Vehicle Fault Propagation Analytics in Multi-Layer Control Software
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle motion control systems rely on manual processes by subject matter experts to identify the root cause of faults, which is inefficient and lacks a data-driven approach.
Innovation Solution
A data analytics system with a multi-layered control software architecture that generates unique triggers as faults propagate, builds a network of propagation paths, and uses data analysis and machine learning to determine the root cause by tracing these paths from the bottommost software layer to the global layer.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual processes by subject matter experts are used to identify root cause of faults, then specialized knowledge can be applied, but the process is inefficient and time-consuming
Solution Approach 1:
The patent replaces the manual mechanical process of expert analysis with an automated data analytics system that uses machine learning models and algorithms to automatically identify fault root causes, thereby eliminating time loss while maintaining diagnostic accuracy
Solution Approach 2:
The patent introduces a data analytics system as an intermediary between fault occurrence and root cause identification, using this intermediate system to process data through multiple software layers and propagate fault analysis automatically, resolving the contradiction between expert knowledge application and time efficiency
2Reliability
If manual review of recorded data is employed to determine root cause, then comprehensive analysis can be performed, but the process lacks automation and scalability
Solution Approach 1:
The patent substitutes the manual review process with an automated data analytics system that systematically processes recorded data through multiple software layers, achieving both reliable fault analysis and complete automation through machine learning models
Solution Approach 2:
The system enables self-service fault diagnosis by automatically analyzing recorded data without human intervention, using machine learning models to independently determine root causes while maintaining reliable analysis through systematic multi-layer software processing
3Adaptability or versatility
If a multi-layer control software architecture is used, then comprehensive control functionality is achieved, but the complexity of identifying fault propagation paths increases
Solution Approach 1:
The patent segments the complex multi-layer software architecture into distinct analyzable layers, allowing the data analytics system to process fault propagation through each layer separately using unique triggers, thereby managing complexity while preserving comprehensive control functionality
Solution Approach 2:
The patent introduces unique triggers as intermediaries between software layers to mark and track fault propagation, simplifying the analysis of complex multi-layer architecture by providing clear transition points that the data analytics system can automatically follow
4Loss of information
If unique triggers are generated as faults propagate through multi-layer software architecture, then fault propagation can be tracked, but the data processing complexity increases
Solution Approach 1:
The patent creates simplified copies of fault propagation information through unique triggers at each software layer, allowing the data analytics system to track fault paths without processing the full complexity of the original multi-layer data structures
Solution Approach 2:
The patent extracts only the essential fault propagation information through unique triggers from the complex multi-layer software architecture, separating the critical diagnostic data from the surrounding system complexity to reduce processing burden
Data Source
AI summary
A data analytics system for a vehicle includes one or more controllers having a multi-layered control software architecture including two or more software layers and a health monitoring structure. The one or more controllers execute instructions to receive a fault, and in response to receiving the fault, generate, by the health monitoring structure, a plurality of unique triggers as the fault propagates throughout the multi-layered control software architecture. The controllers build a network including a plurality of propagation paths and identify one or more main propagation paths that are part of the network based on a data analysis of a mock big data set. The one or more controllers build a complete propagation pathway including two or more main propagation paths. In response to determining only one main propagation path, the controllers determine a root cause of the fault based on the only one main propagation path.