Artificial intelligence laundry treatment apparatus and method of controlling the same

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional laundry treatment apparatuses face limitations in accurately sensing laundry weight and quality due to reliance on experimental constants and simple comparison methods, leading to inefficiencies in spin-drying operations and increased energy consumption.

Innovation Solution

A laundry treatment apparatus utilizing a current sensing unit and a controller that processes current values through a parsing rule to generate input data for an artificial neural network, enabling rapid and accurate sensing of laundry weight and quality by leveraging machine learning algorithms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional experimental constants and comparison methods are used to sense laundry weight, then the sensing process is simple, but the measurement precision is insufficient

Engineering Contradiction:
Improvelaundry weight sensing accuracyVSAvoidsensing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces conventional mechanical sensing methods (using experimental constants and simple comparison) with an artificial neural network-based intelligent sensing system. The neural network learns complex relationships between motor current characteristics and laundry weight, achieving high measurement precision without requiring complex mechanical sensing devices.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the sensing approach from using fixed experimental constants to dynamically analyzing multiple motor parameters (current, voltage, frequency) during the acceleration process. The neural network processes these varying parameters to accurately determine laundry weight, transforming the sensing methodology from static to dynamic parameter analysis.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If accurate laundry weight sensing is achieved through conventional methods, then measurement precision improves, but the time required to find setting values increases

Engineering Contradiction:
Improvelaundry weight sensing accuracyVSAvoidtime to find setting values
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The artificial neural network performs self-learning and self-adjustment during the sensing process. It automatically processes motor current data and determines laundry weight without requiring external calibration or manual setting value adjustment, eliminating the time-consuming process of finding optimal setting values while maintaining high measurement precision.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The neural network is pre-trained with learning data before actual sensing operations. This preliminary training enables the system to immediately accurately sense laundry weight during normal operation without requiring time-consuming calibration or setting value adjustment during actual use.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If simple comparison methods are used for laundry weight sensing, then device complexity is low, but measurement precision and adaptability are insufficient

Engineering Contradiction:
Improvelaundry weight sensing adaptabilityVSAvoidsensing system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent replaces simple comparison methods with an artificial neural network that can adaptively learn and recognize patterns in motor current characteristics. This substitution enables the system to handle various laundry types and weights with high adaptability, overcoming the limitations of fixed threshold comparison methods.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

4Productivity

If inaccurate laundry weight measurement occurs, then device complexity remains low, but productivity decreases due to extended washing time

Engineering Contradiction:
Improvewashing cycle efficiencyVSAvoidlaundry weight measurement accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The neural network provides accurate real-time feedback on laundry weight based on motor current analysis during acceleration. This accurate feedback enables the washing machine to optimize washing parameters and cycle time, improving productivity by preventing extended washing cycles that would result from inaccurate measurement.

Inventive Principle:
Principle #23Feedback

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach allows for precise classification of laundry characteristics, reducing the number of input data needed and improving the accuracy of laundry weight and quality sensing, thereby optimizing washing operations and energy usage.

Implementation Method 1

a current sensing unit configured to sense current of the motor

Methodology Applied
Scientific EffectElectrical current measurement: Ohmmeter

Data Source

PatentEP3617363B1Artificial intelligence laundry treatment apparatus and method of controlling the same
Publication Date: 2021.05.26 LG ELECTRONICS INC
  • EP3617363B1 patent drawingFigure 1
  • EP3617363B1 patent drawingFigure 2
  • EP3617363B1 patent drawingFigure 3~4

AI summary

Disclosed is an artificial intelligence laundry treatment apparatus including a washing tub (4) configured to receive laundry, the washing tub being configured to be rotatable, a motor configured to rotate the washing tub, a controller (60) configured to control the motor (9) such that the washing tub is rotated while being accelerated, and a current sensing unit (75) configured to sense current of the motor at predetermined time intervals, wherein the controller is configured to input, to an input layer of an artificial neural network pre-trained based on machine learning, input data generated by processing current values sensed by the current sensing unit while the motor is accelerated within a range within which the laundry moves in the washing tub according to a predetermined parsing rule in order to obtain at least one of laundry weight or laundry quality from output of an output layer of the artificial neural network.