Search

Drivers have distinctively diverse behaviors when operating vehicles in natural traffic flow, such as preferred pedal position, car-following distance, preview time headway, etc. These highly personalized behavioral variations are known to impact vehicle fuel economy qualitatively. Nevertheless, the quantitative relationship between driving behaviors and vehicle fuel consumption remains obscure. Addressing this critical missing link will contribute to the improvement of transportation sustainability, as well as understanding drivers’ behavioral diversity. This study proposed an integrated microscopic driver behavior and fuel consumption model to assess and predict vehicle fuel economy with naturalistic highway and local commuting traffic data. Through extensive Monte Carlo simulations, significant correlation results are revealed between specific individual driving preferences and fuel economy over drivers’ frequent commuting routes. Correlation results indicate that the differences in fuel consumption incurred by various driving behaviors, even in the same traffic conditions, can be as much as 29% for a light-duty truck and 15% for a passenger car. A Gaussian Process Regression model is further trained, validated, and tested under different traffic and vehicle conditions to predict fuel consumption based on drivers’ personalized behaviors. Such a quantitative and personalized model can be used to identify and recommend fuel-friendly driving behaviors and routes, demonstrating a strong incentive for relevant stakeholders. [ABSTRACT FROM AUTHOR]

A new equivalent consumption minimization strategy (ECMS) is proposed for a hybrid electric vehicle in which the equivalent factor varies dynamically with the current speed and the minimum engine operation time that leads to improvement in vehicle fuel economy and battery performance. To construct the strategy, a self-organizing map neural-network was utilized to recognize and group the speed patterns. The driving cycles corresponding to these speed patterns were reconstructed for solving the corresponding optimal equivalent factors. When applying the strategy on the road, the current vehicle speed pattern is recognized by using the historical vehicle speed data, and the corresponding optimal equivalent factor is adopted based on that pattern. Furthermore, to constrain the battery state of charge (SOC) to avoid exceeding the allowable values and to consider the hysteresis of engine starting, a fuzzy logic controller was used to dynamically adjust the minimum engine operation time. The simulated results indicated that the proposed ECMS improved the vehicle fuel economy by 7.87% and 6.23% over the conventional ECMS and the rule-based single-point strategy, respectively. Furthermore, the peak battery charging-current was reduced by 42.94% and 27.73%, and the peak discharging-current by 62.19% and 56.97%, respectively. In addition, the proposed strategy could lead to better SOC evolution of the battery. [ABSTRACT FROM AUTHOR]

Through shared real-time traffic information and perception of complex environments, connected and automated vehicles (CAVs) are endowed with global decision-making capabilities far beyond that of human drivers. Given more traffic lights information, this planning ability can be greatly strengthened. This study proposed an adaptive speed planning method of CAVs based on multi-light trained deep reinforcement learning (DRL), aiming to improve the fuel economy and comfort of CAVs. By setting a reasonable reward function, the training algorithm takes the key environmental information received by the vehicle as inputs, and finally outputs the acceleration that maximizes the cumulative reward. The results show that the trained DRL agent can adapt to variable scenarios with traffic lights, and quickly solve the approximate optimal speed trajectory. Multi-light DRL models save 6.79% fuel compared with single-light ones and have better performance on fuel economy and computational efficiency than a non-RL method using multi-light optimization. [ABSTRACT FROM AUTHOR]

The development of Autonomous Vehicles (AVs) envisions the promising technology of future Intelligent Transportation Systems (ITS). However, the complex road structures and increased vehicles cause traffic congestion and road safety, which eventually leads to horrible accidents. Cooperative driving of AVs, a groundbreaking initiative of vehicle platooning, epitomizes the next wave in vehicular technology through minimizing accident risks, transport times, costs, energy, and fuel consumption. However, the traditional machine learning-based platooning approaches fail to regulate the policy with the dynamic feature of AVs. This paper proposes a hybrid Deep Reinforcement learning and Genetic algorithm for Smart-Platooning (DRG-SP) the AVs. The leverage of the deep reinforcement learning mechanism addresses the computational complexity and accommodates the high dynamic platoon environments. Adopting the Genetic Algorithm in Deep Reinforcement learning overcomes the slow convergence problem and offers long-term performance. The simulation results reveal that the Smart-Platooning effectively forms and maintains the platoons by minimizing traffic congestion and fuel consumption. [ABSTRACT FROM AUTHOR]

