In-System Hardware Testing for Predictive Fault Degradation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in detecting latent defects in hardware components, which can develop into permanent faults over time, compromising safety due to the limitations of conventional In-System Test (IST) methods that may not detect these issues until they become critical.
Innovation Solution
The system monitors performance characteristics, such as Vmin and leakage current, over time to determine a degradation rate, predicting permanent faults before they occur by performing multiple instances of fault tests and using machine learning models to analyze data from fault test results, environment data, and other factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional In-System Test (IST) methods are used to detect permanent faults, then fault detection capability is provided, but latent defects that develop over time cannot be detected until they become critical
Solution Approach 1:
The system performs preliminary actions by monitoring performance characteristics and detecting degradation trends before latent defects develop into permanent faults. Multiple fault tests are executed over time to establish baseline performance and identify early signs of component degradation, enabling proactive remediation before safety-critical failures occur.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring performance characteristics such as leakage current and Vmin, comparing actual performance against expected degradation rates, and triggering remedial actions when abnormal degradation patterns are detected. This closed-loop approach enhances detection sensitivity by identifying subtle performance changes that precede permanent faults.
2Reliability
If multiple instances of fault tests are performed over time to detect degradation, then early fault prediction capability is improved, but test time and computational resources increase
Solution Approach 1:
The system applies partial action by selectively executing fault tests based on risk assessment and operational context. Rather than performing exhaustive testing at all times, the system monitors key performance characteristics continuously and executes comprehensive fault tests only when degradation patterns suggest impending failures or when safety criticality increases, optimizing the balance between detection capability and resource consumption.
3Reliability
If degradation rate monitoring is implemented to predict permanent faults, then safety is enhanced, but system complexity increases due to additional monitoring and analysis requirements
Solution Approach 1:
The system achieves universality by designing monitoring infrastructure that serves multiple functions: performance characterization during normal operation, degradation rate calculation for trend analysis, fault prediction through machine learning models, and remedial action triggering. This multi-functional approach consolidates what could be separate complex systems into an integrated solution, reducing overall system complexity while maintaining enhanced safety capabilities.
Data Source
AI summary
In various examples, permanent faults in hardware component(s) and/or connections to the hardware component(s) of a computing platform may be predicted before they occur using in-system testing. As a result of this prediction, one or more remedial actions may be determined to enhance the safety of the computing platform (e.g., an autonomous vehicle). A degradation rate of a performance characteristic associated with the hardware component may be determined, detected, and/or computed by monitoring values of performance characteristics over time using fault testing.