METHOD AND SYSTEM FOR CONTROLLING ENGINE COOLING IN A VEHICLE USING REINFORCEMENT LEARNING

A reinforcement learning system with probabilistic and deterministic networks optimizes engine cooling by continuously adapting to real-time conditions, improving efficiency and reducing wear by maintaining optimal engine temperature.

DE102024138402A1Pending Publication Date: 2026-06-18MERCEDES BENZ GROUP AG
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
DE102024138402
Authority / Receiving Office
DE · DE
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-12-13
Filing Date
2024-12-17
Publication Date
2026-06-18

AI Technical Summary

Technical Problem

Current radiator temperature control systems in vehicles rely on reactive measures, failing to account for real-time conditions and fluctuations in engine load, leading to inefficient engine operation and potential damage due to overheating or overcooling.

Method used

A reinforcement learning-based system using a probabilistic and deterministic neural network to process temperature and environmental data, determining optimal cooling actions and continuously updating strategies to maintain engine temperature within a target range, incorporating environmental sensor data and risk-aware strategies.

Benefits of technology

Enhances engine efficiency, longevity, and fuel efficiency by adaptively controlling cooling mechanisms, reducing wear and preventing damage through precise temperature management across varying conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

A method and system for controlling engine cooling in a vehicle includes receiving temperature data from a temperature sensor (104) that monitors the engine temperature. A control unit (106) processes the data using a reinforcement learning model (108) comprising a probabilistic network (110) and a deterministic network (112). The probabilistic network (110) determines a probability distribution of cooling actions based on the temperature data. Specific cooling actions are selected to control a cooling actuator (114). The deterministic network (112) evaluates the effectiveness of the actions and updates the probability distribution. Continuous control signals are generated to operate the cooling actuator (114) and maintain the engine temperature within a target range.The system enables efficient, adaptable control of engine cooling using reinforcement learning techniques.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Machine learning apparatus for learning operation conditions of cooling device, motor control apparatus and motor control system having the machine learning apparatus, and machine learning method

    US9819300B2