Engine Health Estimation and Fault Isolation Under Model Drift
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle engine systems face challenges in accurately identifying and isolating faults due to component degradation and failure, as existing model-based control methods become misaligned with reality over time, necessitating new approaches for health monitoring and fault mitigation.
Innovation Solution
A configurable controller system that includes a state observer, feature calculator, optimizer, health estimator, fault isolator, and mitigator to monitor and adjust the engine's operation based on real-time data from sensors, allowing for precise identification of faults and adaptation of control models to maintain optimal performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If model-based control methods are used to manage complex engine systems, then control capability is improved, but model accuracy deteriorates over time due to component degradation and aging
Solution Approach 1:
The system performs preliminary health degradation estimation by continuously monitoring feature parameters and comparing them against learned normal operation patterns. This early detection mechanism allows the system to identify deviations from nominal behavior before they lead to significant model inaccuracies, enabling proactive model updates or reconfiguration.
Solution Approach 2:
The control system transitions from static model-based control to dynamic adaptive control. The health estimator continuously updates degradation assessments, and the controller dynamically adjusts control strategies based on current system health status. This dynamic adaptation allows the system to maintain control accuracy despite component aging and degradation.
2Reliability
If health monitoring and fault isolation capabilities are enhanced, then system reliability is improved, but controller complexity increases
Solution Approach 1:
The controller is segmented into distinct functional modules: feature parameter extraction module, health estimator module, and fault isolator module. Each module performs a specific function in the health monitoring chain, making the overall complex system manageable through modular design. This segmentation allows independent development, testing, and maintenance of each component.
Solution Approach 2:
Feature parameters serve as intermediaries between raw sensor data and health degradation assessment. Instead of directly analyzing complex sensor signals, the system extracts meaningful feature parameters that capture essential system behavior. These intermediate representations simplify the health estimation process while maintaining diagnostic accuracy.
3Measurement precision
If feature parameters are continuously monitored and analyzed, then fault detection precision is improved, but computational load and data processing requirements increase
Solution Approach 1:
The system extracts only the most relevant feature parameters from sensor data that are indicative of health degradation. Instead of processing all available sensor signals, the feature calculator identifies and extracts specific parameters that capture essential system behavior. This selective extraction reduces computational load while maintaining fault detection precision.
Solution Approach 2:
The health estimator applies change probability models selectively to assess whether observed parameter changes indicate significant degradation. Rather than continuously triggering fault isolation for every parameter variation, the system uses probability thresholds to determine when intervention is warranted. This partial action approach reduces unnecessary computational processing while maintaining detection precision.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods and systems for fault identification and mitigation in an engine system. A state observer obtains current state information from the engine system, and a feature calculator uses data obtained from the state observer to calculate one or more feature indicators, which are monitored by a health estimator for the occurrence of a change using one or more change probability models. When the health estimator identifies a change, a fault isolator determines a component of the engine system that is subject to fault or health deterioration.