Napredna pretraga

Pregled bibliografske jedinice broj: 121243

Application of the RBF neural network for tire-road friction estimation


Matuško, Jadranko; Petrović, Ivan; Perić, Nedjeljko
Application of the RBF neural network for tire-road friction estimation // CD-ROM Proceedings of the IEEE International Symposium on Industrial Electronics, ISIE 2003
Rio de Janeiro, Brazil, 2003. (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Application of the RBF neural network for tire-road friction estimation

Autori
Matuško, Jadranko ; Petrović, Ivan ; Perić, Nedjeljko

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
CD-ROM Proceedings of the IEEE International Symposium on Industrial Electronics, ISIE 2003 / - Rio de Janeiro, Brazil, 2003

Skup
IEEE International Symposium on Industrial Electronics

Mjesto i datum
Rio de Janeiro, Brazil, 09-11.06. 2003

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Tire/road friction; RBF neural network; Lyapunov stability

Sažetak
This paper deals with the problem of the robust tire-road friction force estimation. Good information about friction force generated in contact between wheel and road has significant importance in many active safety systems in modern vehicles (anti-lock brake systems, traction control, vehicle dynamic systems, etc). Since state estimators are usually based on exact model of process, they are therefore limited by the model accuracy. A new estimation scheme based on RBF neural net-works is proposed in this paper. The neural network is added to the estimator to compensate the effects of the friction model uncertainties to the estimation quality. An adaptation law for the neural network parameters is derived using Lyapunov stability analysis. The proposed state estimator provides accurate estimation of the tire-road friction force when friction characteristic is only approximately known or even completely unknown. Quality of the estimation is examined through simulation using one wheel friction model. Simulation results suggest very fast compensation of the changes of the model parameters (< 150 ms) even when they vary in a wide range (changes of 100% and more). Possible drawback of proposed estimation scheme is the fact that neural network does not give the information what particular parameter has changed

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika



POVEZANOST RADA


Projekt / tema
0036017
0036018

Ustanove
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Ivan Petrović (autor)

Avatar Url Jadranko Matuško (autor)

Avatar Url Nedjeljko Perić (autor)

Citiraj ovu publikaciju

Matuško, Jadranko; Petrović, Ivan; Perić, Nedjeljko
Application of the RBF neural network for tire-road friction estimation // CD-ROM Proceedings of the IEEE International Symposium on Industrial Electronics, ISIE 2003
Rio de Janeiro, Brazil, 2003. (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Matuško, J., Petrović, I. & Perić, N. (2003) Application of the RBF neural network for tire-road friction estimation. U: CD-ROM Proceedings of the IEEE International Symposium on Industrial Electronics, ISIE 2003.
@article{article, year = {2003}, keywords = {Tire/road friction, RBF neural network, Lyapunov stability}, title = {Application of the RBF neural network for tire-road friction estimation}, keyword = {Tire/road friction, RBF neural network, Lyapunov stability}, publisherplace = {Rio de Janeiro, Brazil} }