39 results about "Fault mitigation" patented technology

The invention discloses a full-stack NPU system supporting a multistage fault mitigation mechanism, and the system comprises a plurality of NPU functional blocks which are used for executing a neural network calculation task; the plurality of hardware protection modules are used for providing error detection and correction capabilities for at least one NPU functional block in the NPU or a data path in the NPU; and a control mechanism for coordinating operation of the plurality of hardware protection modules. By means of the scheme, NPU functional block calculation errors or data path transmission errors caused by hardware faults and the like can be detected and corrected in time, wrong calculation results are prevented from being continuously used or output, and the accuracy of final results is guaranteed. Meanwhile, even if part of hardware breaks down, an error correction mechanism can also cover errors to a large extent, normal operation of the system is maintained, the overall availability and task success rate of the system are improved, and therefore the reliability and robustness of the NPU are remarkably improved.

A system includes control circuitry configured to manage faults of an electrical system. The system is configured to monitor consumption for a plurality of electrical circuits, such as branch circuits, and generate device information about a device based on an electrical current measurement from at least one electrical circuit of the plurality of electrical circuits to which the device is coupled. The system is also configured to determining that an event has occurred based on the device information and interrupt current of the at least one electrical circuit, generate a notification, communicate a control signal to the device in response to the event occurring to mitigate the event, actuate a second device in response to the event, or a combination thereof.

A computer system for use with a data center includes a monitoring system configured to receive telemetry data from the data center and to generate alert data in response to a data center fault indicated by the telemetry data; a data center orchestrator coupled to the monitoring system that is configured to manage operation of the data center; and a self-healing engine that operates via an application programming interface (API) configured to receive the alert data, topology data corresponding to a topology of the data center, and user intent data and to select and execute one or more skills in conjunction with the data center orchestrator to correct the data center fault.

An active fault tolerance and fault mitigation system based on steer-by-wire dual motors and a mode switching control method thereof are provided. The system includes an acquisition unit, a steering wheel assembly, an ECU control module, a front wheel steering assembly, and a fault tolerance controller (18) which are sequentially connected. The acquisition unit transmits an acquired vehicle signal to the ECU control module, and then a corresponding compensation strategy is selected by means of a fault tolerance control strategy unit, a yaw rate calculation unit, a stability control unit, and a dual-motor compensation unit to act on a rack and pinion mechanism (15). The system and method can perform switching in an active fault tolerance and fault mitigation mode to achieve optimal control of the real-time performance of a vehicle, thereby ensuring the driving performance and higher performance of the vehicle in a field fault condition.

Systems, methods, and instruments for detecting failure mitigation associated with a surgical task are described herein. The device may perform a first autonomous function associated with a surgical task. Performing the first autonomous function may be associated with control feedback. The first autonomous function may be monitored by tracking one or more outputs associated with the control feedback. If the one or more outputs exceed a fault threshold, the device may switch from performing the first autonomous function to performing a second autonomous function associated with the surgical task. The second autonomous function may be associated with fault mitigation feedback.

Embodiments include methods, electronic device, storage medium, and computer program to mitigate faults in a cloud system. In one embodiment, a method comprises moving a first work unit from a running state to a first state upon determining that the first work unit is faulty; responsively causing a set of work units to be started to provide the service based on a probability of a work unit in the first state being moved to a second state, where in the second state the work unit is standby for task execution; moving a second work unit from the first to second state upon determining within a time period that the second work unit is ready for the service; and causing a third work unit to perform task execution by moving it from the second state to the running state upon determining that one or more additional work units are needed.

A low voltage system of a vehicle having a battery, one of a generator and an accessory power module (APM), one or more low voltage load, and a smart energy center. The smart energy center having a first electronic fuse configured to selectively connect the smart energy center to the battery, a second electronic fuse configured to selectively connect the smart energy center to the one of the generator and the APM, and a third electronic fuse configured to selectively connect the smart energy center to the one or more low voltage load. The smart energy center further comprising a plurality of sensors and a controller configured to selectively activate and deactivate the first electronic fuse, the second electronic fuse, and the third electronic fuse based at least in part on data received from the plurality of sensors.

