satellite communication between distribution network terminals and FPGA sampling compensation clock state quantity, so that fault correction is realized. The method is mainly used for time synchronization through self-learning, so that the accuracy of distribution network fault judgment is improved.

Embodiments of the present invention disclose a method, device, equipment and medium for determining a structural trap volume correction coefficient. Among them, the method includes: determining the trap type of the structural trap to be measured, and determining the standard cross-section of the structural trap to be measured according to the trap type; the trap type includes anticline type, faulted anticline type and fault block type, and the standard cross-section is used to represent the plane where the bottom surface of the structural trap to be measured is located; determining the target parameter information of the structural trap to be measured on the standard cross-section, and determining the reference correction coefficient of the structural trap to be measured according to the target parameter information; the reference correction coefficient includes at least two of amplitude correction coefficient, fault correction coefficient and reservoir correction coefficient; determining the volume correction coefficient of the structural trap to be measured according to the reference correction coefficient. The technical solution can quickly and accurately obtain the volume correction coefficient of the structural trap approaching the underground real situation based on the standard cross-section of the structural trap, which helps to improve the prediction speed and prediction accuracy of the resource volume of the structural trap.

The present invention discloses a method for detecting and controlling vehicle brake failure. The method includes the following steps: when a vehicle brake fails and no brake system fault is reported, the method enters a brake caliper clearance fault processing flow, determines whether a brake caliper clearance fault is present, and performs a brake caliper clearance fault correction operation. Advantages of the present invention include: accurately detecting the type of brake system failure and providing an alarm; simultaneously, different control strategies are employed for each failure type to ensure that the brake system provides reliable braking force, ensuring safe braking of the system; and, without requiring hardware system modifications, the method can be implemented by integrating it into the brake system, resulting in zero hardware cost and convenient and reliable implementation.

The present disclosure relates to a BMS that includes processor(s) that execute instructions to obtain a fault rule related to a building parameter and determine that a fault has occurred based on the fault rule and initial BMS data indicating an initial value of the building parameter. The instructions cause the processors to perform an automatic fault correction process including increasing or decreasing an operational value of building equipment that operate to affect the building parameter by a preset interval, operating the building equipment using the increased or decreased operational value to affect the building parameter, and determining whether the fault was resolved. Responsive determining that the fault was not resolved, the instructions cause the processor(s) to repeat the automatic fault correction process until either the fault is resolved, or the operational value of the building equipment reaches a minimum or maximum value threshold.

The invention relates to the field of power grid data scheduling, and discloses a power grid business data intelligent scheduling method based on multi-source data fusion, which comprises the following steps: fusing different business data of a power grid for risk assessment and fault probability assessment of the power grid and user loads, and combining a fault probability assessment result to obtain a power grid business data intelligent scheduling result; and carrying out load intelligent scheduling strategy construction and fault correction strategy construction on the user load and the power grid in the high-risk state. The system can accurately and actively identify the operation risk of the power grid, achieves the intelligent load transfer of main and distribution cooperation, can prevent faults in advance, achieves the quick response when the faults occur, effectively reduces the power-off time and range, guarantees the normal power demands of all walks of life and residents, and improves the power utilization efficiency. And meanwhile, unnecessary equipment overload and redundant operation can be avoided, the operation cost of the power grid is reduced, the service life of equipment is prolonged, and the operation economic benefit of the power grid is improved on the whole.

A method (50) of applying a Crifford circuit to a correction fault in a qubit register (12) of a quantum computer (10) includes receiving (52) circuit data defining the Crifford circuit; receiving (56) additional data identifying one or more measurements for each of a plurality of faces (48) belonging to the lattice (44); issuing (58) a result code based on the circuit data, the result code comprising a series of result checks, each result check corresponding to an expected error syndrome for application of the Crifford circuit to the qubit register; and issuing (60) a topology result code based on the circuit data, the additional data and the result code, the topology result code comprising a series of check operators that support quantum error correction via a topology decoder, thereby enabling fault correction in the application of the Crifford circuit to the quantum bit register.

