AI Laundry Tub Control for Accurate Load Weight Classification
Find Innovative SolutionsGenerate 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 machine learning-based approach with an artificial neural network to classify laundry weight and quality by controlling the acceleration gradient of the washing tub, allowing for precise classification based on current values sensed during rotation, and using these inputs to optimize data processing and reduce the need for extensive data determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If conventional experimental constant-based algorithms are used to sense laundry weight, then the sensing process is simple to implement, but the accuracy of laundry weight sensing deteriorates
Solution Approach 1:
The patent replaces conventional mechanical/mathematical calculation methods (using experimental constants and formulas) with an artificial neural network-based machine learning system. The neural network learns optimal weight sensing patterns from training data, automatically determining laundry weight without relying on pre-established experimental constants or complex mathematical expressions, thereby improving accuracy while maintaining implementation simplicity.
Solution Approach 2:
The patent changes the fundamental approach from using fixed experimental constants to using dynamically learned parameters through machine learning. The neural network adjusts its internal parameters (weights and biases) during training to optimize laundry weight sensing, allowing the system to adapt to different laundry conditions and improve measurement precision compared to static constant-based methods.
2Measurement precision
If experimental constants are accurately determined to improve laundry weight sensing accuracy, then sensing precision improves, but the time and effort required for setup increases
Solution Approach 1:
The patent performs preliminary machine learning training to pre-determine optimal sensing parameters before actual laundry weight measurement. The neural network is trained in advance using labeled training data containing motor current values and corresponding laundry weights, automatically learning the optimal weight sensing model without requiring manual experimentation or constant determination during deployment, thus eliminating time-consuming setup procedures.
Solution Approach 2:
The system performs self-learning through automated machine learning training, eliminating the need for manual experimentation and constant determination. The neural network automatically adjusts its parameters by processing training data and performing backpropagation, replacing the manual setup process where experts would need to determine experimental constants through time-consuming trials and errors.
3Productivity
If simple comparison methods are used to determine laundry weight, then the processing is fast and simple, but the accuracy of weight classification deteriorates
Solution Approach 1:
The patent replaces simple threshold-based comparison methods with an artificial neural network that processes motor current values through multiple layers of non-linear transformations. The neural network learns complex patterns and relationships between current values and laundry weights, enabling accurate classification across multiple weight ranges without requiring numerous discrete comparison operations, thus maintaining processing speed while improving classification accuracy.
4Ease of operation
If inaccurate laundry weight sensing occurs, then the washing process can proceed without precise measurement, but spin-drying time and energy consumption increase
Solution Approach 1:
The patent implements feedback by using the neural network's accurate laundry weight sensing results to dynamically adjust spin-drying parameters. The system measures motor current during washing, the neural network determines precise laundry weight, and this information feeds back to optimize spin-drying speed and duration, preventing excessive energy consumption while maintaining operational simplicity through automated control.
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 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.