Air conditioning system, refrigerant amount estimation method for air conditioning system, air conditioner, and refrigerant amount estimation method for air conditioner
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing refrigerant amount estimation methods in air conditioning systems face inaccuracies due to feature values being affected by factors other than refrigerant leakage, leading to erroneous results and failure to distinguish between refrigerant leakage and other device failures.
Innovation Solution
The implementation of a control circuit with multiple regression analysis and anomaly detection models, using first and second feature values to estimate refrigerant shortage rates and determine normal or abnormal operating conditions, preventing erroneous estimations by classifying detection values as normal or abnormal based on outlier calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a feature value that has a correlation with the remaining refrigerant amount is used to estimate the refrigerant amount, then the estimation can be performed, but the estimation accuracy deteriorates when the feature value is affected by factors other than refrigerant leakage
Solution Approach 1:
The patent segments the estimation process into two distinct phases: a learning phase where the system learns the relationship between feature values and refrigerant amounts under normal conditions, and an estimation phase where the learned model is applied. This segmentation allows the system to adapt to different operational states and improves reliability by distinguishing between normal variations and actual refrigerant leakage.
Solution Approach 2:
The patent performs preliminary learning of the relationship between feature values and refrigerant amounts before actual estimation is needed. By pre-establishing the correlation model during a learning period when the system is known to be operating normally, the system prepares a reference framework that can be used for accurate estimation while accounting for normal operational variations.
2Loss of information
If multiple feature values related to the refrigerant circuit are used for estimation, then more information is available, but it becomes difficult to distinguish between refrigerant leakage and other device failures
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors feature values and compares them against the learned model to determine whether the current state represents normal operation or actual refrigerant leakage. This feedback loop enables the system to distinguish between different failure modes by identifying deviations from the established normal operation patterns.
Solution Approach 2:
The patent utilizes changes in multiple parameters (feature values) simultaneously and analyzes their combined behavior to distinguish between refrigerant leakage and other failures. By monitoring how multiple parameters change together rather than in isolation, the system can identify the specific pattern characteristic of refrigerant leakage versus other abnormal conditions.
Data Source
AI summary
An air conditioning system includes an air conditioner that includes a refrigerant circuit that is constituted to have a structure in which indoor unit is connected to an outdoor unit and a predetermined amount of refrigerant is filled, and a server. The conditioner includes a first processor detect a quantity related to control of the conditioner, acquire the detected value, and transmit the acquired value to the server. The server includes a second processor receive the value from the conditioner, estimate a remaining refrigerant amount of the refrigerant remaining in the circuit by using a value of a feature value in a case where a state quantity related to an amount of the refrigerant that is filled in the circuit is indicated by the feature value, and determine whether the value of the feature value is detection value that is to be used to estimate the remaining refrigerant amount.