Automatic control artificial intelligence device and method for updating a control function
AssigneeLG Electronics Inc.
InventorBongsang KIM
Life of this patent
Estimating the term…
Abstract
An artificial intelligence device is disclosed. In an embodiment, the artificial intelligence device includes a sensor configured to acquire an output value according to control of a control system, and an artificial intelligence unit comprising one or more processors configured to obtain one or more updated parameters of a control function of the control system based on the output value using reinforcement learning, and update the control function for providing a control value to the control system with the one or more updated parameters.
Claims18
An artificial intelligence device comprising:
- a sensor configured to acquire an output value according to control of a control system;
- and
- an artificial intelligence unit comprising one or more processors configured to:
- obtain one or more updated parameters of a control function of the control system based on the output value using reinforcement learning;
- and
- update the control function for providing a control value to the control system with the one or more updated parameters.
A method for updating a control function, the method comprising:
- acquiring an output value according to control of a control system;
- obtaining one or more updated parameters of a control function of the control system based on the output value using reinforcement learning;
- and
- updating a control function for providing a control value to the control system with the one or more updated parameters.
An artificial intelligence based control device for use in a heating, ventilation, air-conditioning (HVAC) system, the control device comprising:
- a sensor configured to sense a temperature which is an output value according to control of the HVAC system;
- a valve configured to control a flow rate of gas or liquid for temperature control of the HVAC system;
- and
- an artificial intelligence unit comprising one or more processors configured to:
- update a control function based on the output value using reinforcement learning;
- and
- control the valve to open or close according to a control value output from the updated control function.
Dependencies are inferred from the claim text.