Vehicle Speed Prediction Research Articles

Real-time energy management for fuel cell electric vehicle using speed prediction-based model predictive control considering performance degradation

Due to the poor dynamic response ability of the fuel cell, the battery is normally applied to integrate with fuel cell to configure the hybrid power system in electric vehicles. In this paper, a vehicle speed prediction model predictive control (SP-MPC) energy management strategy is developed for the hybrid power system in fuel cell electric vehicles. The main principle of the proposed SP-MPC is that the future vehicle total power demand is forecasted via the Markov speed predictor and imported into the energy management system response prediction model to improve the control performance by more accurate disturbance description. The objective function is set for equivalent hydrogen consumption minimization and fuel cell degradation inhibition. As a contrast, the normal MPC strategy, the speed prediction dynamic programming (SP-DP) strategy and the DP offline strategy are formulated. Comparing with the normal MPC strategy, the SP-MPC strategy has a 3.74% reduction in the total operation cost under MANHATTAN condition. The SP-MPC strategy also has a 1.39% reduction in the total operation cost than the SP-DP strategy. Moreover, two scenarios are introduced with different disturbance prediction accuracy to verify the influences of the prediction inaccuracy on the SP-MPC and SP-DP results. For SP-DP strategy, the total operation cost under actual forecast scenario has increased by 5.03% compared with the perfect forecast scenario. The similar result can be seen in the SP-MPC, but the increase between perfect and actual forecast scenario is only 1.02%, which indicates a better robustness to the disturbance prediction inaccuracy compared with the SP-DP strategy. A DSP hardware in loop (HIL) test is conducted for real-time performance verification of the proposed SP-MPC.

Energy Management Strategy of a Hybrid Power System Based on V2X Vehicle Speed Prediction.

Energy consumption in vehicle driving is greatly influenced by traffic scenarios, and the intelligent traffic system (ITS) has a key role in solving the real-time optimal control of hybrid vehicles. To this end, a new energy management control strategy based on vehicle-to-everything (V2X) communication for vehicle speed prediction was proposed to dynamically adjust the engine and motor power output according to the traffic conditions. This study is based on intelligent network connectivity technology to obtain forward traffic state data and use a deep learning algorithm to model vehicle speed prediction using the traffic state data. The energy economy function was modeled using the MATLAB/Sinumlink platform and validated with a plug-in hybrid vehicle model simulation. The results indicate that the proposed strategy improves the vehicle energy economy by 13.02% and reduces CO2 emissions by 16.04% under real vehicle driving conditions, compared with the conventional logic threshold-based control strategy.

Velocity Prediction Based on Vehicle Lateral Risk Assessment and Traffic Flow: A Brief Review and Application Examples

Forecasting future driving conditions such as acceleration, velocity, and driver behaviors can greatly contribute to safety, mobility, and sustainability issues in the development of new energy vehicles (NEVs). In this brief, a review of existing velocity prediction techniques is studied from the perspective of traffic flow and vehicle lateral dynamics for the first time. A classification framework for velocity prediction in NEVs is presented where various state-of-the-art approaches are put forward. Firstly, we investigate road traffic flow models, under which a driving-scenario-based assessment is introduced. Secondly, vehicle speed prediction methods for NEVs are given where an extensive discussion on traffic flow model classification based on traffic big data and artificial intelligence is carried out. Thirdly, the influence of vehicle lateral dynamics and correlation control methods for vehicle speed prediction are reviewed. Suitable applications of each approach are presented according to their characteristics. Future trends and questions in the development of NEVs from different angles are discussed. Finally, different from existing review papers, we introduce application examples, demonstrating the potential applications of the highlighted concepts in next-generation intelligent transportation systems. To sum up, this review not only gives the first comprehensive analysis and review of road traffic network, vehicle handling stability, and velocity prediction strategies, but also indicates possible applications of each method to prospective designers, where researchers and scholars can better choose the right method on velocity prediction in the development of NEVs.