The application discloses a kind of nuclear power plant concurrent fault diagnosis method and system based on transfer learning, constructs nuclear power plant concurrent fault diagnosis model based on multilayer bidirectional long short-term memory network;Using single failure training set, the concurrent fault diagnosis model is pre-trained, and then the single failure test set is input into the trained concurrent fault diagnosis model to test the accuracy of the pre-training model;The full connection layer and classification output layer in the concurrent fault diagnosis model are reset to blank layer, and the adjusted network model is retrained using the concurrent fault training set;The concurrent fault test set is input into the trained concurrent fault diagnosis model, to realize the diagnosis of nuclear power plant sensor and actuator concurrent fault.The present application can realize the accurate online diagnosis of different types and different degrees of sensor and actuator concurrent fault during the steady-state and transient operation of nuclear power plant, and provide a reference for fault mitigation and fault-tolerant control.

An art fault mitigator includes a sensor structured to detect at least one of a user within vicinity of the power system protection device, a light within the power system protection device and an overcurrent within the power system protection device; a mechanical switching device including a fast mechanical circuit interrupter and an actuator; a power electronics circuit coupled to the mechanical switching device in parallel and including a current commutator structured to commutate current from the fast mechanical circuit interrupter to the power electronics circuit upon turning OFF of the fast mechanical circuit interrupter, a power electronic circuit interrupter structured to allow the current to ride there-through up to a threshold current, and a current limiter structured to limit the current flowing through the power electronics circuit interrupter; and a controller including a trip control structured to control operations of the mechanical switching device and the power electronics circuit.

A computer-implemented method, when executed by data processing hardware, causes the data processing hardware to perform operations. Operations include: receiving battery data of a vehicle battery at a monitoring application; detecting, via the monitoring application, a battery event based on the received battery data; and estimating a severity level of the battery event via a fault mitigation algorithm, the severity level being one of the first level and the second level. Operations also include; performing, via a fault mitigation algorithm, a mitigation action based on the estimated severity level; and communicating, via the communication system, the fault state and the mitigation plan based on the performed mitigation action.

An art fault mitigator includes a sensor structured to detect at least one of a user within vicinity of the power system protection device, a light within the power system protection device and an overcurrent within the power system protection device; a mechanical switching device including a fast mechanical circuit interrupter and an actuator; a power electronics circuit coupled to the mechanical switching device in parallel and including a current commutator structured to commutate current from the fast mechanical circuit interrupter to the power electronics circuit upon turning OFF of the fast mechanical circuit interrupter, a power electronic circuit interrupter structured to allow the current to ride there-through up to a threshold current, and a current limiter structured to limit the current flowing through the power electronics circuit interrupter; and a controller including a trip control structured to control operations of the mechanical switching device and the power electronics circuit.

An art fault mitigator includes a sensor structured to detect at least one of a user within vicinity of the power system protection device, a light within the power system protection device and an overcurrent within the power system protection device; a mechanical switching device including a fast mechanical circuit interrupter and an actuator; a power electronics circuit coupled to the mechanical switching device in parallel and including a current commutator structured to commutate current from the fast mechanical circuit interrupter to the power electronics circuit upon turning OFF of the fast mechanical circuit interrupter, a power electronic circuit interrupter structured to allow the current to ride there-through up to a threshold current, and a current limiter structured to limit the current flowing through the power electronics circuit interrupter; and a controller including a trip control structured to control operations of the mechanical switching device and the power electronics circuit.

The application discloses a kind of automatic generation control method and system for wind-light-storage combined system, it is related to electric power control technical field, the method includes: real-time acquisition wind-light-storage combined system instruction and active power measured value;Residual value is determined based on wind-light-storage combined system instruction and active power measured value;Residual statistics is determined based on residual value;Residual fault detection result is obtained based on residual statistics and threshold rule;Using fault mitigation strategy, correction instruction is obtained based on residual fault detection result;Determine allocation strategy based on input instruction;Determine wind farm AGC instruction, photovoltaic power station AGC instruction and energy storage power station AGC instruction based on allocation strategy and correction instruction.The application can improve the control accuracy of AGC and the overall stability of wind-light-storage combined system.

A respiratory apparatus (4000) includes components to protect operations of the apparatus. In some examples, the apparatus may include a fault mitigation integrated circuit (IC). The IC circuit may be included in the respiratory apparatus to detect one or more faults based on physical and system parameters of the apparatus. The fault mitigation integrated circuit may generate a signal to stop the motor based on the detected fault, and may digitally communicate with a processor information about the detected fault. The system may be configured to provide multiple sensor or detector signals to a common port or pin of the fault mitigation integrated circuit to share fault detection resources of the fault mitigation integrated circuit for different fault detections.

