Coupled-System Distress Detection Using Fuzzy Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Health monitoring of complex machines, such as gas turbine engines, faces challenges in accurately modeling cross-coupling effects between systems, leading to difficulties in detecting distress in dynamically and thermally coupled systems, especially when parameters are within valid operating ranges.
Innovation Solution
A distress detection system utilizing data fusion and fuzzy logic to combine parameters from separate sensors, such as main oil pressure and temperature, to identify system deterioration and trigger maintenance actions, even when parameters are within acceptable ranges, thereby addressing reduced observability across systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If health monitoring focuses on discrete systems with separate parameter monitoring, then system complexity is reduced and ease of operation is improved, but measurement precision and reliability of distress detection deteriorate due to inability to capture cross-coupling effects
Solution Approach 1:
The patent merges parameters from multiple discrete systems (e.g., lubrication system oil temperature and gear system vibration) into a unified monitoring framework. This combines previously separate monitoring efforts to detect cross-coupling effects that indicate distress, thereby improving measurement precision without significantly increasing operational complexity.
Solution Approach 2:
The monitoring system is designed to universally apply to multiple systems and parameter types simultaneously. By creating a multi-functional monitoring approach that can handle thermal, mechanical, and dynamic parameters across different subsystems, the patent improves distress detection reliability while maintaining ease of operation through a standardized process.
2Ease of operation
If parameters are monitored within valid operating ranges only, then false alarms are reduced and ease of operation is improved, but measurement precision deteriorates because distress conditions within operational ranges are not detected
Solution Approach 1:
The patent applies preliminary action by detecting early signs of distress through cross-coupling effects before they develop into full-blown failures. By monitoring for subtle interactions between systems while parameters are still within operational ranges, the system identifies incipient faults early, enabling preventive maintenance before distress becomes apparent through traditional threshold-based monitoring.
Solution Approach 2:
The patent uses cross-coupling effects as intermediary indicators of system distress. Rather than directly monitoring for failure conditions, the system detects subtle interactions and energy transfers between systems that serve as early warning signs, allowing precise detection of distress conditions while maintaining operational parameters within valid ranges.
3Device complexity
If discrete block monitoring is used for each system, then device complexity is reduced and ease of manufacture is improved, but reliability of distress detection worsens due to inability to model cross-coupling effects
Solution Approach 1:
The patent merges discrete monitoring blocks into an integrated analysis framework that captures cross-coupling effects. By combining parameters from multiple systems and analyzing their interactions, the patent improves distress detection reliability while keeping the underlying discrete monitoring architecture intact, thus not significantly increasing device complexity.
Solution Approach 2:
The patent adds a new dimension of analysis by examining inter-system relationships and cross-coupling effects. Rather than only monitoring individual system parameters in isolation, the system analyzes the dimensional space of parameter interactions, enabling reliable distress detection through patterns that span multiple systems without requiring complex reconfiguration of the base monitoring infrastructure.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A distress detection system (121) includes a data repository (120) operable to collect sensor data from a monitored system (100). The distress detection system also includes an analysis system (122) with a processing system (130) operable to access a first parameter of a first system of the monitored system from the data repository and access a second parameter of the first system of the monitored system from the data repository. The processing system is also operable to apply fuzzy reasoning rules to evaluate a combination of the first parameter and the second parameter to determine an in-range interaction with respect to a second system of the monitored system as fuzzy metric data points, classify a component of the second system as being in distress based on comparing the fuzzy metric data points to a limit line, and assert a component distress indicator responsive to classifying the component of the second system as being in distress.