Transient Hybrid Electric Vehicle Powertrain Control Based on Iterative Dynamic Programing

2021 ◽  
Vol 144 (2) ◽  
Author(s):  
Qilun Zhu ◽  
Robert Prucka
Keyword(s):  
Machine Learning ◽  
State Space ◽  
Fuel Economy ◽  
Control Policy ◽  
Driving Cycle ◽  
High Fidelity ◽  
Powertrain Control ◽  
Dynamic Programing ◽  
Hybrid Electric ◽  
Fidelity Model

Abstract This research proposes an iterative dynamic programing (IDP) algorithm that generates an optimal supervisory control policy for hybrid electric vehicles (HEVs) considering transient powertrain dynamics. The proposed algorithm tries to solve the “curse of dimensionality” and the “curse of modeling” of conventional dynamic programing (DP). The proposed IDP algorithm iteratively updates the DP formulation using a machine learning-based powertrain model. The machine learning model is recursively trained using the outputs from the driving cycle simulation with a high-fidelity model. Once the reduced model converges to the high-fidelity model accuracy, the resulting control policy yields a 9.1% fuel economy (FE) improvement compared to the baseline nonpredictive rule-based control for the urban dynamometer driving schedule (UDDS) driving cycle. A conventional DP control strategy based on a quasi-static powertrain model and a perfect preview of future power demand yields 14.2% FE improvement. However, the FE improvement reduces to 5.7% when the policy is validated with the high-fidelity model. It is concluded that capturing the transient powertrain dynamics is critical to generating a realistic fuel economy prediction and relevant powertrain control policy. The proposed IDP strategy employs targeted state-space exploration to leverage the improving state trajectory from previous iterations. Compared to conventional fixed state-space sampling methods, this method improves the accuracy of the DP policy against discretization error. It also significantly reduces the computational load of the relatively high number of states of the transient powertrain model.

scholarly journals Reducing Mobile Air Conditioner (MAC) Power Consumption Using Active Cabin-Air-Recirculation in A Plug-In Hybrid Electric Vehicle (PHEV)

2018 ◽  
Vol 9 (4) ◽  
pp. 51 ◽  
Author(s):  
Chengguo Li ◽  
Eli Brewer ◽  
Liem Pham ◽  
Heejung Jung
Keyword(s):  
Air Quality ◽  
Power Consumption ◽  
Electric Vehicle ◽  
Fuel Economy ◽  
Hybrid Electric Vehicle ◽  
Driving Cycle ◽  
Total Power ◽  
Air Conditioner ◽  
Hybrid Electric ◽  
Cabin Air Quality

Air conditioner power consumption accounts for a large fraction of the total power used by hybrid and electric vehicles. This study examined the effects of three different cabin air ventilation settings on mobile air conditioner (MAC) power consumption, such as fresh mode with air conditioner on (ACF), fresh mode with air conditioner off (ACO), and air recirculation mode with air conditioner on (ACR). Tests were carried out for both indoor chassis dynamometer and on-road tests using a 2012 Toyota Prius plug-in hybrid electric vehicle. Real-time power consumption and fuel economy were calculated from On-Board Diagnostic-II (OBD-II) data and compared with results from the carbon balance method. MAC consumed 28.4% of the total vehicle power in ACR mode when tested with the Supplemental Federal Test Procedure (SFTP) SC03 driving cycle on the dynamometer, which was 6.1% less than in ACF mode. On the other hand, ACR and ACF mode did not show significant differences for the less aggressive on-road tests. This is likely due to the significantly lower driving loads experienced in the local driving route compared to the SC03 driving cycle. On-road and SC03 test results suggested that more aggressive driving tends to magnify the effects of the vehicle HVAC (heating, ventilation, and air conditioning) system settings. ACR conditions improved relative fuel economy (or vehicle energy efficiency) to that of ACO conditions by ~20% and ~8% compared to ACF conditions for SC03 and on-road tests, respectively. Furthermore, vehicle cabin air quality was measured and analyzed for the on-road tests. ACR conditions significantly reduced in-cabin particle concentrations, in terms of aerosol diffusion charger signal, by 92% compared to outside ambient conditions. These results indicate that cabin air recirculation is a promising method to improve vehicle fuel economy and improve cabin air quality.

