Engine Health Monitoring Using Synthetic Snapshot Diagnostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional engine health monitoring systems rely on limited snapshots of data, which lack the necessary granularity to effectively reduce unscheduled engine removals and plan targeted maintenance, leading to inefficiencies and potential failure events.
Innovation Solution
A system that utilizes both snapshot and continuous operating data to generate synthetic snapshots using machine-learned models and time-series pattern recognition techniques, providing a more comprehensive health assessment by aggregating alert scores from both data types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional snapshot-based health monitoring is used, then the system complexity remains low, but the measurement precision and reliability of engine health assessment are insufficient
Solution Approach 1:
The patent merges snapshot data and continuous operating data into a unified health assessment framework. The hybrid system combines periodic snapshots with continuous monitoring, allowing the system to leverage both data types simultaneously to improve measurement precision while managing complexity through integrated processing.
Solution Approach 2:
The system dynamically adjusts the monitoring approach by using continuous operating data during critical periods and snapshot data during stable periods. This dynamic adaptation allows the system to maintain high measurement precision when needed while reducing overall system complexity by not continuously processing all data at full resolution.
2Reliability
If more snapshot data is collected to improve health monitoring granularity, then the reliability of health assessment improves, but the loss of time for data processing and analysis increases
Solution Approach 1:
The system performs preliminary processing of continuous operating data by extracting key features and trends before they are needed for health assessment. This preliminary action prepares the data in advance, so when health assessment is required, the processing time is reduced while maintaining high reliability through comprehensive data analysis.
Solution Approach 2:
The hybrid approach allows the system to skip detailed analysis of continuous data during periods when snapshot data provides sufficient information. By selectively processing data based on operational conditions, the system maintains reliability when needed while minimizing time loss during routine operations.
3Quantity of substance
If continuous operating data is used to generate synthetic snapshots, then the quantity of data available for analysis increases, but the device complexity increases
Solution Approach 1:
The system extracts only the essential features and trends from continuous operating data that are relevant for health assessment, rather than processing the entire continuous data stream. This extraction approach increases the effective quantity of usable data while keeping the processing system complexity manageable by focusing on critical information.
Solution Approach 2:
The system creates synthetic snapshots by copying and transforming continuous operating data into snapshot-like structures that can be processed using existing snapshot analysis algorithms. This copying approach allows the system to leverage the full quantity of continuous data while maintaining compatibility with simpler processing frameworks.
4Reliability
If a hybrid approach combining snapshot and continuous data is used, then the reliability and precision of health monitoring improve, but the device complexity and processing requirements increase
Solution Approach 1:
The system designs a unified processing framework that can handle both snapshot and continuous operating data through the same health assessment algorithms. This multi-functional approach improves reliability by comprehensively analyzing all available data while avoiding the need for separate processing systems, thereby limiting the increase in device complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system and method for monitoring and diagnosis of engine health are provided. In one aspect, a system receives continuous operating data (COD) associated with an asset. The COD includes parameter values for one or more parameters over a collection time period. The system generates synthetic snapshot data based at least in part on the COD. The synthetic snapshot data includes one or more synthetic snapshots each containing the parameter values for the one or more parameters for a given timepoint within the collection time period. The system also receives snapshot data associated with the asset. The snapshot data includes one or more snapshots each containing parameter values for the one or more parameters for a given timepoint. The system generates an output indicating a health status of the asset or one or more components thereof based at least in part on the snapshot data and the synthetic snapshot data.