Predicting Aquaplaning Performance from Tyre Profile Images with Machine Learning
نویسندگان
چکیده
The tread of a tyre consists of a profile (pattern of grooves, sipes, and blocks) mainly designed to improve wet performance and to inhibit aquaplaning by providing a conduit for water to be expelled underneath the tyre as it makes contact with the road surface. Testing different tread profile designs is time consuming, as it requires fabrication of a tyre set using the tread profile, followed by physical measurement. In this paper, we propose a supervised machine learning method to predict a tyre’s aquaplaning performance based on the tread profile, which is described only in geometry and rubber stiffness. Our method provides a regressor from the space of profile geometry, reduced to images, to aquaplaning performance. Experimental results demonstrate that image analysis and machine learning, even on non-normalised data, in combination with heuristic or model based methods can yield improved prediction of aquaplaning performance, which have the potential to save substantial cost and time in tyre development. This investigation is based on data provided by Continental Reifen Deutschland GmbH.
منابع مشابه
Real-time estimation of aquaplaning with an optical tyre sensor
Future active safety systems will require more accurate information about the state of a vehicle and the operating conditions of an individual tyre. Aquaplaning is a dangerous situation in which the contact between the tyre and the road is partially or completely lost. In this paper, the movements of the inner liner of the tyre during aquaplaning are measured optically and exploited to estimate...
متن کاملThree 3-axial Accelerometers Fixed inside the Tyre for Studying Contact Patch Deformations in Wet Conditions
The tyre-road contact area was studied visually by means of a high-speed camera and three accelerometers fixed to the inner liner of the tyre carcass. Both methods show a distorted contact area in wet conditions, but interesting differences appeared. First, the contact area in full aquaplaning seems strongly distorted on a glass plate when subjected to visual inspection, while accelerometers in...
متن کاملA Hybrid Algorithm based on Deep Learning and Restricted Boltzmann Machine for Car Semantic Segmentation from Unmanned Aerial Vehicles (UAVs)-based Thermal Infrared Images
Nowadays, ground vehicle monitoring (GVM) is one of the areas of application in the intelligent traffic control system using image processing methods. In this context, the use of unmanned aerial vehicles based on thermal infrared (UAV-TIR) images is one of the optimal options for GVM due to the suitable spatial resolution, cost-effective and low volume of images. The methods that have been prop...
متن کاملماشین بینایی تشخیصگر باروری تخممرغ و ارزیابی کارایی شبکههای عصبی و ماشین بردار پشتیبان در آن
In this research, a system is proposed for detecting fertility of eggs. The system is composed of two parts: hardware and software. The fabricated hardware provides a platform to obtain accurate images from inner side of the eggs, without harming their embryos. The software part includes a set of image processing and machine vision processes, which is able to detect the fertility of eggs from c...
متن کامل