Dual-Input and Multi-Channel Convolutional Neural Network Model for Vehicle Speed Prediction
With the development of technology, speed prediction has become an important part of intelligent vehicle control strategies. However, the time-varying and nonlinear nature of vehicle speed increases the complexity and difficulty of prediction. Therefore, a CNN-based neural network architecture with...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7767 |
| _version_ | 1827675367860600832 |
|---|---|
| author | Jiaming Xing Liang Chu Chong Guo Shilin Pu Zhuoran Hou |
| author_facet | Jiaming Xing Liang Chu Chong Guo Shilin Pu Zhuoran Hou |
| author_sort | Jiaming Xing |
| collection | DOAJ |
| description | With the development of technology, speed prediction has become an important part of intelligent vehicle control strategies. However, the time-varying and nonlinear nature of vehicle speed increases the complexity and difficulty of prediction. Therefore, a CNN-based neural network architecture with two channel input (DICNN) is proposed in this paper. With two inputs and four channels, DICNN can predict the speed changes in the next 5 s by extracting the temporal information of 10 vehicle signals and the driver’s intention. The prediction performances of DICNN are firstly examined. The best RMSE, MAE, ME and R<sup>2</sup> are obtained compared with a Markov chain combined with Monte Carlo (MCMC) simulation, a support vector machine (SVM) and a single input CNN (SICNN). Secondly, equivalent fuel consumption minimization strategies (ECMS) combining different vehicle speed prediction methods are constructed. After verification by simulation, the equivalent fuel consumption of the simulation increases by only 4.89% compared with dynamic-programming-based energy management strategy and decreased by 5.40% compared with the speed prediction method with low accuracy. |
| first_indexed | 2024-03-10T05:04:07Z |
| format | Article |
| id | doaj.art-680460ca438a4f3a9312a0eeda9921e1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:04:07Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-680460ca438a4f3a9312a0eeda9921e12023-11-23T01:29:33ZengMDPI AGSensors1424-82202021-11-012122776710.3390/s21227767Dual-Input and Multi-Channel Convolutional Neural Network Model for Vehicle Speed PredictionJiaming Xing0Liang Chu1Chong Guo2Shilin Pu3Zhuoran Hou4State Key Laboratory of Automotive Dynamic Simulation and Control, Jilin University, Changchun 130022, ChinaState Key Laboratory of Automotive Dynamic Simulation and Control, Jilin University, Changchun 130022, ChinaState Key Laboratory of Automotive Dynamic Simulation and Control, Jilin University, Changchun 130022, ChinaState Key Laboratory of Automotive Dynamic Simulation and Control, Jilin University, Changchun 130022, ChinaState Key Laboratory of Automotive Dynamic Simulation and Control, Jilin University, Changchun 130022, ChinaWith the development of technology, speed prediction has become an important part of intelligent vehicle control strategies. However, the time-varying and nonlinear nature of vehicle speed increases the complexity and difficulty of prediction. Therefore, a CNN-based neural network architecture with two channel input (DICNN) is proposed in this paper. With two inputs and four channels, DICNN can predict the speed changes in the next 5 s by extracting the temporal information of 10 vehicle signals and the driver’s intention. The prediction performances of DICNN are firstly examined. The best RMSE, MAE, ME and R<sup>2</sup> are obtained compared with a Markov chain combined with Monte Carlo (MCMC) simulation, a support vector machine (SVM) and a single input CNN (SICNN). Secondly, equivalent fuel consumption minimization strategies (ECMS) combining different vehicle speed prediction methods are constructed. After verification by simulation, the equivalent fuel consumption of the simulation increases by only 4.89% compared with dynamic-programming-based energy management strategy and decreased by 5.40% compared with the speed prediction method with low accuracy.https://www.mdpi.com/1424-8220/21/22/7767speed predictionvehicle signalsCNNECMS |
| spellingShingle | Jiaming Xing Liang Chu Chong Guo Shilin Pu Zhuoran Hou Dual-Input and Multi-Channel Convolutional Neural Network Model for Vehicle Speed Prediction Sensors speed prediction vehicle signals CNN ECMS |
| title | Dual-Input and Multi-Channel Convolutional Neural Network Model for Vehicle Speed Prediction |
| title_full | Dual-Input and Multi-Channel Convolutional Neural Network Model for Vehicle Speed Prediction |
| title_fullStr | Dual-Input and Multi-Channel Convolutional Neural Network Model for Vehicle Speed Prediction |
| title_full_unstemmed | Dual-Input and Multi-Channel Convolutional Neural Network Model for Vehicle Speed Prediction |
| title_short | Dual-Input and Multi-Channel Convolutional Neural Network Model for Vehicle Speed Prediction |
| title_sort | dual input and multi channel convolutional neural network model for vehicle speed prediction |
| topic | speed prediction vehicle signals CNN ECMS |
| url | https://www.mdpi.com/1424-8220/21/22/7767 |
| work_keys_str_mv | AT jiamingxing dualinputandmultichannelconvolutionalneuralnetworkmodelforvehiclespeedprediction AT liangchu dualinputandmultichannelconvolutionalneuralnetworkmodelforvehiclespeedprediction AT chongguo dualinputandmultichannelconvolutionalneuralnetworkmodelforvehiclespeedprediction AT shilinpu dualinputandmultichannelconvolutionalneuralnetworkmodelforvehiclespeedprediction AT zhuoranhou dualinputandmultichannelconvolutionalneuralnetworkmodelforvehiclespeedprediction |