Multi-SoC Control Unit Failover With Degraded Operation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automotive control units face challenges in achieving fault-tolerance without increasing cost and space requirements, particularly in advanced driver assistance systems (ADAS), where failures of individual components can impact system functionality and driver fallback is limited.
Innovation Solution
A control unit with multiple single-chip systems (SoCs) that share sensor data and employ degradation mechanisms to perform functions of a failed SoC, allowing for a fault-tolerant system design with reduced redundancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fully redundant architectures are used to achieve fault-tolerance, then system reliability is improved, but device complexity and space requirement increase
Solution Approach 1:
The patent implements a multi-functionality principle where a single SoC can perform multiple roles: primary processing, backup processing, and degradation mechanism execution. The control unit is designed so that one SoC can take over functions from another SoC in case of failure, eliminating the need for completely separate redundant systems while maintaining fault-tolerance capability
Solution Approach 2:
The patent merges the backup functionality into the primary system architecture. Instead of having separate redundant components, the degradation mechanisms and fallback capabilities are integrated into the existing SoC structure, allowing one SoC to serve both as primary processor and as backup for another SoC
2Reliability
If multiple main computers are used in Multi-SoC architecture, then fault-tolerance is improved, but manufacturing cost and space requirement increase
Solution Approach 1:
The control unit is designed with universal SoCs that can perform multiple functions including primary processing, backup processing, and degradation operations. This multi-functionality reduces the need for additional specialized components, thereby lowering manufacturing costs while maintaining fault-tolerance through the ability of one SoC to take over from another
3Productivity
If application-specific development is used to optimize performance, then productivity is improved, but adaptability decreases
Solution Approach 1:
The patent implements dynamic adaptability through degradation mechanisms that can adjust system operation in real-time based on fault conditions. The control unit can dynamically switch between different operational modes: full functionality when healthy, and degraded functionality when faults occur, allowing the system to adapt to various failure scenarios while maintaining optimized performance for each mode
Data Source
AI summary
A method for operating a computing arrangement. The computing arrangement includes: a plurality of single-chip systems, wherein the single-chip systems are configured to obtain the same sensor data, and at least one degradation mechanism configured to perform functions of a failed single-chip system on another single-chip system. In the method, when a failure of at least one of the single-chip systems is sensed, a switch takes place to another single-chip system to perform a function assigned to the failed single-chip system. A degradation mechanism is additionally performed.