Confidence-Based Machine Operation Management for Gas Turbine Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Equipment Health Monitoring (EHM) techniques face challenges in accurately diagnosing equipment failures in gas turbine engines due to multiple possible explanations for parameter deviations, secondary impacts on other parameters, and limited data fusion, leading to questionable diagnosis certainty and potential safety risks.
Innovation Solution
A method and tool using a network relationship structure with three bands (features, symptoms, and diagnoses) to process operational data, determining confidence values for features and symptoms, and linking them to diagnose machine operational states, enabling scalable and confident fault detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional EHM techniques use multiple parameter combinations to determine accurate diagnosis, then diagnosis accuracy is improved, but system complexity and difficulty of determining failure mode increases
Solution Approach 1:
The patent segments the diagnosis system into distinct functional modules: a data acquisition module that collects operational parameters, a feature extraction module that identifies anomalies, a diagnosis engine that applies multiple parameter combinations, and a result interpretation module. This segmentation allows complex diagnosis operations to be performed while maintaining manageable system architecture through modular design.
Solution Approach 2:
The patent introduces an intermediary diagnosis engine that acts as a mediator between raw sensor data and final failure mode determination. This engine processes multiple parameter combinations and synthesizes their interactions to determine accurate failure modes, reducing the complexity burden on individual components while maintaining high diagnosis accuracy.
2Reliability
If conventional EHM techniques review data from multiple sensors to determine anomalies, then fault detection capability is improved, but data processing time and computational resources increase
Solution Approach 1:
The patent implements preliminary action by pre-configuring diagnostic rules, parameter thresholds, and analysis algorithms during system setup. When operational data is collected, these pre-established frameworks enable rapid evaluation without requiring complex real-time computations, thus maintaining high fault detection capability while reducing processing time.
Solution Approach 2:
The patent employs skipping mechanisms by implementing hierarchical data processing that skips detailed analysis of normal operational parameters and focuses computational resources only on parameters showing anomalies or deviations. This allows the system to rapidly process large volumes of sensor data while maintaining reliable fault detection by concentrating analysis efforts where needed.
3Adaptability or versatility
If conventional EHM techniques use extensive tabulation and rule-based scripts for diagnosis, then diagnostic coverage is improved, but ease of operation and configuration updates deteriorates
Solution Approach 1:
The patent implements dynamics by providing a flexible, configurable diagnosis system where rules, thresholds, and parameters can be dynamically updated without requiring extensive reprogramming. The system allows operators to modify diagnostic configurations through user-friendly interfaces, enabling adaptability to different equipment and fault scenarios while maintaining ease of operation through automated configuration management.
Solution Approach 2:
The patent utilizes parameter changes by allowing dynamic adjustment of diagnostic thresholds, sensitivity levels, and analysis parameters based on operational conditions and equipment-specific requirements. This enables the system to maintain comprehensive diagnostic coverage across different scenarios while simplifying operation through parameter-based configuration rather than hard-coded rules.
4Adaptability or versatility
If conventional EHM techniques have limited data fusion capability, then system scalability is improved, but diagnosis certainty and reliability deteriorates
Solution Approach 1:
The patent implements universality by designing a data fusion framework that can handle multiple data sources, sensor types, and parameter formats through a unified processing architecture. This universal approach enables the system to scale to different equipment and data configurations while maintaining high diagnosis certainty through consistent application of multi-parameter analysis and anomaly correlation across diverse data sources.
Data Source
Figure 1~2
Figure 3
Figure 4~5
AI summary
A method for managing machine operation comprising sensing a plurality of operational variables for a machine during use thereof so as to generate operational data for said variables. The operational data is processed so as to determine features within the operational data which are indicative of a divergence from a desired operational state of the machine. Confidence values associated with said features are determined and used to assess whether the plurality of features and associated confidence values are indicative of a predetermined diagnosis for said machine. A confidence value for said diagnosis is determined based upon the associated feature confidence values and used to generate a signal indicative of an operational state of the machine. The invention may be used for engine health monitoring applications and may be used for determining necessary servicing or repair work for the engine.