scholarly journals Development and Evaluation of Velocity Predictive Optimal Energy Management Strategies in Intelligent and Connected Hybrid Electric Vehicles

Energies ◽  
2021 ◽  
Vol 14 (18) ◽  
pp. 5713
Author(s):  
Aaron Rabinowitz ◽  
Farhang Motallebi Araghi ◽  
Tushar Gaikwad ◽  
Zachary D. Asher ◽  
Thomas H. Bradley
Keyword(s):  
Energy Management ◽  
Fuel Economy ◽  
Hybrid Electric Vehicle ◽  
High Fidelity ◽  
Energy Management Strategy ◽  
Optimal Energy ◽  
Upper Limit ◽  
Speed Prediction ◽  
Optimal Energy Management ◽  
Hybrid Electric

In this study, a thorough and definitive evaluation of Predictive Optimal Energy Management Strategy (POEMS) applications in connected vehicles using 10 to 20 s predicted velocity is conducted for a Hybrid Electric Vehicle (HEV). The presented methodology includes synchronous datasets gathered in Fort Collins, Colorado using a test vehicle equipped with sensors to measure ego vehicle position and motion and that of surrounding objects as well as receive Infrastructure to Vehicle (I2V) information. These datasets are utilized to compare the effect of different signal categories on prediction fidelity for different prediction horizons within a POEMS framework. Multiple artificial intelligence (AI) and machine learning (ML) algorithms use the collected data to output future vehicle velocity prediction models. The effects of different combinations of signals and different models on prediction fidelity in various prediction windows are explored. All of these combinations are ultimately addressed where the rubber meets the road: fuel economy (FE) enabled from POEMS. FE optimization is performed using Model Predictive Control (MPC) with a Dynamic Programming (DP) optimizer. FE improvements from MPC control at various prediction time horizons are compared to that of full-cycle DP. All FE results are determined using high-fidelity simulations of an Autonomie 2010 Toyota Prius model. The full-cycle DP POEMS provides the theoretical upper limit on fuel economy (FE) improvement achievable with POEMS but is not currently practical for real-world implementation. Perfect prediction MPC (PP-MPC) represents the upper limit of FE improvement practically achievable with POEMS. Real-Prediction MPC (RP-MPC) can provide nearly equivalent FE improvement when used with high-fidelity predictions. Constant-Velocity MPC (CV-MPC) uses a constant speed prediction and serves as a “null” POEMS. Results showed that RP-MPC, enabled by high-fidelity ego future speed prediction, led to significant FE improvement over baseline nearly matching that of PP-MPC.

scholarly journals Support vector machine–based driving cycle recognition for dynamic equivalent fuel consumption minimization strategy with hybrid electric vehicle

2018 ◽  
Vol 10 (11) ◽  
pp. 168781401881102
Author(s):  
QIN Shi ◽  
Duoyang Qiu ◽  
Lin He ◽  
Bing Wu ◽  
Yiming Li
Keyword(s):  
Support Vector Machine ◽  
Fuel Consumption ◽  
Electric Vehicle ◽  
Fuel Economy ◽  
Hybrid Electric Vehicle ◽  
Driving Cycle ◽  
Support Vector ◽  
Equivalent Fuel ◽  
Hybrid Electric ◽  
Equivalent Fuel Consumption

For a great influence on the fuel economy and exhaust, driving cycle recognition is becoming more and more widely used in hybrid electric vehicles. The purpose of this study is to develop a method to identify the type of driving cycle in real time with better accuracy and apply the driving cycle recognition to minimize the fuel consumption with dynamic equivalent fuel consumption minimization strategy. The support vector machine optimized by the particle swarm algorithm is created for building driving cycle recognition model. Furthermore,the influence of the two parameters of window width and window moving velocity on the accuracy is also analyzed in online application. A case study of driving cycle in a medium-sized city is introduced based on collecting four typical driving cycle data in real vehicle test. A series of characteristic parameters are defined and principal component analysis is used for data processing. Finally, the driving cycle recognition model is used for equivalent fuel consumption minimization strategy with a parallel hybrid electric vehicle. Simulation results show that the fuel economy can improve by 9.914% based on optimized support vector machine, and the fluctuations of battery state of charge are more stable so that system efficiency and batter life are substantially improved.