Disturbance prediction-based enhanced stochastic model predictive control for hydrogen supply and circulating of vehicular fuel cells

Hydrogen supply and circulating in vehicular fuel cells is crucial for their output capability and lifetime. In this article, an enhanced multiple-input multiple-output (MIMO) model predictive control (MPC) scheme is proposed for hydrogen regulation based on vehicle speed-induced fuel cell current disturbance stochastic prediction. The Markov exponential smoothing law is first developed for the vehicle speed prediction. The forecasted fuel cell power demand is obtained through vehicle dynamics model and rule-based energy management to release the predictive stack current regarding as the disturbance of hydrogen control system. The discrete predicted current sequence is with stochastic features and typed into the predictive model of MPC which is on longer the length of control horizon. Two case studies are presented to discuss the influence of different speed sampling times on the hydrogen regulation result under the proposed enhanced MPC. The enhanced MPC has a better performance than the traditional MPC, and the control RMSE of which can be reduced by 44.09% in case 1 and 69.78% in case 2 during automotive driving cycles. A dSPACE MicroAutoBox hardware in loop (HIL) experiment was conducted and the results well matched with the simulation which has verified the real-time performance of the enhanced MPC scheme.

Eco-Driving of Connected and Autonomous Vehicles with Sequence-to-Sequence Prediction of Target Vehicle Velocity

The Eco-Driving control problem seeks to perform fuel efficient speed planning for a Connected and Autonomous Vehicle (CAV) that can exploit information available from advanced mapping, and from Vehicle-to-Everything (V2X) communication. The ability of an Eco-Driving strategy to adapt in real time to variable traffic scenarios where surrounding vehicles can be either connected or unconnected is critical for further development and deployment of this technology in the transportation sector. In this work, the Eco-Driving strategy, formulated as a receding-horizon optimal control problem, is integrated with a target vehicle speed prediction model and solved via Dynamic Programming (DP) to determine the optimal speed trajectory in the presence of a human-driven target vehicle. An encoder-decoder architecture analyzes the patterns in the target vehicle velocity recorded over a historic window using a Gated-Recurrent-Unit (GRU) based encoder and generates an estimate of the future velocity trajectory using the GRU based decoder. A sensitivity study is done to analyze the effect of the historical and prediction windows on the accuracy of the velocity predictor. The proposed Eco-Driving controller is evaluated through microscopic simulations using a traffic simulator.

Eco-Driving of Connected and Automated Vehicle With Preceding Driver Behavior Prediction

Abstract The development of vehicle connectivity and autonomy in the ground transportation sector is not only able to enhance traffic safety and driving comfort as well as fuel economy. This study presents a receding-horizon optimization-based control strategy integrated with the preceding vehicle speed prediction model to achieve an eco-driving strategy for connected and automated vehicles (CAVs). In the real traffic scenario where the CAV follows the preceding vehicle on the road, a gated recurrent unit (GRU) network is used to predict the behavior of the preceding vehicle by utilizing the historical inter-vehicle information collected through on-board sensors. Then, a nonlinear model predictive control (NMPC) algorithm is adopted for CAV to minimize the accumulated fuel consumption within the preview horizon. The NMPC approach solves the fuel-optimal speed profile of the CAV, considering a predicted short-term speed preview of the preceding vehicle. With the awareness of the preview speed conditions, the fuel consumption of the CAV is reduced by avoiding unnecessary braking and acceleration, especially during transient traffic conditions. The Pareto front framework is used to examine a trade-off between the vehicle speed prediction accuracy, computational burden, and the fuel consumption of the CAV in the proposed GRU-NMPC design. To analyze the effectiveness of the GRU-NMPC design, adaptive cruise control with constant time headway policy (ACC-CTH) is adopted as a benchmark control design. Comparison results show significant fuel economy improvement of the proposed design and expose possible fuel benefits from vehicle autonomy and sensor fusion technology.

