| CPC F24F 8/10 (2021.01) [A61L 9/22 (2013.01); B01D 53/1487 (2013.01); B03C 3/38 (2013.01); G06N 20/00 (2019.01); B01D 2257/708 (2013.01); B01D 2258/06 (2013.01)] | 12 Claims |
|
1. A method of controlling a machine learning-based air handler, the method comprising:
collecting first data on an air quality of air flowing into the air handler;
controlling a purification part comprising at least one charging part having at least one tube comprising an anode and a cathode and a dust collecting part that collects ionized substances with a positive charge and a negative charge based on the first data;
collecting second data on an air quality of air passing through the purification part; and
controlling the purification part according to a machine-learning model generated based on a setting value related to a control of the purification part, the first data, the second data, and an input value including a number of at least one tube, a location of the at least one tube, and a size of the dust collecting part,
wherein the setting value related to the control of the purification part comprises at least one of a voltage value applied to the anode and a voltage value applied to the cathode, and
wherein the at least one charging part ionizes substance by emitting electromagnetic wave having a wavelength in a range between 0.1 nanometers and 100 nanometers using the cathode composed of carbon nanotube.
|