This paper proposes a predictive equivalent consumption minimization strategy (P-ECMS) for a plug-in hybrid electric vehicle (PHEV), assuming the availability of two levels of traffic information. The two levels of traffic information include 1) segmented traffic information available from mobile mapping applications, and 2) detailed velocity information, possibly obtained by short-term speed forecasting. Battery state-of-charge (SOC) reference waypoints are obtained by a simplified speed profile constructed from that segmented traffic information. The proposed P-ECMS adjusts its co-state or equivalence factor based on the difference between the future SOC obtained from short-horizon prediction and a future reference SOC. The benefits of the proposed P-ECMS are evaluated through vehicle simulations on a specified trip, compared against an adaptive ECMS (A-ECMS) with the same control parameters minus prediction. Simulation results on the trip demonstrate that the proposed P-ECMS can achieve a 9.7% reduction in the corresponding fuel consumption on average, compared to the A-ECMS across different combinations of initial co-state and control gain. Moreover, its performance is robust to variations in the initial co-state, the co-state update rate, and the prediction horizon, as well as to inaccuracies in the velocity prediction. Compared to the A-ECMS, the standard deviation in fuel consumption with the P-ECMS can be reduced by 96% from 84.1 to 3.4 grams. [ABSTRACT FROM AUTHOR]

A novel framework is proposed for enhancing the driving safety and fuel economy of autonomous vehicles (AVs) with the aid of vehicle-to-infrastructure (V2I) communication networks. The problem of driving trajectory design is formulated for minimizing the total fuel consumption, while enhancing driving safety (by obeying the traffic rules and avoiding obstacles). In an effort to solve this pertinent problem, a deep reinforcement learning (DRL) approach is proposed for making collision-free decisions. Firstly, a deep Q-network (DQN) aided algorithm is proposed for determining the trajectory and velocity of the AV by receiving real-time traffic information from the base stations (BSs). More particularly, the AV acts as an agent to carry out optimal action such as lane change and velocity change by interacting with the environment. Secondly, to overcome the large overestimation of action values by the Q-learning model, a double deep Q-network (DDQN) algorithm is proposed by decomposing the max-Q-value operation into action selection and action evaluation. Additionally, three practical driving policies are also proposed as benchmarks. Numerical results are provided for demonstrating that the proposed trajectory design algorithms are capable of enhancing the driving safety and fuel economy of AVs. We demonstrate that the proposed DDQN based algorithm outperforms the DQN based algorithm. Additionally, it is also demonstrated that the proposed fuel-economy (FE) based driving policy derived from the DRL algorithm is capable of achieving in excess of 24% of fuel savings over the benchmarks. [ABSTRACT FROM AUTHOR]

Pulse and glide (PnG) is a driving strategy that controls vehicles in a more fuel-efficient way than driving at a constant speed does. It can be applied by the driver or, which is more likely, by an automated system with autonomy level one or higher. During the pulse phase, the vehicle is accelerated to operate the combustion engine and transmission at higher efficiency. During the following glide phase, the vehicle decelerates and the engine is decoupled from the drive train. The optimal pulse and glide strategy – as addressed in previous studies – implies high acceleration values and abrupt transitions between pulse and glide, which both degrade the ride comfort. A driveability study on PnG conducted recently identified that the acceleration, the jerk during the transitions and the duration of the glide phase have to be limited to reach the desired level of ride comfort. Thresholds have been derived for a level-eight calibration, i.e. a PnG operation that is noticeable only to skeptical customers. We use the results of the study to also provide thresholds for a level-seven calibration, i.e. a PnG operation that is noticeable to all customers without being disturbing. Subsequently, we establish a correlation between ride comfort and fuel consumption by comparing the fuel savings of three different driveability calibrations: level eight, level seven and a calibration without driveability constraints. The simulations are performed for a D-segment vehicle and two different gasoline engines. With reference to constant speed, the fuel savings of the level-seven calibration are larger than 30% below 40 km/h, decreasing gradually with increasing speed. They are around ten percent higher than those of the level-eight calibration and only a few percent lower than those of a PnG operation without driveability constraints. Hence, the level-seven calibration can nearly exploit the maximal fuel-saving potential of PnG, and, as it is not disturbing, should be considered for practical applications of PnG. The PnG strategy can be applied to any vehicle equipped with a combustion engine that features the engine-off functionality, which is the case for mild and full hybrids and for some micro hybrids. However, considering that the benefit of PnG increases with increasing engine size, the fuel saving potential of PnG is highest for micro and mild hybrids as these vehicles are commonly equipped with larger engines than full hybrids. [ABSTRACT FROM AUTHOR]

The electric engine cooling system with the active grille shutter requires intelligent and predictive control to reach its full benefits on fuel economy and thermal management. Conventional control methods regulate the coolant temperature to a fixed value but do not directly minimize the vehicle's fuel/energy consumption. By contrast, we design a fuel minimization controller through solving constraint nonlinear optimization problems, whose cost function is the total fuel consumption and constraints are the vehicle's physical limits. To achieve high computational efficiency and sufficient accuracy, the optimization problem is solved by iterative convex quadratic programming and quasilinearization. The advantages of the proposed control method on both fuel economy and engine thermal management are demonstrated by simulations. [ABSTRACT FROM AUTHOR]

