Engine Health Estimation Using Change-Probability Fault Isolation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle engine systems face challenges in accurately identifying health degradation and isolating faults due to aging and wear of hardware components, which can cause model-based control methods to become misaligned with reality, necessitating new approaches for monitoring and mitigating these changes.
Innovation Solution
A configurable controller system that includes a state observer, feature calculator, optimizer, health estimator, fault isolator, and mitigator to monitor the health of engine components, detect changes indicative of faults, and adjust control strategies accordingly, using sensors and models to determine the source and impact of faults and modify operations to maintain optimal performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If model-based control methods are used to manage complex engine systems, then control performance is improved, but accuracy of fault detection deteriorates as components deviate from nominal behavior through aging and wear
Solution Approach 1:
The system segments fault detection into multiple independent change probability models, each monitoring specific feature parameters (intake manifold pressure, exhaust manifold pressure, mass air flow) separately. This allows precise localization of degradation sources while maintaining overall system control performance.
Solution Approach 2:
The patent introduces a health monitoring system as an intermediary layer between the model-based controller and the physical plant. This intermediary uses sensors and change probability models to detect deviations, enabling the controller to adapt when components deviate from nominal behavior without sacrificing control performance.
2Adaptability or versatility
If system complexity increases to accommodate new technologies and emissions standards, then functional capability is improved, but difficulty of detecting and measuring faults increases
Solution Approach 1:
The system divides the complex engine system into monitorable segments by selecting specific feature parameters (intake manifold pressure, exhaust manifold pressure, mass air flow) that represent key subsystems. This segmentation makes fault detection manageable despite overall system complexity.
Solution Approach 2:
The system uses change probability models that quantify deviations as probabilistic indicators, effectively 'color-coding' different fault conditions. This transforms complex multidimensional fault signatures into interpretable probability metrics that indicate the likelihood and type of degradation.
3Measurement precision
If health monitoring capabilities are enhanced to identify degradation, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The configurable controller serves multiple functions: it performs model-based control optimization while simultaneously running health monitoring and fault isolation. This multi-functionality enhances degradation identification precision without adding separate dedicated hardware systems.
Solution Approach 2:
The system uses the existing sensor infrastructure (intake manifold pressure sensor, exhaust manifold pressure sensor, mass air flow sensor) already present for control purposes to also perform health monitoring. This self-service approach enhances measurement precision without increasing device complexity.
Data Source
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.