Vehicle Sensor Drift Detection via Cross-Sensor Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for diagnosing anomalies in vehicle control units due to sensor malfunctions are inefficient, leading to wasted time and vehicle downtime, as they often require analyzing the control unit and sensors after anomalies are detected, and faulty sensors can behave unpredictably, making systematic monitoring difficult.
Innovation Solution
A predictive diagnosis method that uses comparisons between similar sensors to detect drifts over time, particularly when the engine is stopped or has been stopped for a predetermined period, allowing for early detection of anomalies before they affect vehicle functionalities, and includes sending warnings to the driver or operator about potential future issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor monitoring is performed continuously during vehicle operation, then anomaly detection capability is improved, but false alarms increase due to unpredictable sensor behavior under various operating conditions
Solution Approach 1:
The system performs sensor drift detection during engine stop periods before the vehicle operation begins. By conducting measurements when the engine is stopped or has been stopped for a predetermined number of hours, the system establishes baseline sensor readings under stable conditions, enabling early anomaly detection without the interference of dynamic operating conditions that cause unpredictable sensor behavior.
2Difficulty of detecting and measuring
If diagnostic analysis is performed after anomaly detection, then root cause identification is achieved, but vehicle downtime and operator time are significantly increased
Solution Approach 1:
The system proactively detects sensor drifts during engine stop periods before anomalies affect vehicle functionalities. By monitoring sensor measurements over time and comparing them against reference values or other sensor readings, the system identifies drifts early, allowing for scheduled maintenance during convenient times rather than emergency repairs that cause vehicle downtime and operator time waste.
3Reliability
If multiple sensors are monitored simultaneously, then system coverage is improved, but complexity of the monitoring system increases
Solution Approach 1:
The monitoring system uses a universal approach by comparing sensor readings against reference values that can be derived from other sensors measuring the same physical quantity. This multi-functional comparison method can be applied to various sensor types (temperature, pressure, flow, etc.) using the same basic algorithm, enabling broad system coverage without proportionally increasing system complexity.
Data Source
Figure 1
Figure 2
AI summary
System for the predictive diagnosis of sensor-related anomalies of vehicles comprising the steps of comparing between each other measurements of similar sensors, namely of sensors which measure the same physical magnitudes, over time, in order to detect variations indicating a drift of one of the sensors.