An Evaluation of Autoencoder and Sparse Filter as Automated Feature Extraction Process for Automotive Damper Defect Diagnosis

Zehelein, Thomas; Werk, Philip; Lienkamp, Markus

doi:10.1109/ever.2019.8813630

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, adding their increased complexity compared to traditional machine learning algorithms (e.g., SVM) makes sense only if these simple algorithms are lacking performance. Based on the classification results in [8,9], applying deep learning algorithms for damper defect detection should be investigated.…”

Section: Introductionmentioning

confidence: 99%

Diagnosing Automotive Damper Defects Using Convolutional Neural Networks and Electronic Stability Control Sensor Signals

Zehelein

Hemmert-Pottmann

Lienkamp

2020

JSAN

Self Cite

View full text Add to dashboard Cite

Chassis system components such as dampers have a significant impact on vehicle stability, driving safety, and driving comfort. Therefore, monitoring and diagnosing the defects of these components is necessary. Currently, this task is based on the driver’s perception of component defects in series production vehicles, even though model-based approaches in the literature exist. As we observe an increased availability of data in modern vehicles and advances in the field of deep learning, this paper deals with the analysis of the performance of Convolutional Neural Networks (CNN) for the diagnosis of automotive damper defects. To ensure a broad applicability of the generated diagnosis system, only signals of a classic Electronic Stability Control (ESC) system, such as wheel speeds, longitudinal and lateral vehicle acceleration, and yaw rate, were used. A structured analysis of data pre-processing and CNN configuration parameters were investigated in terms of the defect detection result. The results show that simple Fast Fourier Transformation (FFT) pre-processing and configuration parameters resulting in small networks are sufficient for a high defect detection rate.

show abstract

Section: Introductionmentioning

confidence: 99%