Abstract: The disclosed computer-implemented method optimizes thermal control of a vehicle motor, the vehicle including a cooling device including an actuator varying cooling capacity, the method including training a reinforcement learning algorithm including the iterative steps: 1) determining an action to control an actuator by applying a control function to a current state of the thermal system, and implementing the action; 2) determining a modified state of the thermal system after implementing the action; 3) calculating, by implementing a thermodynamic reward function of the motor, a reward value based on the modified state of the thermal system, and the action; 4) updating a function for estimating thermal performance based on the current state of the thermal system, the modified state of the thermal system, the action and the reward; and 5) modifying the control function based on the update of the function for estimating thermal performance.

Abstract: The system comprises a centralization and interface module, capable of interconnecting module for dynamically simulating the process and an immersive simulation module for enabling an operator and/or a robot to perform, in real time in an immersive three-dimensional representation, a virtualized implementation of an industrial process comprising actions performed in the immersive three-dimensional representation. It comprises a module for monitoring the implementation of the process, the module being capable of recording monitoring data including operating parameters of the process and/or real-time actions of the operator and/or the robot, and a rendering module capable of processing the obtained monitoring data and providing a rendering of a virtual implementation of the process, the rendering being designed to control or optimize the industrial process.

Abstract: The disclosed computer-implemented method optimizes thermal control of a vehicle motor, the vehicle including a cooling device including an actuator varying cooling capacity, the method including training a reinforcement learning algorithm including the iterative steps: 1) determining an action to control an actuator by applying a control function to a current state of the thermal system, and implementing the action; 2) determining a modified state of the thermal system after implementing the action; 3) calculating, by implementing a thermodynamic reward function of the motor, a reward value based on the modified state of the thermal system, and the action; 4) updating a function for estimating thermal performance based on the current state of the thermal system, the modified state of the thermal system, the action and the reward; and 5) modifying the control function based on the update of the function for estimating thermal performance.

Abstract: In a motor vehicle having exhaust-gas recirculation, fluid of an air-conditioning circuit is used to cool coolant of a dedicated hydraulic circuit, which in turn cools recirculated exhaust gases in a two-stage heat exchanger, thus increasing engine gain by replenishing to reduce NOx emissions. A method differentiates control strategies for the circuits, as a function of vehicle driving conditions, continuous modes and transient braking and acceleration modes, to compensate for consumption of the compressor of the air-conditioning circuit. The circuits include a heat exchanger for heat exchange between the air-conditioning fluid and coolant, a bypass, capable of accumulating and releasing cold energy, and, optionally, a line condensing water vapour of the exhaust gases and reinjecting the condensed water to the intake.