Working Paper Article Version 2 This version is not peer-reviewed

Feasibility of Neural Network Based Virtual Sensor for Vehicle Unsprung Mass Relative Velocity Estimation

Version 1 : Received: 28 July 2021 / Approved: 29 July 2021 / Online: 29 July 2021 (11:49:58 CEST)
Version 2 : Received: 23 September 2021 / Approved: 24 September 2021 / Online: 24 September 2021 (12:42:07 CEST)

A peer-reviewed article of this Preprint also exists.

Šabanovič, E.; Kojis, P.; Šukevičius, Š.; Shyrokau, B.; Ivanov, V.; Dhaens, M.; Skrickij, V. Feasibility of a Neural Network-Based Virtual Sensor for Vehicle Unsprung Mass Relative Velocity Estimation. Sensors 2021, 21, 7139. https://doi.org/10.3390/s21217139 Šabanovič, E.; Kojis, P.; Šukevičius, Š.; Shyrokau, B.; Ivanov, V.; Dhaens, M.; Skrickij, V. Feasibility of a Neural Network-Based Virtual Sensor for Vehicle Unsprung Mass Relative Velocity Estimation. Sensors 2021, 21, 7139. https://doi.org/10.3390/s21217139

Journal reference: Sensors 2021, 21, 7139
DOI: 10.3390/s21217139

Abstract

With the automotive industry moving towards automated driving, sensing is increasingly important in enabling technology. The virtual sensors allow data fusion from various vehicle sensors and provide a prediction for measurement that is hard or too expensive to measure in another way or in the case of demand on continuous detection. In this paper, virtual sensing is discussed for the case of vehicle suspension control, where information about the relative velocity of the unsprung mass for each vehicle corner is required. The corresponding goal can be identified as a regression task with multi-input sequence input. The hypothesis is that the state-of-art method of Bidirectional Long-Short Term Memory (BiLSMT) can solve it. In this paper, a virtual sensor has been proposed and developed by training a neural network model. The simulations have been performed using an experimentally validated full vehicle model in IPG Carmaker. Simulations provided the reference data which was used for Neural Network (NN) training. The extensive dataset covering 26 scenarios has been used to obtain training, validation and testing data. The Bayesian Search was used to select the best neural network structure using root mean square error as a metric. The best network is made of 167 BiLSTM, 256 fully connected hidden units and 4 output units. Error histograms and spectral analysis of the predicted signal compared to the reference signal are presented. The results demonstrate the good applicability of neural network-based virtual sensors to estimate vehicle unsprung mass relative velocity.

Keywords

virtual sensor; automotive control; active suspension; vehicle state estimation; neural networks; deep learning; long-short term memory; sequence regression

Subject

ENGINEERING, Automotive Engineering

Comments (1)

Comment 1
Received: 24 September 2021
Commenter: Eldar Šabanovič
Commenter's Conflict of Interests: Author
Comment: Updated version based on reviewer comments.
+ Respond to this comment

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 1
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.