ECU Downtime Probability Reporting With ML Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for updating Electronic Control Unit (ECU) software in vehicles are inefficient, requiring significant memory, downtime, and reprogramming, and often introduce bugs or are inconvenient for vehicle owners, especially when dealing with differential updates or rolling back software versions without full memory requirements or downtime.
Innovation Solution
A system that uses delta files to update ECU software over-the-air without a dedicated client, utilizing a virtual file system to manage and track software versions, allowing for incremental updates and rollbacks without reprogramming, and leveraging machine learning for anomaly detection and remote monitoring to identify and address errors without interrupting ECU operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional ECU software update methods are used, then software can be updated, but significant memory space is required and downtime is needed
Solution Approach 1:
The patent segments the ECU software into functional units that can be independently managed and updated. Instead of requiring full software replacement, only specific functional units are updated via delta files, significantly reducing memory requirements while maintaining update reliability
Solution Approach 2:
The patent extracts and separates the update mechanism from the main ECU software system. A virtual file system is introduced as an independent layer that manages software versions without requiring physical memory expansion or full software reinstallation
2Reliability
If traditional ECU software update methods are used, then software can be updated, but reprogramming is required which is time-consuming and costly
Solution Approach 1:
The patent prepares the ECU for updates in advance by implementing a virtual file system that can store and manage multiple software versions simultaneously. This preliminary setup allows instant switching between versions without time-consuming reprogramming operations
Solution Approach 2:
The patent creates virtual copies of software functional units through the virtual file system. These virtual copies can be updated and tested before deployment, eliminating the need for time-consuming physical reprogramming of the ECU
3Ease of operation
If over-the-air update techniques are used, then updates can be provided remotely, but the entire ECU software must be distributed which is inefficient
Solution Approach 1:
The patent segments the software update into individual functional units rather than distributing the entire ECU software. Only the specific delta files containing changes to particular functional units are transmitted over-the-air, dramatically reducing data transmission volume while maintaining remote update capability
Solution Approach 2:
The patent extracts only the necessary update components (delta files for specific functional units) from the complete ECU software package. This extraction allows efficient over-the-air transmission of minimal data while achieving the desired update outcome
4Adaptability or versatility
If ECU software is updated, then new features and fixes are provided, but bugs may be introduced and dependencies between ECUs must be managed
Solution Approach 1:
The patent implements a feedback mechanism through the virtual file system that tracks software versions and dependencies across multiple ECUs. This feedback system monitors update propagation and ensures dependency management, maintaining system reliability while enabling functional adaptations
Solution Approach 2:
The patent prepares cushioning measures in advance by maintaining multiple software versions in the virtual file system. If bugs are introduced by an update, the system can immediately revert to a previous stable version, protecting software reliability while allowing functional experimentation
Data Source
AI summary
Disclosed embodiments relate to reporting Electronic Control Unit (ECU) errors or faults to a remote monitoring server. Operations may include receiving operational data from a plurality of ECUs in the vehicle, the operational data being indicative of a plurality of runtime attributes of the plurality of ECUs; generating, through a machine learning process, a statistical model of the operational data; receiving live, runtime updates from the plurality of ECUs in the communications network of the vehicle; identifying an ECU error associated with an ECU in the communications network of the vehicle, the ECU error being determined by a comparison of the live, runtime updates with the statistical model of the operational data to identify at least one deviation from the operational data; and wirelessly sending a report to the remote monitoring server based on the live, runtime updates, the report identifying the ECU and the identified ECU error.