scholarly journals Powertrain Control for Hybrid-Electric Vehicles Using Supervised Machine Learning

Vehicles ◽  
2020 ◽  
Vol 2 (2) ◽  
pp. 267-286 ◽  
Author(s):  
Craig K. D. Harold ◽  
Suraj Prakash ◽  
Theo Hofman
Keyword(s):  
Machine Learning ◽  
Dynamic Programming ◽  
Electric Vehicles ◽  
Control Strategy ◽  
Hybrid Electric Vehicles ◽  
Supervised Machine Learning ◽  
Test Case ◽  
Drive Cycle ◽  
Powertrain Control ◽  
Hybrid Electric

This paper presents a novel framework to enable automatic re-training of the supervisory powertrain control strategy for hybrid electric vehicles using supervised machine learning. The aim of re-training is to customize the control strategy to a user-specific driving behavior without human intervention. The framework is designed to update the control strategy at the end of a driving task. A combination of dynamic programming and supervised machine learning is used to train the control strategy. The trained control strategy denoted as SML is compared to an online-implementable strategy based on the combination of the optimal operation line and Pontryagin’s minimum principle denoted as OOL-PMP, on the basis of fuel consumption. SML consistently performed better than OOL-PMP, evaluated over five standard drive cycles. The EUDC performance was almost identical while on FTP75 the OOL-PMP consumed 14.7% more fuel than SML. Moreover, the deviation from the global benchmark obtained from dynamic programming was between 1.8% and 5.4% for SML and between 5.8% and 16.8% for OOL-PMP. Furthermore, a test-case was conducted to emulate a real-world driving scenario wherein a trained controller is exposed to a new drive cycle. It is found that the performance on the new drive cycle deviates significantly from the optimal policy; however, this performance gap is bridged with a single re-training episode for the respective test-case.

Development of adaptive gear shifting strategies of automatic transmission for plug-in hybrid electric commuting vehicle based on optimal energy economy

2019 ◽  
Vol 234 (4) ◽  
pp. 1098-1112
Author(s):  
Peihong Shen ◽  
Zhiguo Zhao ◽  
Jingwei Li ◽  
Qiuyi Guo
Keyword(s):  
Fuel Economy ◽  
Automatic Transmission ◽  
Driving Cycle ◽  
Strategy Development ◽  
Engine Fuel ◽  
Clustering Methods ◽  
Self Organized ◽  
Shifting Strategy ◽  
Energy Economy ◽  
Hybrid Electric

Gear shifting strategy of automatic transmission has an important impact on the fuel economy of vehicles. For plug-in hybrid electric commuting vehicles, to develop the driving cycle and working mode adaptive gear shifting strategy of automatic transmission is of great significance to improve the vehicle energy economy. Three main efforts have been made to distinguish our work from exiting research. First, based on the fixity and repeatability of the driving cycle for plug-in hybrid electric commuting vehicles, the typical driving cycle of plug-in hybrid electric commuting vehicle is constructed by the self-organized mapping and K-means clustering methods. Second, in the typical plug-in hybrid electric commuting vehicle driving cycle constructed herein, the working points with the best energy economy are calculated by improved dynamic programming for each working mode of the plug-in hybrid electric commuting vehicle, considering the working efficiency of the power components and transmission. On this basis, the optimal gear shifting strategy of automatic transmission for the plug-in hybrid electric commuting vehicle in each working mode is extracted. Third, the simulation tests are conducted which compare the formulated adaptive gear shifting strategies with the traditional engine fuel economy-based gear shifting strategy. The simulation results illustrate that the adaptive gear shifting strategies increase the energy economy by 3.32%. The proposed gear shifting strategy development method can provide a reference for further optimization of automatic transmission gear shifting strategies of plug-in hybrid electric commuting vehicle for real applications.

