Learned Model Drying Time Prediction for Continuous Display Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional dryer methods inaccurately display remaining drying time, leading to user confusion due to discontinuous changes and interruptions, necessitating a more precise prediction method.
Innovation Solution
A drying time prediction method using a learned model that inputs operation conditions and actual operation time periods to predict the finish time of drying operations, incorporating sensing information and standardizing actual operation times based on a distribution of past operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional drying time display methods are used, then the system is simple to operate, but the measurement precision of remaining drying time is poor
Solution Approach 1:
The system performs preliminary actions by collecting and storing operation condition data and actual operation time data from multiple past drying operations before making a prediction. This pre-collected data is then used by the learned model to accurately predict the remaining drying time for the current operation, resolving the contradiction between prediction accuracy and system complexity.
Solution Approach 2:
The system implements feedback by continuously comparing the predicted remaining drying time with actual drying progression. The learned model uses feedback from past operation outcomes to refine its predictions, improving measurement precision while maintaining manageable system complexity through iterative learning.
2Reliability
If conventional drying time display methods are used, then the device complexity is low, but the reliability of drying time information is poor
Solution Approach 1:
The system uses feedback from actual operation outcomes to continuously improve prediction reliability. The learned model incorporates feedback from multiple past operations to refine its predictions, ensuring that the drying time information displayed to users is reliable and accurate.
Solution Approach 2:
The system performs preliminary data collection and analysis by gathering operation conditions and actual operation times from multiple past drying operations. This preliminary preparation enables the learned model to generate reliable predictions for current operations, enhancing the reliability of drying time information.
3Measurement precision
If a learned model is used for drying time prediction, then the measurement precision of remaining drying time is improved, but the loss of time for data processing increases
Solution Approach 1:
The system performs preliminary actions by collecting and storing operation condition data and actual operation time data from multiple past drying operations in advance. This pre-collected data is readily available when needed, allowing the learned model to make accurate predictions without time-consuming data collection during the drying process itself.
Solution Approach 2:
The system uses partial action by selecting only the most relevant features from the collected data for the learned model prediction. Instead of processing all possible data, the system focuses on key operation conditions and time data that have the greatest impact on prediction accuracy, reducing data processing time while maintaining high measurement precision.
Data Source
AI summary
A drying time prediction method includes: obtaining an operation condition set at the start of operation of a first dryer; obtaining the first actual operation time period of each of at least one first operation performed by the first dryer; obtaining operation finish time information from a learned model by inputting, to the learned model, the operation condition and first actual information that is based on the first actual operation time period, the operation finish time information being related to the finish time of the operation started under the operation condition; and outputting first information based on the operation finish time information.