Refrigerant Amount Estimation Using Continuous-Value Correction Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating refrigerant amounts in cooling systems using discrete maps are inaccurate due to large step widths and increased data complexity, especially when multiple parameters are involved, making it difficult to implement effectively.
Innovation Solution
A refrigerant amount determining device that acquires operation data, calculates a refrigerant amount index value, infers corrections using a correction model, and determines the refrigerant amount based on continuous values, allowing for improved accuracy and ease of implementation even with multiple parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If discrete map with large step width is used for prediction, then implementation is simple, but prediction accuracy is poor
Solution Approach 1:
The patent transforms the discrete map parameters into continuous value parameters. Instead of using discrete step widths in the map, the system uses continuous parameter values to represent refrigerant amount, allowing for more precise predictions while maintaining implementation feasibility through neural network-based inference.
2Measurement precision
If discrete map with small step width is used for prediction, then prediction accuracy is improved, but data amount and complexity increase
Solution Approach 1:
The system changes from discrete parameters with multiple steps to continuous parameters. This reduces the dimensional complexity of the data structure while maintaining high prediction accuracy, as continuous values require less data to represent the full range of possible states compared to fine-grained discrete steps.
3Reliability
If multiple parameters are used for prediction, then prediction comprehensiveness is improved, but map dimensionality and data amount increase
Solution Approach 1:
The patent applies continuous parameter transformation to handle multiple input parameters. By using continuous value representations instead of discrete map indices, the system can incorporate multiple parameters (such as temperature, pressure, flow rate) without creating a high-dimensional discrete map, thus maintaining prediction comprehensiveness while controlling data complexity.
Data Source
AI summary
A refrigerant amount determining device includes: an operation data acquiring unit configured to acquire operation data of an air conditioning system; a calculating unit configured to calculate a refrigerant amount index value from the operation data acquired; an inferring unit configured to infer information regarding correction of the refrigerant amount index value using a correction model and at least one of the acquired operation data or the calculated refrigerant amount index value; and a determining unit configured to determine a refrigerant amount of the air conditioning system based on the information regarding correction of the refrigerant amount index value.