Load profiles or duty cycles on a powertrain system are one of the major factors that affect the fuel economy of hybrid electric vehicles. Most of optimal power management controllers that are designed for minimum fuel consumption take into account the upcoming duty cycles explicitly or implicitly. Due to this non-causal nature, many optimal algorithms are not implementable in real-time, or they reluctantly assume simple future duty cycles for real-time implementation at the cost of performance. This paper presents an optimal power management controller that uses the predicted near-future duty cycle instead of hypothesized duty cycles. Model predictive control is used for the controller, and a deep neural network is designed for the estimation of the future duty cycle. Signals from a radar sensor and signals from the ego vehicle are used as the input signals for the deep neural network. A model predictive controller with a well-estimated near-future duty cycles showed significantly improved fuel economy than a model predictive controller with simply assumed duty cycles. Even a less accurately estimated future duty cycle helps improve the fuel economy more than a simply assumed future duty cycle does. We observed that some knowledge about the future duty cycle in the model predictive controller is better for improving fuel economy than the simple assumption if the information has the right directional tendency, even if it is not accurate. [ABSTRACT FROM AUTHOR]

Plug-in hybrid electric vehicles have the advantages of both traditional fuel cars and electric vehicles. This paper presents a single planetary gear dual-mode (input- and output-split) hybrid powertrain. Clutches are substituted for a synchronizer to achieve mode switching. To filter six possible topology schemes, a screening method based on kinematics and theoretical efficiency analysis is utilized. Subsequently, a backward model is established by modeling each powertrain component and designing an appropriate control strategy. Finally, a backward simulation method is utilized to select the optimal topologies. To evaluate the performance of the proposed powertrains, two typical power-split powertrains, THS-P610 and Volt-II, are compared with the optimized powertrains. The comparison results show that the proposed powertrains, having a simpler structure than Volt-II, improve the acceleration and fuel economy performances compared with THS-P610 and Volt-II. [ABSTRACT FROM AUTHOR]

Recent advances in transportation have proved that the use of upcoming trip data in energy management of plug-in hybrid electric vehicles (PHEVs) is extremely effective in promoting their fuel economy (FE). However, traffic mispredictions as well as the additional overhead of processing route data induce challenges in use of such strategy in practice. With this in mind, the present paper evaluates practical implementability of a trip planning assisted energy management system (TPAEMS). Toward the end, online integration of the TPAEMS with real-time data and also fast implementation of the trip planning algorithm is first outlined. Then, the TPAEMS under consideration is implemented for the Toyota Prius PHEV and its performance is compared to the vehicle's baseline energy management system (EMS) through model-in-the-loop simulations. In addition, hardware-in-the-loop experiments are carried out to evaluate the computational time of the TPAEMS and verify its real-time implementability. Furthermore, the sensitivity of the TPAEMS to traffic mispredictions is studied through a comprehensive sensitivity analysis. In particular, traffic prediction errors are modeled using probabilistic uncertainty modeling and also real-world data. Numerous repeated random samples of uncertainties are utilized to carry out extensive Monte Carlo simulations followed by statistical analyses of the outcomes. Our results indicate that the TPAEMS under consideration is sufficiently fast to be implemented in real time and exhibits low sensitivity to traffic mispredictions so that it maintains FE gain in real-world scenarios compared to the baseline EMS. [ABSTRACT FROM AUTHOR]

In this paper, the configuration of a novel plug-in hybrid electric vehicle (PHEV) system is proposed. For the novel PHEV system, the main operating modes and the control strategy, including rules for mode switching and energy management, are established. A backward model of the vehicle involving the power sources, transmission, and control system is worked out in MATLAB/Simulink/Stateflow environment. The distribution of operating points of each power source, as well as the fuel consumptions of the vehicle under new European driving cycle (NEDC) and FTP75 testing cycles are simulated and compared with typical hybrid systems such as parallel, series, and Toyota hybrid system (THS). The results indicate that the proposed system can operate at high fuel economy by adopting the rule-based energy management strategy along with the equivalent consumption minimization strategy, which proves the feasibility and effectiveness of the configuration and control strategies. [ABSTRACT FROM AUTHOR]