Combined Prediction for Vehicle Speed with Fixed Route

Achieving accurate speed prediction provides the most critical support parameter for high-level energy management of plug-in hybrid electric vehicles. Nowadays, people often drive a vehicle on fixed routes in their daily travels and accurate speed predictions of these routes are possible with random prediction and machine learning, but the prediction accuracy still needs to be improved. The prediction accuracy of traditional prediction algorithms is difficult to further improve after reaching a certain accuracy; problems, such as over fitting, occur in the process of improving prediction accuracy. The combined prediction model proposed in this paper can abandon the transitional dependence on a single prediction. By combining the two prediction algorithms, the fusion of prediction performance is achieved, the limit of the single prediction performance is crossed, and the goal of improving vehicle speed prediction performance is achieved. In this paper, an extraction method suitable for fixed route vehicle speed is designed. The application of Markov and back propagation (BP) neural network in predictions is introduced. Three new combined prediction methods, all named Markov and BP Neural Network (MBNN) combined prediction algorithm, are proposed, which make full use of the advantages of Markov and BP neural network algorithms. Finally, the comparison among the prediction methods has been carried out. The results show that the three MBNN models have improved by about 19%, 28%, and 29% compared with the Markov prediction model, which has better performance in the single prediction models. Overall, the MBNN combined prediction models can improve the prediction accuracy by 25.3% on average, which provides important support for the possible optimization of plug-in hybrid electric vehicle energy consumption.

Long-Term Vehicle Speed Prediction via Historical Traffic Data Analysis for Improved Energy Efficiency of Connected Electric Vehicles

Connected and automated vehicles (CAVs) are expected to provide enhanced safety, mobility, and energy efficiency. While abundant evidence has been accumulated showing substantial energy saving potentials of CAVs through eco-driving, traffic condition prediction has remained to be the main challenge in capitalizing the gains. The coupled power and thermal subsystems of CAVs necessitate the use of different speed preview windows for effective and integrated power and thermal management. Real-time vehicle-to-infrastructure (V2I) communications can provide an accurate speed prediction over a short prediction horizon (e.g., 30 s to 60 s), but not for a long range (e.g., over 180 s). Therefore, advanced approaches are required to develop detailed speed prediction for robust optimization-based energy management of CAVs. This paper presents an integrated speed prediction framework based on historical traffic data classification and real-time V2I communications for efficient energy management of electrified CAVs. The proposed framework provides multi-range speed predictions with different fidelity over short and long horizons. The proposed multi-range speed prediction is integrated with an economic model predictive control (MPC) strategy for the battery thermal management (BTM) of connected and automated electric vehicles (EVs). The simulation results over real-world urban driving cycles confirm the enhanced prediction performance of the proposed data classification strategy over a long prediction horizon. Despite the uncertainty in long-range CAVs’ speed predictions, the vehicle-level simulation results show that 14% and 19% energy savings can be accumulated sequentially through eco-driving and BTM optimization (eco-cooling), respectively, when compared with normal driving (i.e., human driver) and conventional BTM strategy.

Investigating long-term vehicle speed prediction based on GA-BP algorithms and the road-traffic environment

Investigating long-term vehicle speed prediction based on GA-BP algorithms and the road-traffic environment

An improved extreme gradient boosting approach to vehicle speed prediction for construction simulation of earthwork

Construction simulation is an effective tool to provide schedule plans. Vehicle speed is one of the most significant factors in earthwork construction simulation. However, neglecting the strong correlation with contextual factors, random distribution methods will lead to inaccurate prediction of vehicle speed. To address such issues, an improved extreme gradient boosting (XGBoost) approach to vehicle speed prediction is proposed for earthwork construction simulation. Firstly, to improve the global searching ability, an improved grey wolf optimization algorithm (IGWO) is put forward. Secondly, XGBoost is optimized by IGWO to construct an IGWO-XGBoost model. Then, the prediction model is embedded in the earthwork construction simulation model. The case study proves that the simulation results of the proposed method are more consistent with an actual construction schedule. It is expected that the vehicle speed prediction embedded into a simulation program facilitated an accurate development of schedule plan, thereby improving the efficiency of construction management.

