Vehicle Computing Parameter Verification for Random Error Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computing systems in vehicles face challenges in addressing random errors without duplicating hardware resources, which is costly and not commercially available for high-computing-speed applications.
Innovation Solution
A computing device with a first unit ensuring high integrity and a second unit with higher computing power but lower integrity, executing computation functions redundantly and comparing results to detect errors, without duplicating hardware.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If hardware resources are duplicated to treat random errors, then reliability is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual copy of the computation function by executing it twice on the same computing unit with different random seeds. This virtual copying approach achieves error detection capability without duplicating physical hardware resources, thereby maintaining low device complexity while improving reliability through random error treatment
Solution Approach 2:
The patent changes the parameter of random seed values between two executions of the same computation function. By varying this parameter, the system generates different computational paths that can reveal random errors through result comparison, achieving reliability improvement without hardware duplication
2Reliability
If hardware resources are duplicated to ensure integrity, then reliability is improved, but computing power is reduced
Solution Approach 1:
The patent uses virtual copying through software-based redundant execution rather than physical hardware duplication. This allows the system to maintain full computing power of the original computing unit while achieving integrity improvement through comparative verification of computation results
Solution Approach 2:
The patent replaces the mechanical/hardware-based integrity assurance system with a software-based system. Instead of using dedicated hardware for verification (which would reduce computing power), the system uses software algorithms to perform redundant computations and compare results, thereby maintaining full computing power while ensuring integrity
3Reliability
If redundant execution is performed to detect errors, then reliability is improved, but execution time increases
Solution Approach 1:
The patent implements periodic verification by executing the computation function twice with different random seeds and comparing results. This periodic redundant execution provides error detection capability while minimizing time loss through efficient comparison mechanisms and early termination when errors are detected
4Productivity
If high computing power is used for complex algorithms, then productivity is improved, but vulnerability to random errors increases
Solution Approach 1:
The patent implements a feedback mechanism where computation results from two different executions are compared. When discrepancies are detected (indicating random errors), the system can request re-computation or notify relevant components. This feedback loop maintains high productivity by only triggering additional computations when necessary while ensuring reliability through error detection
Data Source
AI summary
A computing device includes a first unit and a second unit. In response to receipt of a request corresponding to a computing function, the first unit may: determine an execution context; trigger a first execution of the function on the second unit, this delivering a first comparison parameter, a first temporal execution parameter being associated with the first comparison parameter; trigger a second execution of the function on the second unit, this delivering a second comparison parameter, a second temporal execution parameter being associated with the second comparison parameter; compare the first and second comparison parameters, a temporal comparison parameter being associated with the result of the comparison; and determine a computing status.