The multimode power-split architecture for hybrid electric vehicle (HEV) powertrains is generally known for the complexity of its operation. This paper first addresses the challenge of developing an automated on-line near-optimal control strategy for these systems. Particularly, a machine learning logic based on supervised learning is developed for on-line selection of the HEV operating mode, thus the particular set of clutches to be engaged. An efficiency-based approach is then adopted to determine the optimal power-split between powertrain components. Later, the developed strategy finds integration in an optimal design methodology for multimode power-split HEVs considering the effectiveness and ease of on-line controllability. The obtained results are compared with the ones by the traditional HEV design methodology that only considers off-line energy management. The illustrated design methodology with on-line control reveals efficient at identifying the multimode HEV design that demonstrates optimal predicted fuel economy values and ease of on-line controllability simultaneously. Results suggest that the HEV design optimization procedure may produce different outcomes and demonstrate more effective when the evaluation of the on-line controlled operation is integrated. [ABSTRACT FROM AUTHOR]

Higher fuel economy standards and more stringent limitations on greenhouse gas emissions for ground vehicles have been made due to public concerns about energy crisis and environmental issues. By organizing a group of automated vehicles into a platoon at a short intervehicular distance, the overall fuel consumption and greenhouse gas emissions of vehicle platoon can be decreased due to reduced aerodynamic drag, which is called the platooning technology. In addition, the eco-driving technology can help further increase the fuel efficiency of vehicle platoon by optimizing speed trajectories of vehicles. However, little research has been done into the combination of the eco-driving and platooning technologies. Based on distributed model predictive control (DMPC), this paper proposes an ecological cooperative look-ahead control strategy for a platoon of automated vehicles travelling on a freeway with varying slopes, where both the eco-driving and platooning technologies are used. To maximize the fuel efficiency of vehicle platoon, an ecological cooperative look-ahead control problem (Eco-CLC) is first formulated based on DMPC, where rotational inertia coefficient related to reduction ratio of gear box, aerodynamic drag related to spacing and model constraints are considered. Since the Eco-CLC problem is a nonconvex and nonlinear optimization problem with hard state constraints, it is very difficult to quickly obtain its optimal solution. To enhance real-time control performance, after the hard state constraints of the Eco-CLC problem are transformed into parts of the multi-objective function using the band-stop function, the improved ecological cooperative look-ahead control (iEco-CLC) based on DMPC is given. A particle swarm optimization algorithm with multiple dynamic populations is further presented to quickly solve the iEco-CLC problem online. Simulation results demonstrate, compared with benchmarks, the proposed strategy can save more than 21% of fuel for vehicle platoon. [ABSTRACT FROM AUTHOR]

The performance of energy management systems in hybrid electric vehicles (HEVs) is highly related to drivers’ driving style. This paper proposes a driving-style-oriented adaptive equivalent consumption minimization strategy (AECMS-style) in order to improve fuel economy for HEVs. For this purpose, first, a statistical pattern recognition approach is proposed to classify drivers into six groups from moderate to aggressive using kernel density estimation and entropy theory. Then, the effects of driving style on energy management strategies are discussed by analyzing the performance of the equivalent consumption minimization strategy (ECMS). Based on the comprehensive analysis, we design a new optimal equivalent factor adjustment rule for the AECMS-style and also redesign the braking strategy of motors at driving charging mode for different driving styles. Finally, five drivers with typical driving styles participate in experiments to show the effectiveness of our proposed method. Experimental results demonstrate that the AECMS-style can improve the fuel economy and charging sustainability of HEVs, compared with ECMS. [ABSTRACT FROM AUTHOR]

Fuel consumption of fossil-based road vehicles is significantly affected by the way vehicles are driven. The same is true for automated vehicles with longitudinal control. This paper presents a periodic servo-loop longitudinal control algorithm for an adaptive cruise control (ACC) system to minimize fuel consumption in car-following scenarios. The fuel-saving mechanism of pulse-and-glide (PnG) operation is first discussed for the powertrain with internal combustion engine and step-gear transmission. The servo-loop controller is then designed based on a periodic switching map for real-time implementation and adjusted with a range-bounded feedback regulator to enhance the robustness to model mismatch. Simulations in both uniform and natural traffic flows demonstrate that this algorithm achieves a significant fuel-saving benefit in automated car-following scenarios up to 8.9% in naturalistic traffic flow (when coasting at neutral gear), compared with a linear quadratic (LQ) controller. Meanwhile, its intervehicle range is preferably bounded so that the negative impact on safety and traffic smoothness is contained. [ABSTRACT FROM PUBLISHER]

