Artificial intelligence laundry treatment apparatus and method of controlling the same

Patent metadata

Field	Value
Publication number	US-2020109507-A1
Application number	US-201916557995-A
Country	US
Kind code	A1
Filing date	Aug 30, 2019
Priority date	Aug 30, 2018
Publication date	Apr 9, 2020
Grant date	—

Abstract

Disclosed is an artificial intelligence laundry treatment apparatus including a washing tub configured to receive laundry, the washing tub being configured to be rotatable, a motor configured to rotate the washing tub, a controller configured to control the motor such that the washing tub is accelerated to a predetermined target speed at an acceleration gradient of 1.5 to 2.5 rpm/s within a range within which the laundry moves in the washing tub, and a current sensing unit configured to sense current of the motor, wherein the controller is configured to obtain at least one of laundry weight or laundry quality from output of an output layer of an artificial neural network pre-trained based on machine learning using a current value sensed by the current sensing unit during accelerated rotation of the washing tub as input of an input layer of the artificial neural network.

First claim

What is claimed is:

1 . A laundry treatment apparatus comprising:
a washing tub configured to receive laundry, the washing tub being configured to be rotatable; a motor configured to rotate the washing tub; a controller configured to control the motor such that the washing tub is accelerated to a target speed at an acceleration gradient of 1.5 to 2.5 rotations per minute per second (rpm/s)within a range of rotation of the washing tub in which the laundry is separated from an inner surface of the washing tub; and a current sensing unit configured to sense an electrical current value of the motor, wherein the controller is configured to obtain at least one of a laundry weight or a laundry quality by an output of an output layer of a pre-trained machine-learning network based on an input to an input layer of the machine-learning network that comprises the electrical current value sensed by the current sensing unit during an accelerated rotation of the washing tub.

2 . The laundry treatment apparatus according to claim 1 , wherein the acceleration gradient is 2.0 rpm/s.

3 . The laundry treatment apparatus according to claim 1 , wherein the acceleration gradient is a minimum value for accelerating the washing tub that is controllable by the controller.

4 . The laundry treatment apparatus according to claim 1 , wherein the acceleration gradient is maintained at a uniform value until the motor is accelerated to the target speed.

5 . The laundry treatment apparatus according to claim 1 , wherein the controller is further configured to determine a laundry constraint based on the output of the output layer of the machine-learning network.

6 . The laundry treatment apparatus according to claim 1 , wherein, based on the washing tub being rotated by one or more revolutions in a first direction within a range of rotation of the washing tub in which the electrical current value that is input to the machine-learning network is sensed by the current sensing unit:
the laundry that is located at a lowermost position in the washing tub is raised to a first height by the rotation of the washing tub and is then dropped while being separated from the inner surface of the washing tub.

7 . The laundry treatment apparatus according to claim 1 , further comprising:
a speed sensing unit configured to sense a rotational speed of the motor, wherein the controller is further configured to:
select, from among a plurality of electrical current values obtained by electrical current sensing unit and based on the rotational speed of the motor sensed by the speed sensing unit, the electrical current value corresponding to a period in which the rotational speed of the motor is accelerated from a first rotational speed to the target speed; and
use the selected electrical current value as the input to the machine-learning network.

8 . The laundry treatment apparatus according to claim 7 , wherein the target speed is 60 rotations per minute (rpm) to 80 rpm.

9 . The laundry treatment apparatus according to claim 7 , wherein the first rotational speed is 10 rpm to 20 rpm.

10 . A method of controlling a laundry treatment apparatus, the method comprising:
accelerating a washing tub having laundry introduced thereinto to a target speed at an acceleration gradient of 1.5 to 2.5 rotations per minute per second (rpm/s) within a range of rotation of the washing tub within which the laundry is separated from an inner surface of the washing tub; obtaining an electrical current value of a motor that is configured to rotate the washing tub, wherein the electrical current value is obtained during an accelerated rotation of the washing tub; and obtaining at least one of a laundry weight or a laundry quality by an output of an output layer of a pre-trained machine-learning network based on an input to an input layer of the machine-learning network that comprises the electrical current value.

11 . The method according to claim 10 , wherein the acceleration gradient is 2.0 rpm/s.

12 . The method according to claim 10 , wherein the acceleration gradient is a minimum value for accelerating the washing tub that is controllable.

13 . The method according to claim 10 , wherein the acceleration gradient is maintained at a uniform value until the motor is accelerated to the target speed.

14 . The method according to claim 10 , further comprising:
determining a laundry constraint based on the output of the output layer of the machine-learning network.

Assignees

• Lg Electronics Inc

Inventors

• Im Myunghun
• Jung Hwanjin
• Yu Seonhwa
• Kim Sunggyun
• Woo Kyungchul
• Kim Jaehyun

Classifications

• D06F34/18

  Condition of the laundry, e.g. nature or weight · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06N3/08

  Learning methods · CPC title

• D06F37/304

  Arrangements or adaptations of electric motors · CPC title

• D06F2202/065

  Textiles & Paper · mapped topic