6 results about "Failure management" patented technology

This invention discloses a temporally enhanced knowledge graph-driven dialogue agent and its implementation method, belonging to the fields of artificial intelligence and natural language processing technology. The dialogue agent includes a dialogue interface, natural language understanding, a temporal knowledge graph, a temporal reasoning engine, dynamic update and failure management, and a natural language generation module. It includes designing the basic representation unit of the knowledge graph as a temporal quintuple; designing a temporal reasoning engine and a dynamic update and failure management method; designing a method for matching, verifying, and performing multi-hop reasoning of temporal information in natural language problems with temporal facts in the knowledge graph; achieving accurate parsing of temporal constraints in dialogue, real-time adaptation of dynamic knowledge, rigorous temporal logic reasoning, and continuous maintenance of contextual temporal consistency; and outputting a temporally accurate, knowledge-reliable, and logically coherent intelligent response, capable of meeting the needs of complex scenarios such as vertical industry decision support and high-reliability intelligent interaction.

The utility model belongs to the technical field of soft starter, specifically relates to a simulation closed loop enhanced type soft starter, and the thyristor in power main bridge realizes the smooth rise of motor voltage and current limit under the control of simulation slope and current closed loop control unit, after the completion of soft start, the solid state bypass unit that is composed of low conducting resistance SiC MOSFET is driven to conduct, and bypass power main bridge is used to reduce operating loss, the hardware protection logic unit can carry out microsecond level fast detection to overcurrent and other faults and immediately seals the power output, realizes fast protection, and the microcontroller unit is responsible for parameter setting, starting control, bypass switching and fault management. The utility model realizes the motor soft start of starting stable, current-limiting accurate, running efficient and protection quick and reliable through the combination of simulation control and fast hardware protection.

This document discloses a method and a system for managing sensor failures in a vehicle. The method comprises detecting the failure of a sensor in the vehicle. The method then comprises receiving an aggregated model weight from a server based on the sensor failure detection. Finally, the method comprises updating at least one model weight of a training model of the vehicle using the received aggregated model weight for managing the sensor failure in the vehicle.

The application discloses an IGBT thermal failure management method, a voltage regulating circuit and a power utilization device. The IGBT thermal failure management method comprises the following steps: collecting real-time operation parameters of an IGBT, and calculating total transient loss of the IGBT according to the real-time operation parameters; acquiring a reference thermal resistance of the IGBT, and calculating a real-time thermal resistance of the IGBT according to historical operation parameters of the IGBT; collecting a real-time shell temperature of the IGBT, and calculating a real-time junction temperature of the IGBT according to the real-time shell temperature, the total transient loss and the real-time thermal resistance; and triggering an IGBT protection strategy when the real-time junction temperature of the IGBT reaches a threshold temperature. Compared with the prior art, the application can reduce the junction temperature estimation error of the IGBT and ensure the system operation reliability through the double-source coupling of the instantaneous characteristics and the real-time shell temperature and the dynamic thermal resistance compensation algorithm.

A failure management device includes: an information collection unit configured to collect failure information which is information about a failure of devices or instruments loaded in a vehicle; a notification unit configured to output a failure notice notifying occurrence of the failure inside the vehicle; and an instruction unit configured to instruct the notification unit whether or not to output the failure notice when the failure of one of the devices or the instruments is found based on the failure information, and the instruction unit prohibits the notification unit from outputting the failure notice when the device or the instrument in which the failure is found is not involved in execution of an option function for which the execution is permitted, based on management information indicating whether or not the execution of the option function is permitted for each of the option functions in the vehicle.

This invention discloses a cloud-edge integrated power outage management method and system. An edge controller is installed at the power plant site to collect operating status parameters of on-site equipment and auxiliary start-up system equipment, enabling rapid anomaly detection and failure rate calculation. A digital twin module is deployed on the cloud server in the control center. Based on the operating equipment and steps included in the power outage operation in the plant scheduling plan, combined with the real-time operating status parameters of on-site equipment and on-duty personnel information during the simulated power outage operation, the power outage operation is simulated and rehearsed. The probability of a plant-wide power outage risk is determined based on the simulation results, thereby managing and controlling the power outage operation. By integrating multi-dimensional risk factors such as equipment failure rate, failure rate of operation-related equipment, personnel error rate, and the health status of auxiliary start-up system equipment, dynamic judgment is achieved, enabling more accurate and realistic prediction of power plant outage risks and reducing the number of plant-wide power outages.