Compressor Power Prediction for Early HVAC Degradation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing HVAC&R systems lack the ability to efficiently and reliably detect potential problems and performance degradations early, due to the complexity and impracticality of acquiring and processing large data sets over extended periods.
Innovation Solution
A monitoring system employing continuous machine learning and a temperature map to establish a relation between compressor input power parameters and condenser and evaporator intake fluid temperatures, allowing for early detection of performance degradation by comparing predicted and observed power values, while minimizing false positives and negatives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If large data sets are acquired and processed over extended periods to detect performance degradations, then detection reliability is improved, but system complexity and implementation difficulty increase significantly
Solution Approach 1:
The patent extracts only the essential parameters needed for degradation detection (compressor input power, condenser inlet temperature, evaporator inlet temperature) from the full system data set. By focusing on this minimal sufficient data set rather than processing all available system data, the solution achieves reliable detection while significantly reducing computational complexity and implementation burden.
Solution Approach 2:
The system performs preliminary learning during a commissioning phase to establish the relationship between the three key parameters before actual degradation monitoring begins. This preliminary action creates a baseline model that enables immediate reliable detection without requiring extended operational data collection, thus reducing both time and complexity requirements.
2Loss of time
If continuous monitoring is implemented to detect performance degradations early, then detection timeliness is improved, but data acquisition and processing requirements increase
Solution Approach 1:
The patent extracts and monitors only three critical parameters (compressor input power, condenser inlet temperature, evaporator inlet temperature) continuously, rather than collecting and processing large volumes of comprehensive system data. This selective extraction enables immediate early detection of performance degradations while minimizing data acquisition and processing requirements.
3Measurement precision
If system characteristics are learned over long periods to improve prediction accuracy, then prediction reliability is improved, but commissioning time and system downtime increase
Solution Approach 1:
The system performs the learning process during a dedicated commissioning phase before normal operation begins. By completing the characteristic learning in advance using only three key parameters, the system achieves high prediction accuracy without requiring extended commissioning periods or prolonged system downtime, as the learned model enables immediate accurate monitoring.
Data Source
AI summary
System and method for monitoring and detecting potential problems early in a VCC based HVAC&R system employs a monitoring application or agent that uses continuous machine learning and a temperature map to derive or “learn” a relation between a measured input power parameter of one or more system compressors, and condenser and evaporator intake fluid temperatures, based on observations of the temperatures and the input power parameter when the HVAC&R system is new or in a “newly maintained” condition. The monitoring agent can then use the learned relation to determine, based on subsequent observations of the condenser and evaporator intake fluid temperatures, the input power parameter values that should be expected if the HVAC&R system were operating in the “newly maintained” condition. The agent can thereafter compare the expected compressor input power parameter values with observed input power parameter values to determine early whether the system is experiencing performance degradation.