Artificial intelligence washing machine and controlling method therefor

Patent metadata

Field	Value
Publication number	US-11821128-B2
Application number	US-201916557411-A
Country	US
Kind code	B2
Filing date	Aug 30, 2019
Priority date	Aug 30, 2018
Publication date	Nov 21, 2023
Grant date	Nov 21, 2023

Abstract

A control method of washing machine includes: a first detection step of acquiring amount of laundry accommodated in a washing tub; a first washing step of performing washing based on a first laundry amount, when the first laundry amount acquired in the first detection step is equal to or larger than a preset first threshold value; a second detection step of, acquiring the laundry amount accommodated in the washing tub by an output of an output layer of an artificial neural network while using a current value inputted to a motor for rotating and acceleration of the washing tub as an input data of an input layer of the artificial neural network previously learned by machine learning; and a second washing step of performing washing based on a second laundry amount, when the second laundry amount acquired in the second detection step is smaller than the first threshold value.

First claim

What is claimed is:

1. A method of controlling a washing machine, comprising:
acquiring, in a first detection step, a first laundry amount accommodated in a washing tub;
responsive to a determination that the first laundry amount acquired in the first detection step is equal to or greater than a threshold value, performing, in a first washing step, washing based on the first laundry amount;
responsive to a determination that the first laundry amount acquired in the first detection step is less than the threshold value, supplying washing water to the washing tub to wet laundry in the washing tub;
acquiring, in a second detection step, a second laundry amount and a state of the laundry accommodated in the washing tub, the second laundry amount and the state of the laundry being an output of an artificial neural network that uses a current value applied to a motor for rotating and accelerating the washing tub as input data;
responsive to a determination that the second laundry amount acquired in the second detection step is equal to or greater than the threshold value, performing washing based on the second laundry amount; and
responsive to a determination that the second laundry amount acquired in the second detection step is less than the threshold value, performing, in a second washing step, washing based on the second laundry amount and the state of the laundry,
wherein washing water is supplied to the washing tub for the first washing step by:
responsive to a determination that the first laundry amount acquired in the first detection step is equal to or greater than the threshold value, supplying washing water to the washing tub through a dispenser that includes a detergent for pre-washing, or
responsive to a determination that the first laundry amount acquired in the first detection step is less than the threshold value, supplying washing water to the washing tub through a dispenser that includes a detergent for main washing, and

wherein the state of the laundry is classified by a risk of abrasion of the laundry and a washing intensity.

2. The method of claim 1 , wherein the second detection step comprises:
accelerating and rotating the washing tub from a first rotation speed up to a second rotation speed that is higher than the first rotation speed;
acquiring the current value applied to the motor in a section in which the washing tub is accelerated and rotated to the second rotation speed; and
acquiring the second laundry amount based on the current value.

3. The method of claim 2 , wherein the second rotation speed is a rotation speed at which the laundry is rotated integrally with the washing tub.

4. The method of claim 2 , wherein accelerating and rotating the washing tub comprises:
accelerating the washing tub at a constant acceleration from the first rotation speed up to the second rotation speed.

5. The method of claim 2 , wherein acquiring the second laundry amount comprises:
acquiring the second laundry amount based on the current value applied to the motor in a section in which the rotation speed of the washing tub is accelerated from the first rotation speed up to the second rotation speed.

6. The method of claim 2 , wherein the second detection step further comprises detecting a rotation speed of the washing tub.

7. The method of claim 6 , wherein acquiring the second laundry amount comprises:
selecting a current value corresponding to a section in which the washing tub is accelerated from the first rotation speed up to the second rotation speed among current values acquired based on the detected rotation speed of the washing tub; and
acquiring the second laundry amount based on the selected current value.

8. The method of claim 1 , wherein the second washing step comprises:
selecting one of a plurality of washing modes classified by the risk of abrasion of the laundry and the washing intensity based on the second laundry amount and the state of the laundry; and
performing washing according to the selected washing mode.

9. The method of claim 1 , wherein the artificial neural network is trained by machine learning.

10. The method of claim 9 , wherein the second detection step comprises:
accelerating and rotating the washing tub from a first rotation speed to a second rotation speed that is greater than the first rotation speed,
acquiring the current value applied to the motor in a section in which the washing tub is accelerated and rotated to the second rotation speed, and
acquiring the second laundry amount based on the output of the artificial neural network while using the current value as the input data for the artificial neural network.

11. The method of claim 10 ,
wherein acquiring the second laundry amount comprises:
using the current value applied to the motor as the input data in a section in which the rotation speed of the washing tub is accelerated from the first rotation speed to the second rotation speed,

wherein the second detection step further comprises detecting a rotation speed of the washing tub, and
wherein acquiring the second laundry amount comprises:
selecting a current value corresponding to a section in which the washing tub is accelerated from the first rotation speed up to the second rotation speed among current values acquired based on the detected rotation speed of the washing tub, and
using the selected current value as the input data for the artificial neural network.

Assignees

• Lg Electronics Inc

Inventors

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

Classifications

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• D06F34/18 Primary

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

• G06N3/08

  Learning methods · CPC title