Browse Publications Technical Papers 2018-01-0562
2018-04-03

Estimation of Vehicle Tire-Road Contact Forces: A Comparison between Artificial Neural Network and Observed Theory Approaches 2018-01-0562

One of the principal goals of modern vehicle control systems is to ensure passenger safety during dangerous maneuvers. Their effectiveness relies on providing appropriate parameter inputs. Tire-road contact forces are among the most important because they provide helpful information that could be used to mitigate vehicle instabilities. Unfortunately, measuring these forces requires expensive instrumentation and is not suitable for commercial vehicles. Thus, accurately estimating them is a crucial task. In this work, two estimation approaches are compared, an observer method and a neural network learning technique. Both predict the lateral and longitudinal tire-road contact forces. The observer approach takes into account system nonlinearities and estimates the stochastic states by using an extended Kalman filter technique to perform data fusion based on the popular bicycle model. On the other hand, artificial neural networks (ANN) were trained and tested using experimental data to estimate contact forces. These were built with a single hidden layer. Furthermore, the ANN input parameters were carefully selected to ensure appropriate convergence and avoid overtraining. All predictions from both approaches are validated against experimental data. Results show that the observer approach is capable of predicting forces with higher accuracy as consequence of the detailed vehicle dynamic models introduced on the overall estimation scheme. The ANN approach is limited to the specific car from which the training data was collected and is purely based on machine learning. Nevertheless, it provides a fast and straightforward alternative to obtain force estimates with comparable accuracy to observer approaches.

SAE MOBILUS

Subscribers can view annotate, and download all of SAE's content. Learn More »

Access SAE MOBILUS »

Members save up to 18% off list price.
Login to see discount.
Special Offer: Download multiple Technical Papers each year? TechSelect is a cost-effective subscription option to select and download 12-100 full-text Technical Papers per year. Find more information here.
We also recommend:
TECHNICAL PAPER

Recognizing Manipulated Electronic Control Units

2015-01-0202

View Details

TECHNICAL PAPER

Security in Wireless Powertrain Networking through Machine Learning Localization

2019-01-1046

View Details

TECHNICAL PAPER

Feedback Error Learning Neural Networks for Air-to-Fuel Ratio Control in SI Engines

2003-01-0356

View Details

X