Automated Vehicle Device Fault Detection and Mitigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems lack an efficient method to collect, process, and interpret data from on-vehicle and off-vehicle sources to identify problematic devices and execute automated mitigations for device performance issues without human intervention.
Innovation Solution
A system and method that utilize data from engine, mobile device, LMU, and HOS sources to analyze pre-defined patterns, identify malfunctioning devices, and generate mitigation strategies for automated resolution, leveraging AI and machine learning for real-time recognition and mitigation of issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual monitoring and analysis of device data is performed, then device performance issues can be identified, but the process requires human intervention and takes significant time
Solution Approach 1:
The system enables automated self-diagnosis and self-resolution of device performance issues. The machine learning model automatically analyzes device data, identifies problems, and executes mitigation strategies without human intervention, allowing the system to service itself and resolve issues autonomously
Solution Approach 2:
The system implements continuous feedback loops where device performance data is constantly monitored, analyzed by the machine learning model, and used to automatically adjust and optimize device operation. The system learns from past performance patterns and continuously improves its ability to detect and resolve issues
2Measurement precision
If comprehensive data from multiple sources is collected and analyzed, then device faults can be accurately identified, but the system complexity increases
Solution Approach 1:
The machine learning model serves multiple functions: it analyzes data from diverse sources (engine, mobile device, LMU, HOS systems), detects various types of device faults, predicts performance trends, and generates mitigation strategies. This single multi-functional component handles the complexity of processing comprehensive data from multiple sources without requiring separate specialized systems for each function
Solution Approach 2:
The machine learning model acts as an intermediary layer between the raw data from multiple complex sources and the fault detection/resolution processes. It consolidates and processes the multi-source data into actionable insights, simplifying the overall system architecture by providing a single point of analysis rather than requiring direct integration and analysis of all individual data sources
3Productivity
If automated mitigation strategies are executed without human input, then issue resolution time is reduced, but the risk of incorrect mitigations increases
Solution Approach 1:
The system performs preliminary analysis and validation of potential mitigation strategies before execution. The machine learning model evaluates multiple possible actions, predicts their outcomes, and selects the most appropriate mitigation strategy based on learned patterns from historical data, ensuring that automated actions are well-considered before being implemented
Solution Approach 2:
The system monitors the effectiveness of executed mitigations and automatically adjusts future strategies based on the results. This self-learning capability allows the system to improve the accuracy of its automated decision-making over time, reducing the risk of incorrect mitigations while maintaining high productivity
Data Source
AI summary
A system (1600) and method (960) for utilizing data from on-vehicle and off-vehicle sources to identify problematic devices and to execute automated mitigations is disclosed herein. The system (1620) comprises assigning authority engine (1105) for a vehicle (1000), a device (110) for the vehicle (1000), one or more databases (1615), and more or more cloud sources (1175). The assigning authority engine (1105) is configured to analyze the data based on a plurality of pre-defined patterns to identify a malfunctioning device and to transmit a mitigation strategy for the malfunctioning device.