This paper proposes a blended rule-based energy management system (EMS) for a plug-in hybrid electric vehicle (PHEV). The proposed EMS is formulated over driving information and vehicle trip energy and not over vehicle speed profiles, as usually seen. The proposed EMS design structure and strategy is described followed by its evaluation. This is the first time a platform for a rule-based acausal EMS has been designed. Performance metrics such as the fuel economy and the number of engine stop–starts are compared with conventional rule-based EMS over real-world destinations with uncertain trip demand. Its performance metrics compared with a conventional EMS for a full parallel PHEV was found to be superior in this paper. [ABSTRACT FROM PUBLISHER]

Planetary gears (PGs) have been used in power-split hybrid and plug-in hybrid vehicles, sometimes with clutches to enable multimode operations. Chevrolet Volt is a well-known production vehicle using such technologies; it achieves excellent performance in both charge-depleting (CD) and charge-sustaining modes. In this paper, a detailed analysis of the General Motors (GM) Voltec powertrain used in the 2016 Chevrolet Volt (Volt Gen 2) is presented. We search through a large topological space, which includes a total of around 1 million design candidates to find different powertrain layouts that achieve the same or better acceleration and fuel economy in comparison with the benchmark: a simulated Volt Gen 2. The key technologies enabling such large-scale design exercise are discussed, and preliminary findings are reported. The case study results show that 49 designs achieve better charge-sustaining, CD, and launching performances than the benchmark, which clearly demonstrated the value of the proposed design methodology. [ABSTRACT FROM PUBLISHER]

Taking the complex but regular characteristics of bus routines into account, the stochastic dynamic programming (SDP) might be a method with more potential to optimize the energy management of a plug-in hybrid electric bus (PHEB). However, the discrete transmission system and the continuous power system make it a complicated multidimensional optimal problem, particularly for PHEB with automated mechanical transmission (AMT), and the optimal decisions, which are obtained based on historical data, might not always well satisfy the driver's expectation to vehicle maneuverability under various driving conditions. To solve these problems, an adaptive approach based on the SDP is proposed in this paper. Exhaustively, the SDP is propelled into the input of the transmission to only optimize the torque split under the special gearshift logic, which reduces the dimensions of optimization and obtains more applicable optimal sequences. Then, an adaptive factor, which trades off the vehicle fuel economy and drivability in real time by dynamically adjusting the gearshift points and the torque split, is developed for the variation of the complicated bus driving cycles. The simulation results demonstrate that the proposed method could well respond to the variations of the driving conditions (e.g., road grade and vehicle load). Furthermore, the performance of the proposed method is discussed in detail by comparisons with different control strategies. More importantly, the proposed approach has great potential to be applied in practice. [ABSTRACT FROM PUBLISHER]

This paper studies the fuel-optimal cruising strategies of parallel hybrid electric vehicles (HEVs) and their underlying mechanisms. To achieve fuel-optimal operations, a discontinuous nonlinear optimal control problem is formulated and solved using the Legendre pseudospectral method and the knotting technique. Three optimal cruising strategies in free/fixed-speed cruising scenarios are proposed: vehicle speed pulse-and-glide strategy, state-of-charge (SoC) pulse-and-glide (PnG) strategy, and constant-speed strategy. The performance and optimal behavior of the engine and the motor are presented, and their fuel-saving mechanisms are explained. Finally, two principles to compromise between fuel economy and ride comfort are proposed and studied. [ABSTRACT FROM PUBLISHER]

For hybrid electric vehicles (HEVs), the well-studied fuel economy optimization approaches will usually implement frequent engine starts/stops, which can significantly impact the catalyst temperatures and performances of the aftertreatment systems. This paper aims to simultaneously optimize fuel economy and reduce tailpipe emissions for HEVs coupled with aftertreatment systems. First, a control-oriented model is developed by systematically incorporating HEV models with aftertreatment thermal dynamic models, both of which have been experimentally validated. The integrated model is capable of predicting engine-out gas temperature and NOx emissions and simulating the temperature dynamics of the aftertreatment systems. Additionally, post injections' characteristics are investigated and modeled. An aftertreatment warm-up approach is developed by strategically enabling double post injections. Eventually, a supervisory controller is designed to optimize the post-injection ratio and the torque split ratio of HEV powertrains. The controller designed is rooted in a model predictive control (MPC) scheme, and it has an intuitive interpretation in terms of operating costs. The validation results show that the controller can significantly reduce the warm-up time and can successfully regulate the catalyst temperature to the desired range with a reasonable sacrifice of fuel economy for HEVs. [ABSTRACT FROM AUTHOR]

