Vehicle Subsystem Digital Twin for Predictive Maintenance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle subsystems, such as propulsion and cooling systems, often experience unexpected damage or failure, leading to downtime and financial losses due to the difficulty in identifying and preventing root causes during routine inspections, and the inability to predict failures effectively.
Innovation Solution
A system that generates a digital twin of vehicle subsystems based on operating parameters and environmental conditions, using physics-based models to simulate performance and compare it with actual field data, allowing for the determination of a performance composite index that predicts health and potential failures, enabling proactive maintenance and control of vehicle operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the frequency of inspection, repair, and replacement of subsystems is increased, then the occurrence of damage and failure is reduced, but the time spent on inspection increases and productivity decreases
Solution Approach 1:
The system performs preliminary monitoring and analysis of operating parameters to detect early signs of subsystem degradation before failure occurs. By continuously tracking performance metrics and comparing them against baseline data, the system identifies potential issues in advance, allowing for planned maintenance during convenient time windows rather than reactive repairs that disrupt productivity.
Solution Approach 2:
The patent replaces manual inspection mechanisms with an automated electronic monitoring system that continuously collects and analyzes operating parameters. Sensors and processors substitute for human inspectors, enabling real-time surveillance of subsystem health without requiring vehicle downtime for manual checks, thus maintaining productivity while improving reliability detection.
2Reliability
If routine inspections are performed to identify damage, then subsystem failures are detected, but the root cause of damage is difficult to identify and diagnose
Solution Approach 1:
The system implements continuous feedback loops where operating parameters are monitored, analyzed, and compared against expected performance patterns. When deviations are detected, the system traces the feedback chain to identify the root cause by analyzing correlations between multiple parameters and their temporal relationships, enabling precise diagnosis of underlying issues rather than just detecting symptoms.
Solution Approach 2:
The patent introduces digital twins as intermediary virtual models that simulate subsystem behavior under various conditions. These digital twins act as mediators between physical subsystem data and diagnostic conclusions, allowing the system to test hypotheses about root causes in the virtual model before applying diagnoses to the physical system, thereby simplifying complex diagnostic processes.
3Reliability
If unexpected damage or failure of subsystems occurs, then the vehicle becomes non-operational, but significant downtime and financial losses result
Solution Approach 1:
The system performs preliminary detection of degradation trends and predicts potential failures before they occur. By identifying early signs of subsystem deterioration through continuous parameter monitoring and comparison with baseline performance, the system enables advance scheduling of maintenance activities during planned downtime rather than experiencing unplanned vehicle outages, thereby reducing overall downtime and financial losses.
Solution Approach 2:
The patent implements a cushioning approach by maintaining performance thresholds and alert systems that warn of approaching failure conditions. This creates a buffer zone between normal operation and catastrophic failure, allowing operators to take preventive actions before the subsystem actually fails, thus cushioning against the impact of unexpected downtime and enabling smoother transition to maintenance mode.
Data Source
AI summary
A system includes one or more processors configured to obtain operating parameters of a subsystem of a vehicle that is configured to travel along a route during a trip. The one or more processors are configured to generate a digital twin of the subsystem based on the operating parameters, and to receive simulated performance data generated by execution of the digital twin with a designated model of the subsystem. The one or more processors are further configured to obtain field performance data of the subsystem monitored by sensors onboard the vehicle during the trip, and to determine a performance composite index of the subsystem of the vehicle based on a variance between the simulated performance data and the field performance data. The one or more processors are also configured to control the vehicle during the trip or a subsequent trip based on the performance composite index.