Hierarchical model predictive control via deep learning vehicle speed predictions for oxygen stoichiometry regulation of fuel cells

Fuel cells are a promising solution for increasing driving range of electric vehicles. To guarantee the high efficiency and stable operation of fuel cells, the effective regulation of oxygen and hydrogen reactants is needed. During varied driving conditions, in which the drastic current demand changes may result in insufficient reactant, the fuel cell can even be damaged. In this paper, a hierarchical model predictive control (HMPC) strategy is proposed based on the deep learning for vehicle speed predictions. Speed variation predictions are considered by the MPC to regulate the air supply system and preventing oxygen starvation in the fuel cell stack. The problems of fuel cell oxygen stoichiometry control are, first, stated with the preliminary energy management description as well as with the limitations of the traditional MPC. The deep learning Back Propagation (BP) neural network was then designed as the first-level predictor to forecast the vehicle speed by training with integrated driving cycles, and predict the fuel cell current based on its cathode flow model. Subsequently, the second-level MPC used the current disturbance prediction and filling is introduced to regulate the oxygen mass flow. The simulation results for the MANHATTAN drive cycle demonstrated that the root mean square error (RMSE) for speed predictions was less than 1 km/h. Compared with the conventional MPC, HMPC offers better robustness in the face of influence from current changes induced by speed-variations, and the RMSE of the oxygen stoichiometry control was decreased by 63.37%.

Energy optimization of multi-mode coupling drive plug-in hybrid electric vehicles based on speed prediction

Abstract By integrating the functions of centralized drive and distributed drive into a series-parallel hybrid system, the multi-mode coupling drive system can greatly improve the fuel economy of a plug-in hybrid electric vehicle (PHEV). However, some simple energy management strategies do not give full play to the advantages of the drive system. In order to get better fuel economy, after the system working principle analysis and modeling, a vehicle speed prediction model combining Markov and BP neural network algorithm was developed to predict the speed of the next 5s, and an adaptive equivalent consumption minimum strategy (AECMS) based on the combined vehicle speed prediction is proposed to optimize the drive modes selection and power distribution. The vehicle speed prediction accuracy was verified by the actual vehicle road test and the energy management effect was verified by the simulation. The research results show that, the prediction accuracy of the combined vehicle speed prediction can be improved by 27.9% compared with the ordinary single speed prediction, and the proposed control strategy improves the energy consumption of 3.7% for the PHEV under the same driving cycle condition when compared with the rule-based optimization strategy.

A Novel Approach for Vehicle Type Classification and Speed Prediction Using Deep Learning

In Vehicles automation system, Classification and speed detection has become an important research challenge in road safety and intelligent transportation system. Many systems like pattern recognition, image processing and machine learning technologies have overcome numerous hindrances to accomplish this goal. In this paper, we demonstrate a speed detection system and vehicle type classification founded on deep learning technique. Moreover, we built up Modular Neural Network (MNN) architecture, advancement algorithm and its parameters are acquired by training dataset. This integrated part of a system will enhance to finding in automation detection and traffic flow management system.

Hierarchical MPC for Robust Eco-Cooling of Connected and Automated Vehicles and Its Application to Electric Vehicle Battery Thermal Management

Connected and autonomous vehicles (CAVs) have situational awareness that can be exploited for optimal power and thermal management. In this article, we develop a hierarchical model predictive control (H-MPC) strategy for eco-cooling of CAVs, which reduces energy consumption through real-time prediction and multi-timescale and multi-layer optimization. The application of the proposed H-MPC is studied for battery thermal and energy management of an electric vehicle (EV). Our H-MPC approach addresses the uncertainty in the long-term preview of the vehicle speed through robust constraint handling to prevent constraint violation. The simulation results show that compared with a conventional battery thermal management (BTM) strategy, the proposed robust H-MPC saves the battery energy by up to 5.4% under the uncertainties in the long-term vehicle speed predictions in an urban CAV operation scenario.