This paper considers a diesel series hybrid electric vehicle (SHEV) and proposes the utilization of an engine–generator power rate constraint map to reduce soot emissions without a significant compromise in fuel economy. Specifically, model predictive control (MPC) is used to split the vehicle power demand between the engine–generator unit and the battery. To achieve a reduction in soot, the engine–generator power rate is constrained. Unlike existing strategies, the power rate limit is not a fixed value but varies, depending on the power level, resulting in a map. This constraint map is designed by formulating the soot emission reduction problem as an optimization problem, which is solved through a three-step offline discrete optimization process. The optimization relies on a quasi-static soot emissions map that captures the trends, even during transients, but underestimates the magnitudes. Therefore, to evaluate the performance of the MPC-based power management with the power rate constraint map, experiments are conducted through an engine-in-the-loop simulation framework. Experimental results show that compared with a constant power rate constraint, soot emissions can be reduced by 44.5% while compromising fuel economy by only 0.3% through the proposed approach. As a tradeoff, the ampere-hour (Ah) processed in the battery, which is a variable that has been shown to correlate with battery capacity loss, increases by 5.5%. [ABSTRACT FROM PUBLISHER]

This is the second paper in a series of two that describe our research in intelligent energy management in a hybrid electric vehicle (HEV). In the first paper, we presented the machine-learning framework ML_EMO_HEV, which was developed for learning the knowledge about energy optimization in an HEV. The framework consists of machine-learning algorithms for predicting driving environments and generating the optimal power split of the HEV system for a given driving environment. In this paper, we present the following three online intelligent energy controllers: 1) IEC_HEV_SISE; 2) IEC_HEV_MISE ; and 3) IEC_HEV_MIME. All three online intelligent energy controllers were trained within the machine-learning framework ML_EMO_HEV to generate the best combination of engine power and battery power in real time such that the total fuel consumption over the whole driving cycle is minimized while still meeting the driver's demand and the system constraints, including engine, motor, battery, and generator operation limits. The three online controllers were integrated into the Ford Escape hybrid vehicle model for online performance evaluation. Based on their performances on ten test drive cycles provided by the Powertrain Systems Analysis Toolkit library, we can conclude that the roadway type and traffic congestion level specific machine learning of optimal energy management is effective for in-vehicle energy control. The best controller, IEC_HEV_MISE, trained with the optimal power split generated by the DP optimization algorithm with multiple initial SOC points and single ending point, can provide fuel savings ranging from 5% to 19%. Together, these two papers cover the innovative technologies for modeling power flow, mathematical background of optimization in energy management, and machine-learning algorithms for generating intelligent energy controllers for quasioptimal energy flow in a power-split HEV. [ABSTRACT FROM PUBLISHER]

In this series of two papers, we present our research on intelligent energy management for hybrid electric vehicles (HEVs). These two papers cover the modeling of power flow in HEVs, the mathematical background of optimization in energy management in HEVs, a machine learning framework that combines dynamic programming (DP) with machine learning to learn about roadway-type- and traffic-congestion-level-specific energy optimization, machine learning algorithms, and real-time quasi-optimal control of energy flow in an HEV. This first paper presents our research on machine learning for optimal energy management in HEVs. We will present a machine learning framework ML_EMO_HEV developed for the optimization of energy management in an HEV, machine learning algorithms for predicting driving environments, and the generation of an optimal power split for a given driving environment. Experiments are conducted based on a simulated Ford Escape Hybrid vehicle model provided by Argonne National Laboratory's Powertrain Systems Analysis Toolkit (PSAT). Based on the experimental results on the test data, we can conclude that the neural networks trained under the ML_EMO_HEV framework are effective in predicting roadway type and traffic congestion levels, predicting driving trends, and learning optimal engine speed and optimal battery power from DP. [ABSTRACT FROM PUBLISHER]

Fuel consumption of traditional ground vehicles is significantly affected by how the vehicles are driven. This paper focuses on the servo-loop control design of a Pulse-and-Gliding (PnG) strategy to minimize fuel consumption in automated car following. A switching-based framework is proposed for real-time implementation. The corresponding controller was synthesized for ideal conditions and subsequently enhanced to compensate for practical factors such as powertrain dynamics, speed variations, and plant uncertainties. Simulations in both uniform and naturalistic traffic flows demonstrate that, compared with a linear quadratic (LQ)-based benchmark controller, the PnG controller improves fuel economy up to 20%. The significant fuel saving is achieved while maintaining precise range bounds so that the negative impact on safety/traffic flow is contained. The developed algorithm can potentially be embedded in adaptive cruise control systems to achieve fuel-saving function. [ABSTRACT FROM PUBLISHER]

