Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

5results about How to "Self-learning" patented technology

Intelligent operation device of underground carry-scraper

ActiveCN222183476UAutomatic loadingself-learningMechanical machines/dredgersControl engineeringMachine
The utility model provides an underground carry-scraper intelligent operation device which comprises a machine frame and a driving assembly, and the driving assembly comprises a lifting mechanism assembly, a bucket adjusting mechanism assembly and a control assembly. The lifting mechanism assembly comprises a lifting driving mechanism, an upper lifting arm, a lower lifting arm and a lifting arm connecting frame; the bucket adjusting mechanism assembly comprises a branch chain, a branch chain fixing plate and a bucket; one ends of the upper lifting arm and the lower lifting arm are connected with the rack, the other ends of the upper lifting arm and the lower lifting arm are fixed in the middle of the lifting arm connecting frame, one end of the lifting arm connecting frame is connected with the bucket, the other end of the lifting arm connecting frame is connected with the rack, the lifting driving mechanism is simultaneously connected with the upper lifting arm and the lower lifting arm, and the branch chain fixing plate is simultaneously connected with the rack and the lifting arm connecting frame. One end of the branch chain is connected with the branch chain fixing plate, the other end of the branch chain is connected with the bucket, and the bucket adjusting mechanism assembly and the lifting driving mechanism are both connected with the control assembly. According to the utility model, the functions of energy consumption saving, accurate dynamic weighing and the like are realized.
Owner:UNIV OF SCI & TECH BEIJING

Information grading identification method based on rule engine and LLM cooperation and related device

PendingCN122594873AReduce call costsImprove processing efficiency
The embodiment of the present application relates to the technical field of computer information security and artificial intelligence, and discloses a sensitive information automatic identification method combining a rule engine and a natural language processing technology and related devices, which comprises the following steps: receiving original data to be identified; performing rule matching on the original data to be identified to obtain a matching result; calculating a confidence score corresponding to the matching result; when the confidence score is lower than a first confidence threshold and higher than or equal to a second confidence threshold, inputting the matching result into a lightweight model for verification to obtain a first verification result; when the first verification result is consistent with the matching result, taking the matching result as a text information identification result; when the confidence score is lower than the second confidence threshold or the verification result of the lightweight model on the matching result is inconsistent, inputting the matching result into a large model for analysis and identification to obtain a large model identification result, and taking the large model identification result as the text information identification result. The embodiment of the present application realizes the balance between the text information identification efficiency and accuracy.
Owner:GUOSEN SECURITIES

A hybrid electric vehicle mode switching control method based on reinforcement learning

ActiveCN115257691BSolve the defect of poor adaptabilitySelf-learning abilityHybrid vehiclesDesign optimisation/simulationElectrical batteryReinforcement learning algorithm
The present invention relates to a hybrid vehicle mode switching control method based on reinforcement learning, the method comprising: using a reinforcement learning algorithm of a deep Q network to control the mode switching of a hybrid vehicle, using the vehicle speed, required power, battery SOC, etc. as the state of reinforcement learning, using the mode switching of the vehicle as the action variable, and using the collected historical driving data to train the deep Q network; extracting the control rules of the mode switching from the trained network to apply to the vehicle controller of the actual vehicle. Compared with the prior art, the present invention uses a deep Q learning algorithm to control the mode switching of the vehicle, which can improve the adaptability of the energy management strategy and ensure the reliability and real-time performance of the mode switching control.
Owner:TONGJI UNIV

Environment-adaptive intelligent early warning and operation and maintenance decision system and method for wind farm

The application provides an environment-adaptive wind farm intelligent early warning and operation and maintenance decision system and method, the system of the application comprises: a first data acquisition module for acquiring multi-source environment data in a wind farm area; a second data acquisition module for collecting operation state data of each device in the wind farm; a data processing module for spatiotemporal alignment and feature fusion of the multi-source environment data and the operation state data to generate multi-modal fusion features; an environment-device coupling early warning module for risk prediction of wind farm devices based on the multi-modal fusion features through multiple environment-device coupling early warning models to obtain risk early warning information; a device health assessment module for assessing the health status of each device in the wind farm according to the operation state data to generate a device health score; and an operation and maintenance decision support module for generating corresponding operation and maintenance decision suggestions according to the risk early warning information and the device health score in combination with an operation and maintenance strategy knowledge base.
Owner:HUANENG DAQING RANGHU ROAD CLEAN ENERGY CO LTD

A bionic adaptive vibration reduction system and adjustment method for a high mobility carrier platform

ActiveCN115583130Bgood vibration dampinggood exercise formResilient suspensions
The invention discloses a bionic adaptive vibration reduction system and control method for a high-mobility transport platform, comprising a frame (1), an upper end of a simulated femoral adductor oil cylinder (4), a lower end of a simulated tibial connecting rod (5) and an upper end of a simulated metatarsal connecting rod (14) hinged on the frame (1), the lower end of the simulated femoral adductor oil cylinder (4), the upper end of the simulated tibial connecting rod (5) and the upper end of the simulated Achilles tendon oil cylinder (8) are hinged at a first movable hinge point (6), the lower end of the simulated Achilles tendon oil cylinder (8) is hinged at a second movable hinge point (13) on the simulated tibial connecting rod (5), and a control unit obtains the vibration amplitude of the frame through a sensor, and adjusts the stiffness and damping of the oil cylinder according to the vibration amplitude. The system beneficially combines bionics with practical engineering applications, accurately establishes a bionic efficient adaptive coordinated vibration reduction system, improves the off-road performance and comfort of the high-mobility transport platform under high speed, heavy load and strong impact conditions, and extends its service life.
Owner:GUIZHOU JONYANG KINETICS