The present application is applicable to the field of remote sensing detection technology, and provides a method for locating a laser radar code disk fault, a method for correcting a code disk fault, and a device. The method includes: receiving a square wave level signal, which is obtained by filtering the analog voltage signal output by the photoelectric sensor; identifying a valid level jump signal from the square wave level signal each time, determining that the photoelectric sensor currently scans a code tooth, obtaining the number of the currently scanned code tooth, and counting the interval time between the photoelectric sensor currently scanning a code tooth and the last time it scanned a code tooth; obtaining the regular interval time between the photoelectric sensor scanning two adjacent code teeth when the code disk is normally triggered, comparing the interval time between the photoelectric sensor currently scanning a code tooth and the last time it scanned a code tooth with the regular interval time, and obtaining the abnormal code tooth number and the abnormal interval time corresponding to the abnormal code tooth number. The above method can quickly identify the abnormal fault triggered by the code disk jump tooth, and accurately locate the code disk fault.

A diagnostic system for a high-power laser system that detects and responds to malfunctions in the interlock of a laser safety system. When a fault is detected in any of the interlock circuits, the operating conditions of the laser are restricted or even shut down. To distinguish between typical transient faults caused by ambient conditions and persistent faults caused by a failed component or circuit that require external intervention for repair, the system uses a database of possible fault classifications to determine the likely type of fault. If the fault is likely to be transient, the laser is maintained in a reduced-power state until one or more temporary interlocks are applied as a backup for the failed interlock. The system can be repeatedly tested at full-power output for fault correction. Once recovered from a fault, the backup interlock can be disabled and the system returned to full operation.

The present application provides an online resistance identification method for a high-resistance contact fault in a multi-phase permanent magnet synchronous motor, and relates to the technical field of multi-phase motor fault-tolerant control. The method comprises: determining the position of the fault phase where the high-resistance contact fault occurs, selecting a corresponding compensation coefficient matrix, calculating a corresponding fault correction coefficient matrix based on the compensation coefficient matrix in combination with the stator current and the coordinate transformation matrix, and extracting the fault correction coefficient; obtaining an expanded equation group of a fault state mathematical model taking into account the neutral point offset in a rotating coordinate system, selecting at least one voltage equation in the expanded equation group as a target equation, and determining an online resistance identification model that satisfies the recursive least squares method based on the target equation; inputting the stator voltage and stator current, electrical angular velocity, and fault correction coefficient in the rotating coordinate system corresponding to the target equation into the online resistance identification model to obtain a resistance matrix. The method can identify high-resistance contact resistance and stator resistance in real time, thereby improving the performance of the fault-tolerant control algorithm.

The invention relates to the technical field of artificial intelligence, can be applied to business system platforms of smart home, medical health and the like, and discloses an artificial intelligence-based fault identification and processing method, which comprises the following steps of: obtaining multi-modal information of task execution of an intelligent robot through image and audio information, constructing a task scene graph based on the image and audio information and generating an audio event tag, identifying an image key frame and creating key scene text description, analyzing the key scene text description and the audio event tag by using a large language model, identifying a subtask completion condition and detecting a fault, and if no fault exists, executing the next step; if yes, fault detection is carried out on a robot task execution result, if a fault is found, error recognition is carried out in combination with task description and a task plan, and according to a fault analysis or error recognition result, a fault correction task is generated to be executed by the intelligent robot. According to the method, the state information of the intelligent robot is converted into the text description which is easy to understand, so that the fault reason is positioned and corrected.

The invention discloses a telecontrol communication machine fault detection method and system, and the method comprises the steps: synchronously collecting a communication signal distortion parameter, a power fluctuation parameter, an environment electromagnetic interference parameter and a module temperature parameter in the operation process of a telecontrol communication machine; establishing a dynamic coupling fault model based on the coupling characteristics of the parameters to calculate fault deviation; dynamically adjusting a compensation coefficient according to the fault deviation and historical data; combining the fault deviation, the compensation coefficient and the electromagnetic interference change rate to generate a fault correction amount and performing adjustment; and feeding back an adjustment result to the dynamic coupling fault model to form a closed loop. The system correspondingly realizes the method. According to the method, the problem of fault misjudgment caused by influence of various factors is solved, and the fault detection accuracy and the response speed are improved.

The invention relates to the technical field of fault diagnosis, in particular to a mechanical equipment operation fault diagnosis method, and the method comprises the steps: carrying out the BAS clustering of to-be-diagnosed mechanical equipment based on the operation log data of the to-be-diagnosed mechanical equipment, obtaining a to-be-diagnosed BAS group to which the to-be-diagnosed mechanical equipment belongs, and obtaining a diagnosis target of the to-be-diagnosed mechanical equipment; determining associated mechanical equipment associated with the mechanical equipment to be diagnosed from the repaired mechanical equipment; determining an omission diagnosis process with omission in the fault correction process standard strategy according to the repaired fault correction process of the associated mechanical equipment; and adding the to-be-diagnosed omission diagnosis process to the fault correction process standard strategy to obtain an optimized fault correction process of the to-be-diagnosed mechanical equipment. According to the method, the personalized fault correction process of each mechanical device does not need to be determined in sequence according to factors such as characteristics of the mechanical devices, so that the accuracy and the efficiency are improved.

