Deep Convolutional Autoencoder for Assessment of Drive-Cycle Anomalies in Connected Vehicle Sensor Data

TL;DR

This paper presents a convolutional autoencoder-based method for unsupervised detection of powertrain faults in hybrid-electric vehicles by analyzing multivariate sensor time-series data, demonstrating superior performance over other techniques.

Contribution

Introduces a fully convolutional autoencoder for automated fault detection in vehicle sensor data, outperforming other unsupervised methods in identifying anomalies.

Findings

Autoencoder effectively detects powertrain faults from sensor data.

Autoencoder outperforms outlier detectors and other deep learning methods.

Robust data reconstruction approach identifies abnormal sequences.

Abstract

This work investigates a practical and novel method for automated unsupervised fault detection in vehicles using a fully convolutional autoencoder. The results demonstrate the algorithm we developed can detect anomalies which correspond to powertrain faults by learning patterns in the multivariate time-series data of hybrid-electric vehicle powertrain sensors. Data was collected by engineers at Ford Motor Company from numerous sensors over several drive cycle variations. This study provides evidence of the anomaly detecting capability of our trained autoencoder and investigates the suitability of our autoencoder relative to other unsupervised methods for automatic fault detection in this data set. Preliminary results of testing the autoencoder on the powertrain sensor data indicate the data reconstruction approach availed by the autoencoder is a robust technique for identifying the abnormal sequences in the multivariate series. These results support that irregularities in hybrid-electric vehicles' powertrains are conveyed via sensor signals in the embedded electronic communication system, and therefore can be identified mechanistically with a trained algorithm. Additional unsupervised methods are tested and show the autoencoder performs better at fault detection than outlier detectors and other novel deep learning techniques.