Turbomachine Event Duration Analytics for Health Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring and predicting failures in turbomachines, such as gas turbine engines or gas compressors, are inadequate in providing timely and effective interventions to prevent costly unexpected failures.
Innovation Solution
A method involving hardware processors that receive data from electronic control units, calculate machine event durations, generate datasets, apply machine-learning models to predict future abnormal states, and execute remedial functions when indicated by the predictive output.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring methods are used to track machine failures, then implementation is simple, but prediction accuracy and timeliness are insufficient
Solution Approach 1:
The system performs preliminary actions by calculating machine event durations and applying machine-learning models to predict future abnormal states before failures actually occur. This advance prediction capability enables proactive maintenance scheduling, improving prediction accuracy while managing system complexity through structured data processing pipelines.
Solution Approach 2:
The patent introduces intermediate processing layers including duration calculation modules and machine-learning model layers that act as mediators between raw sensor data and failure predictions. These intermediaries transform complex sensor data into meaningful duration metrics and predictive insights, enhancing prediction accuracy while organizing system complexity into manageable stages.
2Reliability
If machine event durations are calculated and analyzed to predict failures, then prediction capability improves, but data processing complexity increases
Solution Approach 1:
The system segments the failure prediction process into distinct stages: data collection from sensors, duration calculation for specific machine events, dataset generation with correlated parameters, and machine-learning model application. This segmentation improves prediction reliability by ensuring thorough analysis at each stage while making the overall complex process more manageable and systematic.
Solution Approach 2:
The system performs preliminary data processing by calculating machine event durations and generating correlated datasets before applying prediction models. This preliminary preparation of structured data with meaningful features improves the reliability of failure predictions while organizing data processing complexity into systematic preparatory steps.
3Productivity
If proactive maintenance is implemented through prediction, then downtime and repair costs are reduced, but implementation complexity increases
Solution Approach 1:
The system enables proactive maintenance by performing preliminary failure predictions and generating maintenance recommendations before actual failures occur. This advance prediction allows scheduling maintenance during convenient downtime windows, improving operational continuity while managing implementation complexity through automated prediction and recommendation systems.
Solution Approach 2:
The system implements feedback loops where prediction results inform maintenance decisions, and maintenance outcomes feed back into the prediction model for continuous improvement. This feedback mechanism enhances productivity by optimizing maintenance timing while managing implementation complexity through iterative learning and adaptation.
Data Source
AI summary
The unexpected failure of a turbomachine can be costly and dangerous. Processes may collect data from a turbomachine, calculate durations of machine events from the collected data, and apply a model to those machine-event durations to predict future machine-event durations and/or detect trends in the machine-event durations. This predictive output may be utilized to inform downstream functions regarding the health of the turbomachine. For example, a downstream function may utilize the predictive output to detect degradation or a potential future failure in the turbomachine and trigger remedial functions, such as alerts and/or controls, to prevent or mitigate the degradation or failure of the turbomachine.