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.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a network node can receive, from a network entity, a configuration of a codebook associated with a reconfigurable intelligent surface (RIS) pattern. The network node can receive, from the network entity, an indication of a codeword in the codebook that is potentially associated with a RIS element failure based at least in part on one or more RIS attributes. The network node can perform RIS failure mitigation based at least in part on the indication. Numerous other aspects are described.

A method for circuit modification for fault mitigation including: obtaining a netlist defining a circuit; inserting at least one saboteur circuit into a first net of the netlist; configuring an FPGA to implement the first net and the at least one saboteur circuit; activating a first of the at least one saboteur circuits; determining whether the first net experiences a fault; and upon determining that the first net experiences a fault, modifying the first net by inserting at least one redundant circuit into the first net.

Provided are systems, methods, and computer-readable storage media that leverage artificial intelligence and machine learning to identify, diagnose, and mitigate occurrences of network faults or incidents within a network. Historical network incidents may be used to generate a model that may be used to evaluate real-time occurring network incidents, such as to identify a cause of the network incident. Clustering algorithms may be used to identify portions of the model that share similarities with a network incident and then actions taken to resolve similar network incidents in the past may be identified and proposed as candidate actions that may be executed to resolve the cause of the network incident. Execution of the candidate actions may be performed under control of a user or automatically based on execution criteria and the configuration of the fault mitigation system.

The embodiment of the invention relates to resource fault mitigation. Resource failures in a distributed control system (DCS) may compromise the stability and availability of the system. Therefore, a resource failure mitigation method for a distributed control system is provided. The method includes: predicting a failure of a first resource executing a service; maintaining the state of the service; and resuming the service at the second resource using the maintained state. A corresponding system is also provided. Thus, the risk of data loss can be reduced while improving flexibility, resulting in an improved user experience for non-critical services.

The invention discloses a method and a system for relieving cascade faults of a power system based on an accident disaster background, which aim at actual engineering requirements and aiming at cascade faults of the power system, firstly, equipment risk indexes are established according to risk levels of disaster accidents, and the development mode of the cascade faults of the system under the disaster scene is refined by utilizing the indexes. From the perspective of operation control, a cooperative mitigation strategy of a system cascade fault under a disaster condition is formulated in combination with an optimal generator scheduling and load / generator shedding method; the strategy is combined with an active prevention measure, and aims to quickly cut off a potential cascade fault path at the first time after a disaster occurs, so that an affected interruption area is reduced to the greatest extent; the method can effectively reduce the influence of disasters and accidents on the operation of the power system.

A computer-implemented procedure that, when executed by data processing hardware, causes the data processing hardware to perform operations. These operations include receiving battery data from a vehicle battery by a monitoring application, detecting a battery event via the monitoring application based on the received battery data, and estimating the severity of the battery event using a fault mitigation algorithm, where the severity is either first- or second-level. The operations also include: performing mitigation actions based on the estimated severity by the fault mitigation algorithm, and transmitting a fault status and a mitigation plan based on the executed mitigation actions via a communication system.

Embodiments of the present disclosure provide techniques for fault detection and mitigation. Plant data associated with one or more process assets of a process plant may be received. Fault data comprising at least one fault with at least one process asset may be generated based on the plant data and a set of conditions by applying the plant data to a fault monitoring machine learning model. Fault mitigating data for the at least one fault may be generated. The fault mitigating data may comprise one or more recommendations for minimizing potential impact of the at least one fault. Performance of one or more fault mitigation actions may be generated.

Message faults are a major contributor to latency in 5G and expected to be even more so in 6G due to pathloss, crowding, and the rapid cadence of high-volume traffic. Efficient means for correcting message faults are needed. Therefore, disclosed herein are methods for a receiver to compare two versions of a message, both faulted according to their embedded error-detection codes, and reconstruct the correct message-without a time-consuming grid search of possible modulation substitutions. In addition, the receiver can pass the message data, including modulation quality and signal quality, directly to an artificial intelligence model, which can (a) indicate which resource elements of the message (and / or the error-detection code) are faulted, and (b) reconstruct the most likely corrected version of the message, all in a small fraction of a retransmission time.

