A Machine Learning Model for Predicting Noise Limits of Motor Vehicles in UNECE R51 Regulations
It is vital to greatly reduce traffic noises emitted by motor vehicles during accelerating through determining limit values of noises and further improve technical specifications and comforts of these automobiles for automotive manufacturers. The United Nations Economic Commission for Europe (UNECE)...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/22/8092 |
id |
doaj-acb1aedafec84a36b13fdb4d2b322f39 |
---|---|
record_format |
Article |
spelling |
doaj-acb1aedafec84a36b13fdb4d2b322f392020-11-25T04:06:16ZengMDPI AGApplied Sciences2076-34172020-11-01108092809210.3390/app10228092A Machine Learning Model for Predicting Noise Limits of Motor Vehicles in UNECE R51 RegulationsGangping Tan0Qingshuang Chen1Changyin Li2Richard (Chunhui) Yang3School of Mechanical and Electrical Engineering, Nanchang University, Nanchang 330031, ChinaThe Jiangxi Province Key Laboratory of Vehicle Noise and Vibration, Nanchang 330000, ChinaJiangling Motors Import & Export, Nanchang 330000, ChinaSchool of Engineering, Western Sydney University, Kingswood, NSW 2747, AustraliaIt is vital to greatly reduce traffic noises emitted by motor vehicles during accelerating through determining limit values of noises and further improve technical specifications and comforts of these automobiles for automotive manufacturers. The United Nations Economic Commission for Europe (UNECE) R51 regulations define the noise limits for all vehicle categories, which are kept updating, and these noise limits are implemented by governments all over the world; however, the automobile manufactures need to estimate future values of noise limits for developing their next-generation vehicles. In this study, a machine learning model using the back-propagation neural network (BPNN) approach is developed to determine noise limits of a vehicle during accelerating by using historic data and predict its noise limits for future revisions of the UNECE R51 regulations. The proposed prediction model adopts the Levenberg-Marquardt algorithm which can automatically adapt its learning rate to train the model with input data, and at the same time randomly select the validation data and test data to verify the correlation and determine the accuracy of the prediction results. To showcase the proposed prediction model, acceleration noise limits from six historic data are used for training the model, and the noise limits at the seventh version can be predicted and validated. As the results achieve a required accuracy, vehicle noise limits in the next revision as the future eighth version can be predicted based on these data. It can be found that the obtained prediction results are much close to those noise limits defined in current regulations and negative error ratios are reduced significantly, compared to those values obtained using a quadratic regression model. As a result, the proposed BPNN model can predict future noise limits for the next revision of the UNECE R51automotive noise limit regulations.https://www.mdpi.com/2076-3417/10/22/8092UNECE R51automotive noise limitsmachine learningBPNNLevenberg-Marquardt algorithmquadratic regression |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Gangping Tan Qingshuang Chen Changyin Li Richard (Chunhui) Yang |
spellingShingle |
Gangping Tan Qingshuang Chen Changyin Li Richard (Chunhui) Yang A Machine Learning Model for Predicting Noise Limits of Motor Vehicles in UNECE R51 Regulations Applied Sciences UNECE R51 automotive noise limits machine learning BPNN Levenberg-Marquardt algorithm quadratic regression |
author_facet |
Gangping Tan Qingshuang Chen Changyin Li Richard (Chunhui) Yang |
author_sort |
Gangping Tan |
title |
A Machine Learning Model for Predicting Noise Limits of Motor Vehicles in UNECE R51 Regulations |
title_short |
A Machine Learning Model for Predicting Noise Limits of Motor Vehicles in UNECE R51 Regulations |
title_full |
A Machine Learning Model for Predicting Noise Limits of Motor Vehicles in UNECE R51 Regulations |
title_fullStr |
A Machine Learning Model for Predicting Noise Limits of Motor Vehicles in UNECE R51 Regulations |
title_full_unstemmed |
A Machine Learning Model for Predicting Noise Limits of Motor Vehicles in UNECE R51 Regulations |
title_sort |
machine learning model for predicting noise limits of motor vehicles in unece r51 regulations |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-11-01 |
description |
It is vital to greatly reduce traffic noises emitted by motor vehicles during accelerating through determining limit values of noises and further improve technical specifications and comforts of these automobiles for automotive manufacturers. The United Nations Economic Commission for Europe (UNECE) R51 regulations define the noise limits for all vehicle categories, which are kept updating, and these noise limits are implemented by governments all over the world; however, the automobile manufactures need to estimate future values of noise limits for developing their next-generation vehicles. In this study, a machine learning model using the back-propagation neural network (BPNN) approach is developed to determine noise limits of a vehicle during accelerating by using historic data and predict its noise limits for future revisions of the UNECE R51 regulations. The proposed prediction model adopts the Levenberg-Marquardt algorithm which can automatically adapt its learning rate to train the model with input data, and at the same time randomly select the validation data and test data to verify the correlation and determine the accuracy of the prediction results. To showcase the proposed prediction model, acceleration noise limits from six historic data are used for training the model, and the noise limits at the seventh version can be predicted and validated. As the results achieve a required accuracy, vehicle noise limits in the next revision as the future eighth version can be predicted based on these data. It can be found that the obtained prediction results are much close to those noise limits defined in current regulations and negative error ratios are reduced significantly, compared to those values obtained using a quadratic regression model. As a result, the proposed BPNN model can predict future noise limits for the next revision of the UNECE R51automotive noise limit regulations. |
topic |
UNECE R51 automotive noise limits machine learning BPNN Levenberg-Marquardt algorithm quadratic regression |
url |
https://www.mdpi.com/2076-3417/10/22/8092 |
work_keys_str_mv |
AT gangpingtan amachinelearningmodelforpredictingnoiselimitsofmotorvehiclesinunecer51regulations AT qingshuangchen amachinelearningmodelforpredictingnoiselimitsofmotorvehiclesinunecer51regulations AT changyinli amachinelearningmodelforpredictingnoiselimitsofmotorvehiclesinunecer51regulations AT richardchunhuiyang amachinelearningmodelforpredictingnoiselimitsofmotorvehiclesinunecer51regulations AT gangpingtan machinelearningmodelforpredictingnoiselimitsofmotorvehiclesinunecer51regulations AT qingshuangchen machinelearningmodelforpredictingnoiselimitsofmotorvehiclesinunecer51regulations AT changyinli machinelearningmodelforpredictingnoiselimitsofmotorvehiclesinunecer51regulations AT richardchunhuiyang machinelearningmodelforpredictingnoiselimitsofmotorvehiclesinunecer51regulations |
_version_ |
1724431707609759744 |