Car Sensors Health Monitoring by Verification Based on Autoencoder and Random Forest Regression

2025-05-01

AI Summary

This paper addresses the challenge of real-time health monitoring for automotive sensors by proposing a novel ECU-based cross-sensor validation framework for fault detection and fault-tolerant operation. Methodologically, it first identifies highly cooperative sensor groups via correlation analysis; then jointly employs an autoencoder for anomaly detection and a random forest regressor to estimate nominal sensor values; finally, a dynamic normality-based statistical model enables adaptive alarm triggering and seamless value compensation. Its key innovation lies in the first-ever inter-sensor mutual calibration mechanism, integrating deep-learning-based anomaly identification with interpretable regression estimation to support early fault warning, autonomous alerting, and real-time sensor-value substitution. Evaluated on 20 critical sensors of the Saipa Quick vehicle platform, the method achieves 99% fault detection accuracy with millisecond-level response latency, significantly enhancing system robustness and online fault tolerance.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements

Abstract

Driver assistance systems provide a wide range of crucial services, including closely monitoring the condition of vehicles. This paper showcases a groundbreaking sensor health monitoring system designed for the automotive industry. The ingenious system leverages cutting-edge techniques to process data collected from various vehicle sensors. It compares their outputs within the Electronic Control Unit (ECU) to evaluate the health of each sensor. To unravel the intricate correlations between sensor data, an extensive exploration of machine learning and deep learning methodologies was conducted. Through meticulous analysis, the most correlated sensor data were identified. These valuable insights were then utilized to provide accurate estimations of sensor values. Among the diverse learning methods examined, the combination of autoencoders for detecting sensor failures and random forest regression for estimating sensor values proved to yield the most impressive outcomes. A statistical model using the normal distribution has been developed to identify possible sensor failures proactively. By comparing the actual values of the sensors with their estimated values based on correlated sensors, faulty sensors can be detected early. When a defective sensor is detected, both the driver and the maintenance department are promptly alerted. Additionally, the system replaces the value of the faulty sensor with the estimated value obtained through analysis. This proactive approach was evaluated using data from twenty essential sensors in the Saipa's Quick vehicle's ECU, resulting in an impressive accuracy rate of 99%.

Problem

• Monitoring car sensor health using autoencoder and random forest regression
• Detecting faulty sensors by comparing actual and estimated values
• Providing early warnings and replacing faulty sensor values automatically

Innovation

• Autoencoder detects sensor failures effectively
• Random forest regression estimates sensor values
• Normal distribution model identifies potential failures