Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Nov 20;22(22):8981.
doi: 10.3390/s22228981.

A Deep Learning Approach to Detect Anomalies in an Electric Power Steering System

Lawal Wale Alabe  1 , Kimleang Kea  1 , Youngsun Han  1 , Young Jae Min  2 , Taekyung Kim  3
Affiliations

A Deep Learning Approach to Detect Anomalies in an Electric Power Steering System

Lawal Wale Alabe et al. Sensors (Basel). .

Abstract

As anomaly detection for electrical power steering (EPS) systems has been centralized using model- and knowledge-based approaches, EPS system have become complex and more sophisticated, thereby requiring enhanced reliability and safety. Since most current detection methods rely on prior knowledge, it is difficult to identify new or previously unknown anomalies. In this paper, we propose a deep learning approach that consists of a two-stage process using an autoencoder and long short-term memory (LSTM) to detect anomalies in EPS sensor data. First, we train our model on EPS data by employing an autoencoder to extract features and compress them into a latent representation. The compressed features are fed into the LSTM network to capture any correlated dependencies between features, which are then reconstructed as output. An anomaly score is used to detect anomalies based on the reconstruction loss of the output. The effectiveness of our proposed approach is demonstrated by collecting sample data from an experiment using an EPS test jig. The comparison results indicate that our proposed model performs better in detecting anomalies, with an accuracy of 0.99 and a higher area under the receiver operating characteristic curve than other methods providing a valuable tool for anomaly detection in EPS.

Keywords: anomaly detection; deep learning; electric power steering; machine learning; sensor.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Framework of proposed anomaly detection model using electric power steering data.
Figure 2
Figure 2
Schematic of long short-term memory (LSTM) model.
Figure 3
Figure 3
The Autoencoder Architecture.
Figure 4
Figure 4
Data collection setup schematic.
Figure 5
Figure 5
Training and validation loss over epochs.
Figure 6
Figure 6
Training and validation Loss against number of epochs.
Figure 7
Figure 7
Model detection result from the confusion matrix.
Figure 8
Figure 8
ROC curve for LSTM-AE, GRU-AE and BiLSTM-AE anomalies detection model.
See this image and copyright information in PMC

References

    1. Xiaoling W., Yan Z., Hong W. Non-conduct steering sensor for Electric Power Steering; Proceedings of the 2009 International Conference on Information and Automation; Macau, China. 22–24 June 2009; pp. 1462–1467. - DOI
    1. LEARNING MODEL: Electric Power Steering. Exxotest Education, 2007; pp. 1–45. [(accessed on 16 November 2022)]. Available online: https://exxotest.com/en/
    1. Lin W.C., Ghoneim Y.A. Model-based fault diagnosis and prognosis for Electric Power Steering systems; Proceedings of the 2016 IEEE International Conference on Prognostics and Health Management (ICPHM); Ottawa, ON, Canada. 20–22 June 2016; pp. 1–8. - DOI
    1. Lee J., Lee H., Kim J., Jeong J. Model-based fault detection and isolation for electric power steering system; Proceedings of the 2007 International Conference on Control, Automation and Systems; Seoul, Republic of Korea. 17–20 October 2007; pp. 2369–2374. - DOI
    1. Choi K., Yi J., Park C., Yoon S. Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines. IEEE Access. 2021;9:120043–120065. doi: 10.1109/ACCESS.2021.3107975. - DOI