Prediction of vehicle energy consumption on a planned route based on speed features forecasting

The prediction of energy consumption is the primary goal of an intelligent energy management system (IEMS). Based on the actual road–traffic conditions, the vehicle energy consumption on the whole planned path can be predicted online by road condition recognition or speed sequence prediction. Because the speed sequence prediction required by the latter cannot accurately reflect the real dynamic characteristics of vehicle speed such as acceleration and deceleration changes due to the random factors of traffic or human beings, which will greatly affect the predicting accuracy, especially on the urban road with complex working conditions. Therefore, based on the analysis of the cumulative relationship between vehicle speed characteristics and energy consumption, this study proposes a prediction method of vehicle driving energy consumption based on the statistical characteristics of vehicle speed, regardless of the accuracy of the prediction of vehicle speed sequence, including the establishment of a long-term vehicle speed feature prediction model and energy consumption prediction model by BP and SVM algorithms. Finally, its rationality is validated based on the authentic data with an accuracy of about 95%, significantly improved compared with that based on long-term vehicle speed prediction.

An Improved Car-Following Speed Model considering Speed of the Lead Vehicle, Vehicle Spacing, and Driver’s Sensitivity to Them

This paper introduces an improved car-following speed (CFS) model that simultaneously considers speed of the lead vehicle, vehicle spacing, and driver’s sensitivity to them. Specifically, the proposed model extends the Helbing-Tilch model and Yang et al. model developed based on the principle of grey relational analysis where vehicle spacing is considered as the primary factor contributing to car-following speed choices. A computational experiment is conducted for model calibration using vehicle spacing, speed, and acceleration data derived from vehicle trajectory data of the Next Generation Simulation (NGSIM) project sponsored by the Federal Highway Administration (FHWA). It shows that speed of the lead vehicle and vehicle spacing significantly affect speed of the lag vehicle. Further, model validation is carried out using an independent NGSIM dataset by comparing vehicle speed predictions made by the calibrated CFS model with Helbing-Tilch model and Yang et al. model as benchmarks. Compared with speed prediction results of the benchmark models, mean relative errors, root mean square errors, and equal coefficient of speed predictions of the CFS model have reduced by 72.41% and 61.85%, 70.14% and 57.99%, and 33.15% and 14.48%, respectively. The findings of model validation reveal that the CFS model could improve the accuracy of speed predictions in the car-following process.

A-EMCS for PHEV based on real-time driving cycle prediction and personalized travel characteristics.

Energy management plays an important role in improving the fuel economy of plug-in hybrid electric vehicles (PHEV). Therefore, this paper proposes an improved adaptive equivalent consumption minimization strategy (A-ECMS) based on long-term target driving cycle recognition and short-term vehicle speed prediction, and adapt it to personalized travel characteristics. Two main contributions have been made to distinguish our work from exiting research. Firstly, online long-term driving cycle recognition and short-term speed prediction are considered simultaneously to adjust the equivalent factor (EF). Secondly, the dynamic programming (DP) algorithm is applied to the offline energy optimization process of A-ECMS based on typical driving cycles constructed according to personalized travel characteristics. The improved A-ECMS can optimize EF based on mileage, SOC, long-term driving cycle and real-time vehicle speed. In the offline part, typical driving cycles of a specific driver is constructed by analyzing personalized travel characteristics in the historical driving data, and optimal SOC consumption under each typical driving cycle is optimized by DP. In the online part, the SOC reference trajectory is obtained by recognizing the target driving cycle from Intelligent Traffic System, and short-term vehicle speed is predicted by Nonlinear Auto-Regressive (NAR) neural network which both adjust EF together. Simulation results show that compared with CD-CS, the fuel consumption of A-ECMS proposed in the paper is reduced by 8.7%.