Automotive electrification in the past decade was accompanied by infrastructural changes in the electric power industry. The dual fuel (gasoline and electricity) and dual operation (vehicle to grid (V2G) and grid to vehicle) modes of plug-in hybrid electric vehicles (PHEVs) make them attractive to the automotive and the electric power industries. The value proposition of PHEVs from consumer and automotive perspectives depends on a number of key indicators, such as fuel economy, emissions, battery lifetime, and incremental premium over a hybrid electric (HEV) or a conventional vehicle (CV). In addition, the value proposition of a PHEV from a utility perspective can diverge or even conflict with the consumer or automotive industry perspective. The traditional distance-based utility factor (UF) is primarily used to estimate the vehicle miles that are electrifiable. In this paper, a novel energy-based electrification potential factor (EPF) is proposed to differentiate between travel miles that are electrified and electrifiable. The EPF also acts as a coupling factor that can be also used to assess the overall benefits and impacts of PHEVs from consumer, automotive industry, and utility perspectives. The EPF is developed using existing transportation survey data and detailed simulations using the Powertrain System Analysis Toolkit (PSAT). For different driving profiles and control strategies (charge sustaining, charge depleting, blended, and all electric), the tradeoffs between driving cost and battery lifetime are analyzed. Specific battery lifetime targets are set, and a baseline HEV is used to compare the driving cost savings of the PHEV before determining the EPF. The viability and usefulness of the proposed EPF is demonstrated through comprehensive vehicular simulations and tradeoff analyses. [ABSTRACT FROM PUBLISHER]

Given the heated discussion of climate change and the ever-increasing demand for fossil fuels, the ability to reduce vehicular carbon footprints is of great importance for both environmental and economical reasons. This paper presents a carbon-footprint/fuel-consumption-aware variable-speed limit (FC-VSL) traffic control scheme that targets minimizing the average vehicular fuel consumption on freeways under live traffic conditions. We first formulated the problem of minimizing fuel consumption for a single vehicle under certain traffic conditions as an optimal control problem. By solving the problem, we obtained the optimal vehicular trajectory, which results in minimum fuel consumption. Then, we designed the FC-VSL scheme based on the optimal trajectory. We evaluated the performance of the FC-VSL scheme through detailed simulation. The results show that the FC-VSL scheme can significantly reduce the average fuel consumption and outperform another speed limit scheme that was designed to smooth traffic flow without considering fuel consumption. [ABSTRACT FROM PUBLISHER]

The main aim in the control of a hybrid electric vehicle (HEV) is to decrease the fuel consumption and emissions without significant loss of driving performance. The performance of the vehicle in terms of fuel economy and emissions is very much dependent on the vehicle's supervisory control strategy. In this paper, the equivalent consumption minimization strategy (ECMS) is developed with a novel approach for the charge sustaining of the batteries to provide an overall improved optimization performance for series hybrid electric vehicles (SHEVs), considering the efficiencies of the internal combustion engine (ICE), generator, and battery. Another novelty is the development of a combined map, which simultaneously facilitates the optimization of the fuel consumption and multiple emission components, unlike most past studies that have concentrated on one component at a time. After the derivation of the cost map, the algorithm is divided into two main parts. The first part optimizes the engine–generator set (GENSET), and the second part determines how much power is needed from the GENSET according to the ECMS. The algorithm is implemented using generic emission and fuel consumption maps of an actual mid-sized series hybrid bus to reduce the desired emissions. The hybrid electric vehicle in consideration is converted from a conventional bus that is driven by an ICE. The performance of the novel ECMS strategy is compared with the conventional vehicle, as well as the SHEV version that is driven by an on–off strategy. In addition to reduced fuel consumption, the results of this paper demonstrate a significant reduction of 14.58% in CO2 production with ECMS, whereas the on–off control strategy achieves only 6.47% reduction over the conventional vehicle. [ABSTRACT FROM PUBLISHER]

To extend the lithium-ion (Li-ion) battery cycle life, an active combination of an ultracapacitor (UC) with an energy-dense Li-ion battery is shown as a promising approach for electric vehicles (EVs) and plug-in hybrid electric vehicles (PHEVs). In this paper, the problem of the sizing of the Li-ion battery and UC, as well as the degree of hybridization between the UC power and battery power, is approached from a new perspective, i.e., by solving an optimization problem to minimize fuel consumption. To implement this optimized power sharing in real time, a novel energy management strategy is proposed, which includes battery power reference generation, UC state-of-charge regulation, and forecast control based on the driver commands. Finally, simulations and experiments in which the flywheel + generator + controlled load is used to emulate the vehicle drivetrain are provided to verify the reduced stress on the battery current and the improved fuel economy achieved by the proposed method. [ABSTRACT FROM PUBLISHER]

