Anomaly detection model for an air conditioning system and methods of generating the anomaly detection model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current air conditioning systems rely on scheduled or reactive maintenance, which can lead to early or unnecessary replacements, reduced efficiency, and potential failures due to human error or lack of timely intervention.
Innovation Solution
Implementing anomaly detection models, such as artificial-intelligence-based machine-learning models, to monitor and control air conditioning systems by analyzing operating data from sensors, identifying anomalies, and providing predictive maintenance recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If scheduled or reactive maintenance is used, then maintenance can be performed, but it leads to early or unnecessary replacements, reduced efficiency, and potential failures
Solution Approach 1:
The anomaly detection model performs preliminary analysis of operating data to identify potential issues before they cause system failures. By continuously monitoring sensor data and comparing it against learned normal patterns, the system can detect anomalies early and schedule maintenance proactively, preventing failures before they occur and avoiding unnecessary maintenance interventions.
Solution Approach 2:
The system implements a feedback loop where operating data from sensors is continuously collected, analyzed by the anomaly detection model, and used to generate maintenance recommendations. This closed-loop feedback enables the system to adapt to changing operating conditions and improve its anomaly detection accuracy over time, optimizing maintenance timing based on actual system state rather than fixed schedules.
2Reliability
If anomaly detection models are implemented, then predictive maintenance is enabled, but device complexity increases
Solution Approach 1:
The anomaly detection model serves multiple functions: it monitors system health, detects anomalies, predicts potential failures, and generates maintenance recommendations. By consolidating these functions into a single machine learning model rather than using separate systems for each function, the patent reduces overall system complexity while maintaining comprehensive predictive maintenance capabilities.
Solution Approach 2:
The system uses its own operating data from integrated sensors to perform self-diagnosis and anomaly detection. Rather than requiring external monitoring equipment or manual inspection, the air conditioning system autonomously collects and analyzes its own performance data, reducing the complexity of adding external monitoring infrastructure while enabling sophisticated predictive maintenance.
Data Source
AI summary
An anomaly detection model for an air (fluid) conditioning unit or system, methods of detecting an anomaly using the anomaly detection model, and methods of generating the anomaly detection model. The air conditioning unit may include a plurality of sensors measuring operating conditions of the air conditioning unit to generate operating data. A computing device may be coupled to the air conditioning unit to receive the operating data and configured to execute the anomaly detection model to detect an anomaly in the air conditioning unit. The anomaly detection model may be an artificial-intelligence-based model, such as a machine-learning-based model. When the air conditioning unit is a dehumidifier, the anomaly detection model may determine a moisture mass balance between the process air and the reactivation air and determine, using an outlier detection method, if the moisture mass balance is an outlier.