Heat Exchanger Abnormal Operation Detection via Model Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Diagnosing and predicting abnormal operation of an environmental control system (ECS) connected to a gas turbine engine is difficult and time-consuming due to the complexity of monitoring and comparing environmental and operating parameters with modeled parameters.
Innovation Solution
A computer-implemented method that receives environmental operating conditions data, calculates differences between estimated and measured values, and compares these differences to threshold values and abnormal operation models to identify any abnormal operation, outputting an associated identity if a match is found.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional monitoring and comparison methods are used to diagnose ECS abnormal operation, then measurement precision can be maintained, but diagnostic time increases significantly
Solution Approach 1:
The system pre-establishes multiple abnormal operation models representing different failure modes of the heat exchanger before actual operation. These models include expected sensor readings under various abnormal conditions, allowing the diagnostic system to quickly compare actual measurements against pre-computed expectations rather than performing complex real-time analysis from scratch.
Solution Approach 2:
The patent creates simplified copies of normal operating models and abnormal operation models that represent typical failure patterns. Instead of analyzing raw sensor data through complex physical equations in real-time, the system compares measurements against these pre-generated model copies, dramatically reducing diagnostic computation time while maintaining accuracy.
2Measurement precision
If comprehensive sensor monitoring is implemented to improve detection accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The system extracts and separates the diagnostic function from the overall ECS control system. By isolating the abnormal operation detection into a dedicated module that uses pre-established models, the patent reduces the complexity burden on the main control system while maintaining comprehensive monitoring capabilities through targeted sensor measurements.
Solution Approach 2:
The patent introduces abnormal operation models as intermediary representations between raw sensor measurements and diagnostic conclusions. These models act as a bridge, translating complex multi-sensor data into comparable expected patterns, thereby simplifying the analysis process while preserving measurement precision through the use of multiple sensor inputs.
3Speed
If real-time comparison of measured and modeled parameters is performed, then detection speed improves, but computational complexity increases
Solution Approach 1:
The system performs preliminary computation by pre-establishing abnormal operation models that encapsulate expected sensor readings under various failure conditions. This advance preparation allows real-time diagnostics to simply compare measurements against pre-computed models rather than performing complex calculations during actual diagnostic operations, achieving fast response with minimal real-time computation.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This method enables efficient identification of abnormal ECS operation, reducing diagnostic time by comparing calculated differences to known abnormal operation modes and generating new models for future reference when unknown issues are encountered.
Implementation Method 1
a heat exchanger operable to remove heat from an airflow therethrough
Implementation Method 2
a heat exchanger operable to remove heat from an airflow therethrough
Data Source
AI summary
A computer-implemented method, environmental control system, and aircraft are provided. Environmental operating conditions data for a heat exchanger is received. Measured values from sensors measuring parameters of the heat exchanger are also received. An operating model for the heat exchanger based on the received environmental operating conditions is retrieved from a first data structure. The retrieved model includes estimated values for the sensors. A difference between the estimated values and the measured values is calculated. The calculated differences are compared to at least one threshold value. Upon the differences exceeding the at least one threshold value, the calculated differences are compared to abnormal operation models in an abnormal operation library data structure. Upon the calculated difference matching an abnormal operation model in the abnormal operation library data structure, outputting an abnormal operation identity associated with the abnormal operation model. If there is no match, a learning process develops a new model for a new abnormal operation.