AI Laundry Load Sensing From Motor Current During Drum Acceleration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional laundry treatment apparatuses face limitations in accurately sensing laundry weight and quality, requiring extensive expert settings and time, leading to increased energy consumption and prolonged washing times due to inaccurate measurements.
Innovation Solution
A laundry treatment apparatus utilizing machine learning and an artificial neural network to rapidly and accurately sense laundry weight and quality by analyzing current values from a motor current sensing unit, allowing for classification based on various criteria such as softness, water content, and volumetric differences between dry and wet laundry.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional algorithms with multiple experimental constants are used to sense laundry weight, then measurement coverage is improved, but measurement precision deteriorates due to inaccurate experimental values
Solution Approach 1:
The system performs self-learning by automatically collecting motor current data during washing operations and using machine learning algorithms to determine optimal setting values for different laundry types, eliminating the need for manual expert configuration and enabling continuous improvement of measurement accuracy
Solution Approach 2:
The system pre-processes motor current data during the acceleration phase before main washing begins, collecting and analyzing data to determine laundry weight and type in advance, so that optimal settings are ready before the actual washing process starts
2Measurement precision
If simple comparison methods are used to sense laundry weight, then device complexity is reduced, but measurement precision deteriorates to only large/small distinction
Solution Approach 1:
The system replaces complex mechanical sensing devices with electronic motor current sensing and software-based machine learning analysis, achieving high-precision laundry weight and type classification through data processing rather than physical measurement devices
Solution Approach 2:
The system analyzes changes in motor current parameters during the acceleration phase to infer laundry weight and type, transforming the problem from direct weight measurement to indirect parameter analysis that achieves higher precision with simpler hardware
3Productivity
If inaccurate laundry weight sensing is used, then device complexity is reduced, but energy consumption increases due to prolonged washing time
Solution Approach 1:
The system determines laundry weight and type during the acceleration phase before main washing begins, allowing the washing process to be optimized from the start based on accurate measurements, thereby avoiding energy-wasting prolonged washing times
Solution Approach 2:
The system uses motor current feedback during acceleration to continuously monitor and determine laundry characteristics, creating a closed-loop system that adjusts washing parameters based on real-time measurements to optimize energy efficiency
Data Source
AI summary
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 rotated while being accelerated, and a current sensing unit configured to sense current of the motor, wherein the controller is configured to obtain laundry weight and 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 within a range within which the laundry moves in the washing tub.