Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

EngineAD: A Real-World Vehicle Engine Anomaly Detection Dataset

Hadi Hojjati, Christopher Roth, Rory Woods, Ken Sills, Narges Armanfard

Abstract

The progress of Anomaly Detection (AD) in safety-critical domains, such as transportation, is severely constrained by the lack of large-scale, real-world benchmarks. To address this, we introduce EngineAD, a novel, multivariate dataset comprising high-resolution sensor telemetry collected from a fleet of 25 commercial vehicles over a six-month period. Unlike synthetic datasets, EngineAD features authentic operational data labeled with expert annotations, distinguishing normal states from subtle indicators of incipient engine faults. We preprocess the data into $300$-timestep segments of $8$ principal components and establish an initial benchmark using nine diverse one-class anomaly detection models. Our experiments reveal significant performance variability across the vehicle fleet, underscoring the challenge of cross-vehicle generalization. Furthermore, our findings corroborate recent literature, showing that simple classical methods (e.g., K-Means and One-Class SVM) are often highly competitive with, or superior to, deep learning approaches in this segment-based evaluation. By publicly releasing EngineAD, we aim to provide a realistic, challenging resource for developing robust and field-deployable anomaly detection and anomaly prediction solutions for the automotive industry.

EngineAD: A Real-World Vehicle Engine Anomaly Detection Dataset

Abstract

The progress of Anomaly Detection (AD) in safety-critical domains, such as transportation, is severely constrained by the lack of large-scale, real-world benchmarks. To address this, we introduce EngineAD, a novel, multivariate dataset comprising high-resolution sensor telemetry collected from a fleet of 25 commercial vehicles over a six-month period. Unlike synthetic datasets, EngineAD features authentic operational data labeled with expert annotations, distinguishing normal states from subtle indicators of incipient engine faults. We preprocess the data into -timestep segments of principal components and establish an initial benchmark using nine diverse one-class anomaly detection models. Our experiments reveal significant performance variability across the vehicle fleet, underscoring the challenge of cross-vehicle generalization. Furthermore, our findings corroborate recent literature, showing that simple classical methods (e.g., K-Means and One-Class SVM) are often highly competitive with, or superior to, deep learning approaches in this segment-based evaluation. By publicly releasing EngineAD, we aim to provide a realistic, challenging resource for developing robust and field-deployable anomaly detection and anomaly prediction solutions for the automotive industry.

Paper Structure

This paper contains 16 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Works
  3. Anomaly Taxonomies
  4. Methodological Paradigms
  5. Benchmarking Efforts
  6. Method
  7. Data Recording
  8. Preprocessing
  9. Dataset Annonymization
  10. Dataset Access
  11. Experiments
  12. Evaluation Protocol
  13. Anomaly Detection Models
  14. Results and Discussion
  15. Conclusion
  16. ...and 1 more sections

Figures (2)

  • Figure 1: Overview of Data Recording Process. Sensor signals from the vehicles were transmitted via the CAN bus and captured using a proprietary logging device connected to the network. Following data collection, a team of technicians systematically analyzed the sensor traces and maintenance information to assign ground-truth labels.
  • Figure 2: Preprocessing pipeline for vehicle sensor data. Thirteen sensors were selected with technician input. Data were cleaned, engine-on periods identified, resampled to 1Hz, and segmented into non-overlapping five-minute windows. Incomplete or missing segments were removed, and each vehicle’s labeled segments were saved for analysis.