Prediction method, recording medium, prediction system, server, and display device
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing drying time prediction methods in washing machines fail to accurately account for temporary stops during the drying operation, leading to reduced accuracy and user inconvenience when the operation is restarted.
Innovation Solution
A prediction method that includes a first prediction method using a learned model and a second prediction method based on temperature differences, with a determiner to assess the applicability of the first method after a restart, switching between methods as necessary to maintain accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the first prediction method (learned model) is used continuously after a restart, then prediction accuracy is maintained, but the system cannot adapt to internal environment changes caused by the stop
Solution Approach 1:
The patent implements dynamic switching between the first prediction method (learned model) and the second prediction method (temperature difference method) based on the operational state. When a stop is detected, the system transitions from the learned model to the temperature difference method, which is better suited for capturing internal environment changes during restart scenarios. This dynamic adaptation resolves the contradiction by allowing the system to maintain prediction accuracy while adapting to changing conditions.
Solution Approach 2:
The patent changes the prediction parameters based on operational state. The first method uses learned parameters from training data, while the second method uses real-time temperature difference parameters. By switching between different parameter sets depending on whether the dryer is continuously operating or has been stopped, the system maintains accuracy across different operational scenarios while adapting to internal environment changes.
2Adaptability or versatility
If the prediction method is switched after a restart, then adaptability to internal environment changes is improved, but prediction accuracy may be reduced
Solution Approach 1:
The patent incorporates feedback mechanisms where the system monitors operational state (continuous operation vs. stopped) and adjusts the prediction method accordingly. The control unit receives feedback about the operational history and dynamically selects the appropriate prediction method. This feedback loop ensures that the system adapts to internal environment changes while maintaining prediction accuracy by using the method best suited for the current operational context.
Solution Approach 2:
The system dynamically adjusts the prediction approach based on real-time operational state. Rather than using a fixed prediction method, the system transitions between the learned model and temperature difference method based on whether stops have occurred. This dynamic adaptation allows the system to maintain accuracy while being adaptable to internal environment changes.
3Device complexity
If a single prediction method is used, then device complexity is reduced, but the system cannot handle both continuous and stopped operation scenarios effectively
Solution Approach 1:
The patent implements a multi-functional prediction system where a single control unit can execute both the first prediction method (learned model) and the second prediction method (temperature difference method). This universal approach allows the system to handle both continuous operation and stopped operation scenarios effectively without requiring separate dedicated systems for each scenario, thus managing complexity while maintaining versatility.
Solution Approach 2:
The system uses dynamic method selection to handle different operational scenarios with a unified prediction framework. The control unit dynamically chooses between the learned model and temperature difference method based on operational state, allowing a single system to effectively handle both continuous and stopped operations without increasing overall structural complexity.
Data Source
AI summary
A prediction method includes acquisition step, prediction step, determination step, and processing step. In acquisition step, parameters for a drying operation are acquired. In prediction step, based on the acquired parameters, a drying time required for the drying operation is predicted by a first prediction method. In determination step, when the restart of the drying operation is detected while the drying operation is stopped, whether the first prediction method performed in prediction step is applicable is determined. In processing step, when the first prediction method is determined to be applicable, the first prediction method is continued and when the first prediction method is determined not to be applicable, predetermined processing is performed.