A configurable, data-driven computer software program that predicts system behavior and detects anomalies within these behavior predictions. The software program is configured by a data set specified by the user or another computer program and utilizes system data provided by the user or the target system itself. The program predicts system behavior, estimates outlying predictions and then automatically labels the predictions and outliers. Once system predictions are labeled, the program uses outlier recognition to classify predictions as expected (nominal) or unexpected (anomalous) behavior. Users can configure the program to perform various tasks, such as testing other software programs for defects, as well as detecting and mitigating system errors / faults in real-time on target systems.

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.

Embodiments include methods, electronic device, storage medium, and computer program for fault mitigation in a distributed system. In one embodiment, a method comprises obtaining measurements related to one or more one-way data flows that are from one or more source service instances and that are to be distributed to one of at least two destination service instances in the distributed system; determining the obtained measurements indicating that distribution of a one-way data flow within the one or more one-way data flows to a destination service instance of the at least two destination service instances fails to comply with a quality-of-service requirement; and causing reroute of the one-way data flow to be distributed to another destination service instance instead of the destination service instance.

The invention provides a fault mitigation design method, system and device for an instrument control card, and a storage medium, and the method comprises the steps: obtaining an initial model of the instrument control card; performing failure mode and influence analysis on the initial model to determine a target element in the initial model; and fault mitigation design is carried out on the target element, and the initial model after the fault mitigation design is used as a target model. According to the invention, the reliability and availability of the card are improved, and the probability of card fault occurrence and the degree of influence on functions are reduced.

The present application discloses a full-stack NPU system that supports a multi-level fault mitigation mechanism, including: multiple NPU functional blocks for performing neural network computing tasks; multiple hardware protection modules for providing error detection and correction capabilities for at least one NPU functional block within the NPU or the data path within the NPU; and a control mechanism for coordinating the operations of multiple hardware protection modules. Utilizing the solution of the present application, NPU functional block computing errors or data path transmission errors caused by hardware failures, etc. can be detected and corrected in a timely manner, preventing erroneous calculation results from being continued to be used or output, and ensuring the accuracy of the final results. At the same time, even if some hardware fails, the error correction mechanism can cover up the error to a large extent, maintain the normal operation of the system, improve the overall availability of the system and the task success rate, thereby significantly improving the reliability and robustness of the NPU.

An arc fault mitigator includes a sensor configured to detect at least one of users in proximity to a power system protection device, light within the power system protection device, and an overcurrent within the power system protection device; a mechanical switching device comprising a fast mechanical circuit interrupter and an actuator; a power electronic circuit coupled in parallel to the mechanical switching device and including a current commutator configured to commutate current from the fast mechanical circuit interrupter to the power electronic circuit when the fast mechanical circuit interrupter is open, a power electronic circuit interrupter configured to interrupt the current from the fast mechanical circuit interrupter to the power electronic circuit when the fast mechanical circuit interrupter is open, and a current limiter configured to limit the current from the fast mechanical circuit interrupter to the power electronic circuit. The power electronic circuit interrupter is configured to allow current to pass through within a range of threshold current, and the current limiter is configured to limit the current flowing through the power electronic circuit interrupter; and a controller including a trip control mechanism configured to control operation of the mechanical switching device and the power electronic circuit.

This application relates to a fault diagnosis and safety guidance control method for a locomotive brake command controller, comprising: a signal acquisition step, wherein when the switch signal DI2 of the brake command controller in the full braking position is valid, the equalization pressure reduction amount AI corresponding to the analog quantity of the current braking zone is acquired; a guidance judgment step, wherein a preset value for the equalization pressure reduction amount is set, and if the equalization pressure reduction amount AI is less than the preset value, the brake automatically guides to the full braking pressure reduction amount, and the full braking pressure reduction amount X1 and fault code are recorded; if the equalization pressure reduction amount AI is greater than or equal to the preset value, no guidance is performed, the equalization pressure reduction amount X2 is recorded, and the fault code is set to 0; and a mitigation step, wherein the fault state of the braking zone is judged under different mitigation states, and the pressure reduction amount is set according to the judgment result. This application solves the technical problems of fault diagnosis, fault guidance control, and post-fault mitigation control of the brake command controller when there is an analog quantity fault in the braking zone, thereby improving the reliability and safety of the braking system.