Commutation control method and system for a brushless motor and a readable medium. The method includes: if the commutation control fails upon detection of the zero crossing of the back EMF, acquiring a bus current value and / or a commutation time; performing processing based on the acquired bus current value and / or commutation time to acquire processed information; determining whether the processed information satisfies a preset condition; and, if the preset condition is met, controlling the motor to perform a forced commutation.If commutation faults occur in a brushless motor without a position sensor under certain operating conditions, a specific fault correction mechanism is used to correct the failed detection and control in order to ensure normal operating control of the motor, allowing the system to continue operating and increasing the stability of the system.

The embodiment of the present invention discloses a method, device, equipment and medium for determining the volume correction coefficient of a fault-block type trap. The method includes: determining the target parameter information of the fault-block type trap to be measured on a standard cross section; the standard cross section is used to represent the plane where the bottom surface of the fault-block type trap to be measured is located; determining the reference correction coefficient of the fault-block type trap to be measured according to the target parameter information; the reference correction coefficient refers to the fault correction coefficient and the reservoir correction coefficient; determining the volume correction coefficient of the fault-block type trap to be measured according to the reference correction coefficient. This technical solution can quickly and accurately obtain the volume correction coefficient of the fault-block type trap that is close to the actual underground situation based on the standard cross section of the fault-block type trap, which helps to improve the resource prediction speed and prediction accuracy of the fault-block type trap.

The invention provides an online resistance identification method for a high-resistance contact fault of a multi-phase permanent magnet synchronous motor, and relates to the technical field of fault-tolerant control of a multi-phase motor. The method comprises the steps of determining a fault phase position where a high-resistance contact fault occurs, selecting a corresponding compensation coefficient matrix, calculating a corresponding fault correction coefficient matrix according to the compensation coefficient matrix in combination with stator current and a coordinate transformation matrix, and extracting a fault correction coefficient; obtaining a fault state mathematical model expansion equation set considering neutral point offset under the rotating coordinate system, selecting at least one voltage equation in the expansion equation set as a target equation, and determining an online resistance identification model satisfying a recursive least square method based on the target equation; and inputting the stator voltage, the stator current, the electrical angular velocity and the fault correction coefficient under the corresponding rotating coordinate system in the target equation into an online resistance identification model to obtain a resistance matrix. According to the method, the high-resistance contact resistance and the stator resistance can be identified in real time, and the fault-tolerant control algorithm performance is improved.

An electrical generator system comprising a control device (2) configured to detect a fault (OL) in an electrical distribution unit (EDU), to issue a priority parameter setpoint value (PpCONS 2), for regulating the voltage (RegU), in the event of detecting a fault (OL), to an assisting converter (C2) having an assisting power (Pass), and, once the fault (OL) has been corrected, to issue a priority parameter setpoint value (PpCONS 2), for auxiliary regulation (RegA), to the assisting converter (C2) on the basis of the latest assisting power (Pass).

This disclosure provides systems, methods, and devices for memory systems that support SRAM fault correction. In a first aspect, a method includes receiving, by a memory controller coupled to a memory module through a first channel and configured to store data in and access data stored in the memory module through the first channel from a host device, data to be stored in a memory of the memory module, determining, by the memory controller, a row in the memory at which the data will be stored, determining, by the memory controller based on the row, an address associated with the row, wherein the address indicates one bit location in the row at which data will not be stored, and storing, by the memory controller, the data at the row in accordance with the address, wherein the data is not stored at the one bit location.

Message faulting is expected to be a major challenge in 5G—Advanced and especially 6G, due to increased pathloss and phase noise at FR2 frequencies, and exponential crowding of networks. Legacy methods for forward-correction or automatic retransmissions are unsuitable to the fast-paced demands of next-generation users. Therefore, disclosed herein is an AI-based receiver that interprets a corrupted message to determine the most likely meaning or intent, and thereby provides one or more candidate corrected messages along with a likelihood that each of the candidate corrected messages is indeed correct. The AI model may also be provided with data on the context or current activity of the receiver, data on the waveform of each message element, and other data available to the receiver, so that the AI model can further refine the likelihood values. By recovering corrupted messages in the receiver, a costly retransmission may be avoided, saving time and resource usage.