A unified quantitative analysis of fuel economy for hybrid electric vehicles based on energy flow

2021 ◽  
Vol 292 ◽  
pp. 126040
Author(s):  
Xiaohua Zeng ◽  
Qifeng Qian ◽  
Hongxu Chen ◽  
Dafeng Song ◽  
Guanghan Li
Keyword(s):  
Quantitative Analysis ◽  
Electric Vehicles ◽  
Fuel Economy ◽  
Energy Flow ◽  
Hybrid Electric Vehicles ◽  
Hybrid Electric

Powertrain Matching Based on Driving Cycle for Fuel Cell Hybrid Electric Vehicle

2013 ◽  
Vol 288 ◽  
pp. 142-147 ◽  
Author(s):  
Shang An Gao ◽  
Xi Ming Wang ◽  
Hong Wen He ◽  
Hong Qiang Guo ◽  
Heng Lu Tang
Keyword(s):  
Fuel Cell ◽  
Electric Vehicle ◽  
Cell Hybrid ◽  
Hybrid Electric Vehicle ◽  
Combustion Engine ◽  
Driving Cycle ◽  
Power Performance ◽  
Matching Method ◽  
Hybrid Electric ◽  
Fuel Cell Hybrid

Fuel cell hybrid electric vehicle (FCHEV) is one of the most efficient technologies to solve the problems of the energy shortage and the air pollution caused by the internal-combustion engine vehicles, and its performance strongly depends on the powertrains’ matching and its energy control strategy. The theoretic matching method only based on the theoretical equation of kinetic equilibrium, which is a traditional method, could not take fully use of the advantages of FCHEV under a certain driving cycle because it doesn’t consider the target driving cycle. In order to match the powertrain that operates more efficiently under the target driving cycle, the matching method based on driving cycle is studied. The powertrain of a fuel cell hybrid electric bus (FCHEB) is matched, modeled and simulated on the AVL CRUISE. The simulation results show that the FCHEB has remarkable power performance and fuel economy.

Match and Optimization of Series Hybrid Bus Powertrain Parameters

2011 ◽  
Vol 121-126 ◽  
pp. 2710-2714
Author(s):  
Ling Cai ◽  
Xin Zhang
Keyword(s):  
Electric Vehicle ◽  
Fuel Economy ◽  
Hybrid Electric Vehicle ◽  
Simulation Platform ◽  
Optimal Method ◽  
Orthogonal Method ◽  
Series Hybrid Electric Vehicle ◽  
Hybrid Bus ◽  
Promising Solution ◽  
Hybrid Electric

With the requirements for reducing emissions and improving fuel economy, it has been recognized that the electric, hybrid electric powered drive train technologies are the most promising solution to the problem of land transportation in the future. In this paper, the parameters of series hybrid electric vehicle (SHEV), including engine-motor, battery and transmission, are calculated and matched. Advisor software is chosen as the simulation platform, and the major four parameters are optimized in orthogonal method. The results show that the optimal method and the parameters can improve the fuel economy greatly.

Research on Torque Distribution Strategy for ISG Hybrid Electric Cars

2012 ◽  
Vol 546-547 ◽  
pp. 212-217
Author(s):  
Xu Dong Wang ◽  
Hai Xing Zhang ◽  
Shu Cai Yang ◽  
Yong Qin Zhou ◽  
Jin Fa Liu
Keyword(s):  
Hybrid System ◽  
Fuel Economy ◽  
Test Model ◽  
Torque Distribution ◽  
Electric Cars ◽  
Distribution Strategy ◽  
Hybrid Car ◽  
Total Vehicle ◽  
Hybrid Electric ◽  
Minimum Work

Based on the configuration and working state analysis of the ISG hybrid electric cars, the torque distribution strategy of a hybrid system is designed to delineate the maximum and minimum work torque curves of the engine, achieve optimization of engine’s range so as to make sure the target torque of the engine and ISG motor, and finally through the calibrated driving characteristics MAP and battery SOC state to achieve the calculation of total vehicle torque demand. Taking the Hafei Saibao ISG hybrid car as a test model, the test of fuel economy and emissions carried out under specific conditions showed that using the torque distribution strategy has increased by 12.8 % of the ISG hybrid car fuel economy and improved emissions performance to some extent compared to the traditional Hafei Saibao cars.

Sign in / Sign up

Export Citation Format

Share Document