Pavement type and wear condition classification from tire cavity acoustic measurements with artificial neural networks

Research on the effect of tire pattern design on noise and its reduction

This paper studies pattern noise in original equipment fitment through four approaches, including pitch arrangement optimization, pipe resonance experiment, orthogonal experimental design of tread transverse groove, and block shift simulation. An in-cab noise test is conducted to verify the effectiveness. Results show an 8.7% reduction in total harmonic energy and 12% decrease in the highest harmonic peak through pitch optimization. This paper introduces the 3-Sum concept to measure the difficulty of exciting a certain pitch harmonic. Meanwhile, the optimal width combination is found for central and shoulder longitudinal grooves. Transverse groove width, angle, and direction are studied using analysis of range and analysis of variance with the best match producing an indoor drum noise value of 76.09 dB. The simulation by the tread noise prediction system shows that the optimal misalignment of the central rib should be -7 mm, and its noise prediction value has a 2.21 dB(A) decrease from the original plan while the optimal misalignment of the shoulder rib is at its initial position. In the in-cab noise test, the sound pressure level of the optimized plan is reduced by 0.46 dB(A). Notably, the root mean square value within the frequency band 700-1300 Hz is reduced by 3.26 dB(A), which is a figure that fulfills the expected tread noise reduction.

Urban Road Surface Discrimination by Tire-Road Noise Analysis and Data Clustering

The surface condition of roadways has direct consequences on a wide range of processes related to the transportation technology, quality of road facilities, road safety, and traffic noise emissions. Methods developed for detection of road surface condition are crucial for maintenance and rehabilitation plans, also relevant for driving environment detection for autonomous transportation systems and e-mobility solutions. In this paper, the clustering of the tire-road noise emission features is proposed to detect the condition of the wheel tracks regions during naturalistic driving events. This acoustic-based methodology was applied in urban areas under nonstop real-life traffic conditions. Using the proposed method, it was possible to identify at least two groups of surface status on the inspected routes over the wheel-path interaction zone. The detection rate on urban zone reaches 75% for renewed lanes and 72% for distressed lanes.

Intelligent Tire Sensor-Based Real-Time Road Surface Classification Using an Artificial Neural Network

Vehicles today have many advanced driver assistance control systems that improve vehicle safety and comfort. With the development of more sophisticated vehicle electronic control and autonomous driving technology, the need and effort to estimate road surface conditions is increasing. In this paper, a real-time road surface classification algorithm, based on a deep neural network, is developed using a database collected through an intelligent tire sensor system with a three-axis accelerometer installed inside the tire. Two representative types of network, fully connected neural network (FCNN) and convolutional neural network (CNN), are learned with each of the three-axis acceleration sensor signals, and their performances were compared to obtain an optimal learning network result. The learning results show that the road surface type can be classified in real-time with sufficient accuracy when the longitudinal and vertical axis acceleration signals are trained with the CNN. In order to improve classification accuracy, a CNN with multiple input that can simultaneously learn 2-axis or 3-axis acceleration signals is suggested. In addition, by analyzing how the accuracy of the network is affected by number of classes and length of input data, which is related to delay of classification, the appropriate network can be selected according to the application. The proposed real-time road surface classification algorithm is expected to be utilized with various vehicle electronic control systems and makes a contribution to improving vehicle performance.

Low-Cost Road-Surface Classification System Based on Self-Organizing Maps

Expanding the performance and autonomous-decision capability of driver-assistance systems is critical in today’s automotive engineering industry to help drivers and reduce accident incidence. It is essential to provide vehicles with the necessary perception systems, but without creating a prohibitively expensive product. In this area, the continuous and precise estimation of a road surface on which a vehicle moves is vital for many systems. This paper proposes a low-cost approach to solve this issue. The developed algorithm resorts to analysis of vibrations generated by the tyre-rolling movement to classify road surfaces, which allows for optimizing vehicular-safety-system performance. The signal is analyzed by means of machine-learning techniques, and the classification and estimation of the surface are carried out with the use of a self-organizing-map (SOM) algorithm. Real recordings of the vibration produced by tyre rolling on six different types of surface were used to generate the model. The efficiency of the proposed model (88.54%) and its speed of execution were compared with those of other classifiers in order to evaluate its performance.