Forecasting ECMS for Hybrid Electric Vehicles

This paper aims to propose a real-time suitable method to tackle the problem of energy and pollutant management of Hybrid Electric Vehicles. Methods proposed in the literature often limit the underlying optimal control problem to single-instant optimizations (Paganelli, 2002) due to the difficulty of taking future into account and to onboard limited computational resources. The point of the present paper is to propose an online oriented method based on a long-term vehicle speed prediction, using cartographic information such as speed limitation, road curvature, traffic and road signs. Pontryagin Maximum Principle applied on this speed prediction signal allows to convert the optimal control problem into a root-finding problem. This problem is solved using a Pegasus algorithm initialized by a black-box method trained offline, allowing high computational efficiency. The results are near-optimal and significantly better than classical methods: in the real-driving trip used in this paper, forecasting-ECMS showed a consumption 1.1% better and NOx emissions 4.4% better than a SOC-feedback adaptive-ECMS.

Study of noise level at roundabouts in Maminasata area

The rapid growth of a country affects one of many fields, such as transportation, which is important for development and as public facilities. This research was conducted at the Mandai Roundabout, Riburane Roundabout, and the Samata Roundabout. This study aims to analyze the noise level at 3 observation points, as well as noise prediction by using the CoRTN method (Traffic Noise Calculation) based on Vissim Software in 2019-2023. Data collected for 12 hours from 07.00 until 19.00 by taking samples for 10 minutes per hour using the Sound Level Meter (SLM) type TM-103. While for the prediction results, the number of vehicles and vehicle speed are used. For vehicle speed predictions, the number of vehicles are added by 7% per year then run the program Vissim. The results are divided into 3 locations, the Mandai Roundabout about 76.21 dB; Riburane Roundabout about 75.82 dB; and the Samata Roundabout about 80.09 dB where the noise level is higher than the standard from government, Minister of Environment No.48 on 1996 which stated the standard for noise level in trading and service area is 70 dB. The estimated result based on the CoRTN model on the roundabout in the Maminasata area using the Leq formula is 73.47 dB for the Mandai Roundabout; 70.07 dB for Riburane Roundabout; and 73.40 dB for the Samata Roundabout. There has been a difference in predicted results from 2019-2023. In 2019 there has been a difference of about ≥ 3 dB, which is 4.1 dB at the Mandai Roundabout so that improvements need to be made to this region.

Fast Numerical Powertrain Optimization Strategy for Connected Hybrid Electric Vehicles

Connected vehicle (CV) technology allows traffic information sharing that can be utilized to improve fuel benefits of hybrid electric vehicles (HEVs). However, there are challenges from the powertrain optimization perspective. First, optimizing powertrain operations is computational heavy due to the nonlinearities, constraints, and high dimensionality of the problem, especially with long optimization time horizon. Secondly, a slow powertrain optimization means the solution may not be optimal anymore at current time if the traffic states change. In this paper, a fast, near global-optimal, and practical HEV powertrain optimization utilizing vehicle speed prediction in CV environment is systematically formulated and solved. First, the minimum fuel rate and battery state-of-charge rate are calculated for different engine and battery power-split ratios. Then, the nonlinear minimum fuel rate and battery state-of-charge rate are piecewise-linearized by introducing dimensionless variables. The engine operating range, engine dynamics, and battery charge-sustaining constraint are represented by the dimensionless variables and treated as linear constraints. This transformation exploits the problem's structure, known as Separable Programming, which is solved efficiently as a large-dimension constrained linear problem. Fast optimization allows utilization of repeated speed predictions to maintain prediction accuracy. Results show comparable fuel economy with Dynamic Programming with significantly less computation time. Average fuel savings of 4.0% and 10.4% over Pontryagin's Minimum Principle and Rule-Based optimization methods are observed. Experimental results show the feasibility of the optimized engine operating points with fuel benefits over the rule-based method. Simulations with vehicle speed prediction and limited Gaussian uncertainties to emulate CV settings also show satisfactory fuel benefits.