Diagnostic Aggregation Mechanism for Turbine Engine Fault Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fault detection systems for mechanical systems, particularly turbine engines, face challenges in harmonizing multiple fault detection techniques, leading to incomplete, ambiguous, or contradictory conclusions, which limits their ability to accurately detect potential faults and handle multiple concurrent faults effectively.
Innovation Solution
A multi-technique, multi-fault detection system that combines conclusions from multiple fault detection techniques using a diagnostic aggregation mechanism, which evaluates the dependency of data to isolate likely faults by identifying valid multiple fault sets and applying aggregation rules based on evidence interdependence, employing a hybrid Dezert-Smarandache Theory (DSmT) to aggregate conclusions from independent and dependent evidence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple fault detection techniques are used to monitor a mechanical system, then the ability to detect potential faults is improved, but the ability to correctly harmonize multiple potential conclusions is worsened
Solution Approach 1:
The patent introduces a diagnostic aggregation mechanism as an intermediary component that receives conclusions from multiple fault detection techniques and harmonizes them into a unified diagnostic result. This mechanism manages the complexity of combining multiple conclusions by providing a structured aggregation process that handles dependencies and conflicts between different detection techniques.
Solution Approach 2:
The patent creates a composite diagnostic system that combines multiple fault detection techniques and their conclusions into a unified diagnostic framework. By aggregating conclusions from different techniques while accounting for their interdependencies, the system forms a composite diagnostic capability that is more reliable than individual techniques alone.
2Reliability
If multiple fault detection techniques are used, then comprehensive fault coverage is improved, but the ability to deal with multiple concurrent faults and dependent evidence is worsened
Solution Approach 1:
The patent changes the parameters of evidence evaluation by introducing dependency modeling that adjusts how conclusions from different fault detection techniques are weighted and combined. The aggregation mechanism modifies the evaluation parameters based on the interdependence relationships between evidence sources, allowing for more accurate precision when multiple faults are present.
Solution Approach 2:
The patent segments the diagnostic process into distinct components: individual fault detection techniques, conclusion generation, dependency analysis, and aggregation. This segmentation allows each component to be optimized independently while maintaining overall system accuracy, particularly in handling multiple concurrent faults through structured aggregation.
3Ease of operation
If previous techniques for combining incomplete conclusions are used, then simple aggregation is achieved, but the ability to accurately detect potential faults is reduced
Solution Approach 1:
The diagnostic aggregation mechanism serves as an intermediary that bridges simple aggregation and accurate fault detection. It provides a structured approach that maintains operational simplicity while incorporating sophisticated dependency modeling and aggregation rules that preserve detection accuracy even when dealing with incomplete conclusions from multiple techniques.
Data Source
AI summary
A system and method for combining conclusions from multiple fault detection techniques to isolate likely faults in a turbine engine is provided. The system and method provide the ability to effectively deal with multiple concurrent faults in the engine. Additionally, the embodiments of the invention provide the ability to correctly characterize multiple conclusions generated from evidence having different levels of interdependence. In one embodiment, the conclusions based on device data with high dependency are aggregated using a high dependency aggregation rule, and the resulting high-dependency sets are then further aggregated using a weak dependency rule. Finally, any conclusions based on independent evidence can be aggregated using an independent combination rule. The resulting aggregation determines which fault(s) are most likely indicated by the plurality of conclusions, taken into account the dependency of the device data used to generate the conclusions.