Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Machine learning to classify and predict objective and subjective assessments of vehicle dynamics: the case of steering feel.
KTH, School of Engineering Sciences (SCI), Aeronautical and Vehicle Engineering, Vehicle Dynamics. Volvo Cars.ORCID iD: 0000-0002-6699-1965
KTH, School of Engineering Sciences (SCI), Aeronautical and Vehicle Engineering, Vehicle Dynamics.ORCID iD: 0000-0002-2265-9004
KTH, School of Engineering Sciences (SCI), Aeronautical and Vehicle Engineering, Vehicle Dynamics.ORCID iD: 0000-0001-8928-0368
Volvo Cars.
2018 (English)In: Vehicle System Dynamics, ISSN 0042-3114, E-ISSN 1744-5159, Vol. 56, no 1, p. 150-171Article in journal (Refereed) Published
Abstract [en]

Objective measurements and computer-aided engineering simu- lations cannot be exploited to their full potential because of the high importance of driver feel in vehicle development. Further- more, despite many studies, it is not easy to identify the relation- ship between objective metrics (OM) and subjective assessments (SA), a task further complicated by the fact that SA change between drivers and geographical locations or with time. This paper presents a method which uses two artificial neural networks built on top of each other that helps to close this gap. The first network, based solely on OM, generates a map that groups together similar vehicles, thus allowing a classification of measured vehicles to be visualised. This map objectively demonstrates that there exist brand and vehi- cle class identities. It also foresees the subjective characteristics of a new vehicle, based on its requirements, simulations and measure- ments. These characteristics are described by the neighbourhood of the new vehicle in the map, which is made up of known vehicles that are accompanied by word-clouds that enhance this description. This forecast is also extended to perform a sensitivity analysis of the tolerances in the requirements, as well as to validate previously pub- lished preferred range of steering feel metrics. The results suggest a few new modifications. Finally, the qualitative information given by this measurement-based classification is complemented with a second superimposed network. This network describes a regression surface that enables quantitative predictions, for example the SA of the steering feel of a new vehicle from its OM. 

Place, publisher, year, edition, pages
Taylor & Francis Group, 2018. Vol. 56, no 1, p. 150-171
Keywords [en]
Objective metrics, Driver preference, Subjective assessments, Neural network, Regression analysis, Steering feel, Vehicle dynamics.
National Category
Vehicle Engineering
Research subject
Vehicle and Maritime Engineering
Identifiers
URN: urn:nbn:se:kth:diva-202345DOI: 10.1080/00423114.2017.1351617ISI: 000415982200008Scopus ID: 2-s2.0-85025804899OAI: oai:DiVA.org:kth-202345DiVA, id: diva2:1075897
Projects
iCOMSA
Funder
VINNOVA, 2012-04609TrenOp, Transport Research Environment with Novel Perspectives
Note

QC 20170308

Available from: 2017-02-21 Created: 2017-02-21 Last updated: 2017-12-11Bibliographically approved
In thesis
1. Towards efficient vehicle dynamics development: From subjective assessments to objective metrics, from physical to virtual testing
Open this publication in new window or tab >>Towards efficient vehicle dynamics development: From subjective assessments to objective metrics, from physical to virtual testing
2017 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Vehicle dynamics development is strongly based on subjective assessments (SA) of vehicle prototypes, which is expensive and time consuming. Consequently, in the age of computer- aided engineering (CAE), there is a drive towards reducing this dependency on physical test- ing. However, computers are known for their remarkable processing capacity, not for their feelings. Therefore, before SA can be computed, it is required to properly understand the cor- relation between SA and objective metrics (OM), which can be calculated by simulations, and to understand how this knowledge can enable a more efficient and effective development process.

The approach to this research was firstly to identify key OM and SA in vehicle dynamics, based on the multicollinearity of OM and of SA, and on interviews with expert drivers. Sec- ondly, linear regressions and artificial neural network (ANN) were used to identify the ranges of preferred OM that lead to good SA-ratings. This result is the base for objective require- ments, a must in effective vehicle dynamics development and verification.

The main result of this doctoral thesis is the development of a method capable of predicting SA from combinations of key OM. Firstly, this method generates a classification map of ve- hicles solely based on their OM, which allows for a qualitative prediction of the steering feel of a new vehicle based on its position, and that of its neighbours, in the map. This prediction is enhanced with descriptive word-clouds, which summarizes in a few words the comments of expert test drivers to each vehicle in the map. Then, a second superimposed ANN displays the evolution of SA-ratings in the map, and therefore, allows one to forecast the SA-rating for the new vehicle. Moreover, this method has been used to analyse the effect of the tolerances of OM requirements, as well as to verify the previously identified preferred range of OM.

This thesis focused on OM-SA correlations in summer conditions, but it also aimed to in- crease the effectiveness of vehicle dynamics development in general. For winter conditions, where objective testing is not yet mature, this research initiates the definition and identifica- tion of robust objective manoeuvres and OM. Experimental data were used together with CAE optimisations and ANOVA-analysis to optimise the manoeuvres, which were verified in a second experiment. To improve the quality and efficiency of SA, Volvo’s Moving Base Driving Simulator (MBDS) was validated for vehicle dynamics SA-ratings. Furthermore, a tablet-app to aid vehicle dynamics SA was developed and validated.

Combined this research encompasses a comprehensive method for a more effective and ob- jective development process for vehicle dynamics. This has been done by increasing the un- derstanding of OM, SA and their relations, which enables more effective SA (key SA, MBDS, SA-app), facilitates objective requirements and therefore CAE development, identi- fies key OM and their preferred ranges, and which allow to predict SA solely based on OM. 

Place, publisher, year, edition, pages
Stockholm: Kungliga tekniska högskolan, 2017. p. 72
Series
TRITA-AVE, ISSN 1651-7660 ; 2017:12
Keywords
Steering feel, vehicle handling, driver preference, objective metrics, subjective assessments, regression analysis, artificial neural network
National Category
Vehicle Engineering
Research subject
Vehicle and Maritime Engineering
Identifiers
urn:nbn:se:kth:diva-202348 (URN)978-91-7729-302-6 (ISBN)
Public defence
2017-03-17, D3, Lindstedsvägen 5, Stockholm, 10:00 (English)
Opponent
Supervisors
Projects
iCOMSA
Funder
VINNOVA, 2012-04609
Note

QC 20170223

Available from: 2017-02-23 Created: 2017-02-21 Last updated: 2017-02-23Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Gil Gómez, GasparNybacka, MikaelDrugge, Lars
By organisation
Vehicle Dynamics
In the same journal
Vehicle System Dynamics
Vehicle Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 1702 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf