Apparatus for predicting friction coefficient of road surface and method thereof
An apparatus and method for predicting a friction coefficient of a road surface are disclosed. The apparatus includes a microphone that obtains a sound signal around a tire mounted on a vehicle, and a controller that estimates a state and a type of the road surface and a degree of tire wear corresponding to the sound signal around the tire based on a first deep learning model, estimates a peak adjustment factor and an initial inclination adjustment factor of a friction coefficient curve corresponding to the state and the type of the road surface and the degree of tire wear based on a second deep learning model, and predicts the friction coefficient based on the peak adjustment factor and the initial inclination adjustment factor of the friction coefficient curve.
1. An apparatus for predicting a friction coefficient of a road surface, the apparatus comprising:
a microphone to obtain a sound signal around a tire mounted on a vehicle; and
a controller configured to:
estimate a state and a type of the road surface and a degree of tire wear corresponding to the sound signal around the tire based on a first deep learning model,
estimate a peak adjustment factor and an initial inclination adjustment factor of a friction coefficient curve corresponding to the state and the type of the road surface and the degree of tire wear based on a second deep learning model, and
predict the friction coefficient based on the peak adjustment factor and the initial inclination adjustment factor of the friction coefficient curve.
2. The apparatus of claim 1 , wherein the controller is further configured to:
convert the sound signal around the tire into an image, and
input the image into the first deep learning model to estimate the state and the type of the road surface and the degree of tire wear.
3. The apparatus of claim 2 , wherein the controller is further configured to:
divide the sound signal around the tire obtained through the microphone by a unit of a preset time,
convert the divided sound signal into a first image, and
normalize a region of interest in the first image to a second image of a preset size.
4. The apparatus of claim 3 , wherein the controller is configured to convert the divided sound signal to the first image based on a continuous wavelet transform (CWT) algorithm.
5. The apparatus of claim 1 , wherein the controller is further configured to generate a surface image of the tire corresponding to the degree of tire wear.
6. The apparatus of claim 5 , wherein the controller is configured to estimate the peak adjustment factor and the initial inclination adjustment factor of the friction coefficient curve corresponding to the state and the type of the road surface and the surface image of the tire based on the second deep learning model.
7. The apparatus of claim 1 , wherein the controller is further configured to:
generate the friction coefficient curve based on the peak adjustment factor and the initial inclination adjustment factor of the friction coefficient curve, and
predict a maximum friction coefficient on the friction coefficient curve.
8. The apparatus of claim 1 , wherein the state of the road surface includes at least one of a dry state, a wet state, a snow state, and an ice state.
9. The apparatus of claim 1 , wherein the type of the road surface includes at least one of a first asphalt, a second asphalt, a first concrete, a second concrete, a lateral groove, and a longitudinal groove.
10. The apparatus of claim 1 , wherein the microphone is mounted in front of a wheel housing arranged on a rear wheel of the vehicle.
11. A method of predicting a friction coefficient of a road surface, the method comprising:
acquiring, by a microphone, a sound signal around a tire mounted on a vehicle;
estimating, by a controller, a state and a type of the road surface and a degree of tire wear corresponding to the sound signal around the tire based on a first deep learning model;
estimating, by the controller, a peak adjustment factor and an initial inclination adjustment factor of a friction coefficient curve corresponding to the state and the type of the road surface and the degree of tire wear based on a second deep learning model; and
predicting, by the controller, the friction coefficient based on the peak adjustment factor and the initial inclination adjustment factor of the friction coefficient curve.
12. The method of claim 11 , wherein the estimating of the state and the type of the road surface and the degree of the tire wear includes:
converting, by the controller, the sound signal around the tire into an image; and
inputting, by the controller, the image into the first deep learning model to estimate the state and the type of the road surface and the degree of tire wear.
13. The method of claim 12 , wherein the converting of the sound signal around the tire to the image includes:
dividing, by the controller, the sound signal around the tire obtained through the microphone by a unit of a preset time;
converting, by the controller, the divided sound signal into a first image; and
normalizing, by the controller, a region of interest in the first image to a second image of a preset size.
14. The method of claim 13 , wherein the converting of the divided sound signal into the first image includes:
converting, by the controller, the divided sound signal to the first image based on a continuous wavelet transform (CWT) algorithm.
15. The method of claim 11 , wherein the estimating of the peak adjustment factor and the initial inclination adjustment factor includes:
generating, by the controller, a surface image of the tire corresponding to the degree of tire wear.
16. The method of claim 15 , wherein the predicting of the friction coefficient includes:
estimating, by the controller, the peak adjustment factor and the initial inclination adjustment factor of the friction coefficient curve corresponding to the state and the type of the road surface and the surface image of the tire based on the second deep learning model.
17. The method of claim 11 , wherein the predicting of the friction coefficient includes:
generating, by the controller, the friction coefficient curve based on the peak adjustment factor and the initial inclination adjustment factor of the friction coefficient curve; and
predicting, by the controller, a maximum friction coefficient on the friction coefficient curve.
18. The method of claim 11 , wherein the state of the road surface includes at least one of a dry state, a wet state, a snow state, and an ice state.
19. The method of claim 11 , wherein the type of the road surface includes at least one of a first asphalt, a second asphalt, a first concrete, a second concrete, a lateral groove, and a longitudinal groove.
20. The method of claim 11 , wherein the microphone is mounted in front of a wheel housing arranged on a rear wheel of the vehicle.