The potential of plug-in hybrid electric vehicles (PHEVs) to operate in electric and hybrid modes and their ability to supplement the energy storage off the grid have made them a front-runner in alternative fuel vehicle development. However, there is currently no widely accepted standard classification that provides an accurate comparison of PHEVs. This paper presents a novel classification for PHEVs: “Pihef: Plug-In Hybrid Electric Factor.” Pihef is the average ratio of the energy provided by the grid to the sum of the energy provided by the grid and fuel. The viability of Pihef is demonstrated via comprehensive simulations and a sensitivity analysis. In addition, the relationship between Pihef and emissions, efficiency, hybridization, and electric range is developed. [ABSTRACT FROM PUBLISHER]

Unlike conventional hybrid electric vehicles (HEVs), the novel powertrain configuration of the University of Technology, Sydney (UTS) plug-in HEV (PHEV) contains only one electric machine, which functions as either an electric motor or a generator in different time intervals specified by a special energy management strategy (EMS). This paper presents a comparative analysis of the fuel economy and the greenhouse gas (GHG) emissions between a conventional HEV and the UTS PHEV, which includes vehicle modeling, EMS development, and a simulation model of the conventional HEV, which is embedded in the advanced vehicle simulator, and the UTS PHEV simulation code. The fuel economy and the emissions, such as hydrocarbon, carbon monoxide, and nitrogen oxides, are computed, analyzed, and compared for the two standard drive cycles, i.e., 1) the high-speed highway drive cycle and 2) the low-speed city drive cycle, proposed by the U.S. Environmental Protection Agency and their combination. [ABSTRACT FROM PUBLISHER]

To reduce fuel consumption and emissions in plug-in hybrid electric vehicles (PHEVs), it is equally important to select an appropriate drive train topology as it is to develop a suitable power flow control strategy. While there are many control strategies that have been developed and presented, most are expansions of hybrid electric vehicle (HEV) control strategies and do not maximize the true potential the PHEV offers as a result of its ability to operate in electric-only mode over a significant distance. In this paper, state-of-the-art control strategies are reviewed and classified in detail. PHEV controllers mostly operate on either a rule-based or an optimization-based algorithm, each having its own advantages and disadvantages. An overview of the controllers is given, and an analysis on which strategy is more suitable to maximize PHEV performance in different drive cycle conditions is provided. Finally, a new classification for PHEV control strategies based on the operation of the vehicle is presented and verified through simulation results. [ABSTRACT FROM PUBLISHER]

Previous research has shown that current driving conditions and driving style have a strong influence over a vehicle's fuel consumption and emissions. This paper presents a methodology for inferring road type and traffic congestion (RT&TC) levels from available onboard vehicle data and then using this information for improved vehicle power management. A machine-learning algorithm has been developed to learn the critical knowledge about fuel efficiency on 11 facility-specific drive cycles representing different road types and traffic congestion levels, as well as a neural learning algorithm for the training of a neural network to predict the RT&TC level. An online University of Michigan-Dearborn intelligent power controller (UMD_IPC) applies this knowledge to real-time vehicle power control to achieve improved fuel efficiency. UMD_IPC has been fully implemented in a conventional (nonhybrid) vehicle model in the powertrain systems analysis toolkit (PSAT) environment. Simulations conducted on the standard drive cycles provided by the PSAT show that the performance of the UMD_IPC algorithm is very close to the offline controller that is generated using a dynamic programming optimization approach. Furthermore, UMD_IPC gives improved fuel consumption in a conventional vehicle, alternating neither the vehicle structure nor its components. [ABSTRACT FROM AUTHOR]

Hybrid electric vehicles (HEVs) are equipped with multiple power sources for improving the efficiency and performance of their power supply system. An energy management (EM) strategy is needed to optimize the internal power flows and satisfy the driver's power demand. To achieve maximum fuel profits from EM, many solution methods have been presented. Optimal solution methods are typically not feasible in an online application due to their computational demand and their need to have a priori knowledge about future vehicle power demand. In this paper, an online EM strategy is presented with the ability to mimic the optimal solution but without using a priori road information. Rather than solving a mathematical optimization problem, the methodology concentrates on a physical explanation about when to produce, consume, and store electric power. This immediately reveals the vehicle characteristics that are important for EM. It is shown that this concept applies to many existing HEVs as well as possible future vehicle configurations. Since the method only focuses on typical vehicle characteristics, the underlying algorithm requires minor computational effort and can be executed in real time. Clear directions for online implementation are given in this paper. A parallel HEV with a 5-kW integrated starter/generator (ISG) is selected to demonstrate the performance of the EM strategy. Simulation results indicate that the proposed EM strategy exhibits similar behavior as an optimal solution obtained from dynamic programming. Profits in fuel economy primarily arise from engine stop/start and energy obtained during regenerative braking. This latter energy is preferably used for pure electric propulsion where the internal combustion engine is switched off. [ABSTRACT FROM AUTHOR]