The embodiment of the invention provides a temperature drift self-healing control method and device for a high-temperature aging table of an integrated circuit. The temperature drift self-healing control method for the high-temperature aging table of the integrated circuit comprises the following steps: acquiring first output results of at least two temperature sensors of a high-temperature test box of the aging table at the current moment and second output results of a plurality of historical moments; determining the distance between the temperature sensors at the current moment based on the first output result and the second output result; determining a weight corresponding to each temperature sensor according to the distance; determining the fault type of the target temperature sensor based on the first output result and the second output result under the condition that the target temperature sensor is determined to have a fault according to the weight; and performing fault correction on the target temperature sensor based on the fault type.

The present disclosure relates to a system (100) for fault analysis and / or fault correction in a vehicle (10), comprising: - an input module (110) configured to receive input data (FM, KD1, KD2, KD3), wherein the input data (FM, KD1, KD2, KD3) comprise an error message (FM) relating to a vehicle fault and context data (KD1, KD2, KD3) relating to the vehicle (10); and - an interaction and analysis module (120) that is set up for user interaction (NI) using a Large Language Model (LLM), wherein the Large Language Model (LLM) is set up to perform the user interaction (NI) based on the input data (FM, KD1, KD2, KD3), and wherein the interaction and analysis module (120) is set up to perform error analysis and / or error correction based on the input data (FM, KD1, KD2, KD3) and the user interaction (NI).

The embodiment of the present application discloses a method, device, equipment and medium for determining the volume correction coefficient of a faulted anticline trap. The method comprises the following steps: determining the target parameter information of a to-be-measured faulted anticline trap on a standard cross section; the standard cross section is used to represent the plane where the bottom surface of the to-be-measured faulted anticline trap is located; determining the reference correction coefficient of the to-be-measured faulted anticline trap according to the target parameter information; the reference correction coefficient refers to the amplitude correction coefficient, the fault correction coefficient and the reservoir correction coefficient; and determining the volume correction coefficient of the to-be-measured faulted anticline trap according to the reference correction coefficient. According to the technical scheme, the volume correction coefficient of the faulted anticline trap approximating to the real underground situation can be quickly and accurately obtained based on the standard cross section of the faulted anticline trap, and the prediction speed and the prediction accuracy of the resource quantity of the faulted anticline trap can be improved.

A wireless 5G / 6G message can be demodulated by converting the as-received I-branch and Q-branch signals to the corresponding waveform amplitude and phase, using simple algorithms. Then, fault diagnosis and fault correction can be performed efficiently based on the waveform parameters.

A diagnostic system for a high power laser system, which detects and responds to malfunctions in interlocks of the laser safety system. A fault detected in any interlock circuit mandates a limitation in the operating conditions of the laser, or even a shutdown. In order to distinguish between transient faults, arising typically from ambient conditions, and more permanent faults, arising from faulty components or circuits, and which require external intervention to rectify, the system uses a database of possible fault classifications to determine the likely type of fault. If the fault is likely transient, the laser is maintained in a reduced power state, until one or more temporary interlocks are applied as backup for the failed interlocks, so that the system can be repeatedly tested for fault correction at full power output. Once the fault recovers, the backup interlocks may be disabled and the system returned to full operation.

The invention discloses an approximate fault detection and fault correction method and system, and the method comprises the steps: setting a fault detection and fault positioning threshold value based on the target performance provided by a user, and maintaining a fault deviation value higher than the threshold value after optimization selection in the subsequent fault detection and fault positioning process, therefore, the expensive fault positioning overhead is reduced, and the unnecessary overhead is reduced as much as possible on the premise of ensuring the fault-tolerant capability.

This application relates to a data acquisition method, apparatus, computer equipment, and storage medium. The method includes: acquiring the topology, operating status, and standard fault parameters of a target power grid; determining reference electrical characteristics of the target power grid based on the topology, operating status, and standard fault parameters; acquiring historical fault data and corresponding historical operating status; obtaining historical fault correction data using the historical fault data and reference electrical characteristics; wherein the fault correction data is used to characterize the difference between the fault data and the reference electrical characteristics; training a target model based on the historical fault correction data and historical operating status; wherein the target model is used to determine the fault correction data based on the operating status, and to determine the electrical characteristics of the target power grid based on the fault correction data. This method can improve the efficiency and accuracy of acquiring power grid electrical characteristics.