On-Board Machine Diagnostics for CAN and LIN Fault Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Diagnosing failures in complex industrial machines with sophisticated diagnostic systems is challenging due to increasing complexity, especially in communication systems like CAN and LIN, where issues may be elusive and time-consuming to resolve.
Innovation Solution
An on-board diagnostic system with machine learning capabilities is deployed on a telematics gateway, providing real-time monitoring and analysis of machine components and communications systems, using virtual fault injection and machine learning to automate diagnostics and recommend solutions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If internal diagnostic systems are used, then cost and size are reduced, but diagnostic capability and scope are limited
Solution Approach 1:
The patent introduces an intermediary diagnostic system that bridges the gap between simple internal diagnostics and complex external diagnostic tools. This intermediary system provides enhanced diagnostic capabilities while remaining integrated within the machine architecture, resolving the contradiction between cost-effectiveness and diagnostic reliability.
Solution Approach 2:
The diagnostic system is segmented into multiple levels: basic internal diagnostics for routine monitoring and advanced diagnostic capabilities for complex failures. This segmentation allows the system to provide comprehensive diagnostic coverage without requiring all components to be present in every configuration, balancing cost and capability.
2Device complexity
If traditional diagnostic methods are used, then system complexity is low, but diagnostic accuracy and speed are insufficient
Solution Approach 1:
The patent replaces traditional mechanical and manual diagnostic methods with electronic and software-based solutions. Machine learning algorithms and automated analysis systems substitute for manual technician diagnostics, significantly improving diagnostic accuracy while managing system complexity through software integration.
Solution Approach 2:
The system dynamically adjusts diagnostic parameters and thresholds based on operating conditions and historical data. This adaptability allows the system to maintain high diagnostic accuracy across varying operational scenarios without requiring proportional increases in system complexity.
3Extent of automation
If manual diagnostic procedures are used, then automation level is low, but diagnostic time and resource consumption are high
Solution Approach 1:
The diagnostic system performs self-diagnosis and automated fault detection without requiring constant technician intervention. The system monitors itself, identifies anomalies, and provides diagnostic information automatically, dramatically reducing diagnostic time while increasing automation level.
Solution Approach 2:
The system implements continuous feedback loops where diagnostic results are fed back into the monitoring system to refine future diagnostics. This automated feedback mechanism enables the system to learn from past diagnostics and improve accuracy over time without additional manual input, reducing both time and resource consumption.
Data Source
AI summary
A diagnostic system and technique for a machine (e.g. an industrial machine) to detect, identify, and resolve faults and issues with the machine, including connectivity and/or issues with a communications system. An on-board diagnostic system provides monitoring of machine components and/or the machine's communications system. The on-board system provides faster (e.g. real-time) and more accurate diagnostics and troubleshooting of machine issues. Captured data is communicated to a remote system for further analysis based on machine learning.