Adaptive Equivalent Consumption Minimization Strategy Research Articles

A multi-objective hierarchical deep reinforcement learning algorithm for connected and automated HEVs energy management

Connected and autonomous vehicles have offered unprecedented opportunities to improve fuel economy and reduce emissions of hybrid electric vehicle (HEV) in vehicular platoons. In this context, a hierarchical control strategy is put forward for connected HEVs. Firstly, we consider a deep deterministic policy gradient (DDPG) algorithm to compute the optimized vehicle speed using a trained optimal policy via vehicle-to-vehicle communication in the upper level. A multi-objective reward function is introduced, integrating vehicle fuel consumption, battery state-of-the-charge, emissions, and vehicle car-following objectives. Secondly, an adaptive equivalent consumption minimization strategy is devised to implement vehicle-level torque allocation in the platoon. Two drive cycles, HWFET and human-in-the-loop simulator driving cycles are utilized for realistic testing of the considered platoon energy management. It is shown that DDPG runs the engine more efficiently than the widely-implemented Q-learning and deep Q-network, thus showing enhanced fuel savings. Further, the contribution of this paper is to speed up the higher-level vehicular control application of deep learning algorithms in the connected and automated HEV platoon energy management applications.

Optimal Rule-Interposing Reinforcement Learning-Based Energy Management of Series—Parallel-Connected Hybrid Electric Vehicles

P2–P3 series–parallel hybrid electric vehicles exhibit complex configurations with multiple power sources and operational modes, presenting a difficulty in developing efficient energy management strategies. This paper takes a P2–P3 series–parallel hybrid power system-KunTye 2DHT system as the research object and proposes a deep reinforcement learning framework based on pre-optimized energy management to improve the energy consumption performance of the hybrid electric vehicles. Firstly, a control-oriented model is established based on its system configuration and characteristics. Then, the optimal distribution of the motor energy under different operating modes is pre-optimized, which aims to reduce the energy management task’s dimensionality by equating two motors as an equivalent motor. Subsequently, based on real-time traffic information under connected conditions, deep reinforcement learning is utilized to optimize the optimal operating modes of the hybrid system and the optimal distribution between the engine and equivalent motors. Combining the pre-optimized results, the optimal energy distribution between the engine and the two motors in the system is achieved. Finally, performance comparisons are made between the predictive control and the traditional Dynamic Programming and Adaptive Equivalent Consumption Minimization Strategy, revealing the proposed optimization algorithm’s promising potential in reducing fuel consumption.

Gradient-aware trade-off control strategy dynamic optimization for a fuel cell hybrid electric vehicle

Road gradients not only affect the actual performance of control strategies but also impact battery life due to the drastic changes in power demands. To balance battery degradation with fuel economy using gradient information, this study proposes a gradient-aware trade-off control strategy. Initially, a vehicle dynamics model and a battery degradation model are established. Based on the characteristics of known road information and remaining driving distance, state of charge planning of the battery is conducted. Subsequently, the Non-dominated Sorting Genetic Algorithm-II is applied for bi-objective optimization, yielding a set of Pareto solutions that represent different levels of energy consumption and battery degradation. Thereafter, by introducing a real-time battery degradation severity factor, an optimized bias coefficient is obtained, which adjusts in accordance with the gradient changes. Through the optimization of the bias line, the optimal bias solution set under different working conditions is determined, achieving the optimal control for power system. The fuel economy of the proposed strategy is improved by 6.8% relative to the mileage adaptive Equivalent Consumption Minimization Strategy, and the battery degradation inhibition is improved by 9.3%. After real-world conditions validation, the proposed strategy demonstrates good performance in both economic efficiency and battery life.

Comparative study of real-time A-ECMS and rule-based energy management strategies in long haul heavy-duty PHEVs

Road transport is a significant contributor to Green House Gas (GHG) emissions in the European Union (EU) and is responsible for approximately 25% of total GHG emissions in the EU13. The European Commission has proposed stricter CO2 emissions targets for heavy-duty vehicles that require manufacturers to achieve a reduction of 90% in average fleet emissions from new vehicles by 2040 compared to a 2019 baseline. To meet these ambitious targets, there is an urgent need to explore alternative pathways away from conventional fossil fuel-based powertrain systems like electrified powertrains and carbon–neutral fuels. One promising option is the plug-in hybrid electric powertrain concept, which combines the advantages of both power sources, enabling improved fuel efficiency and reduced CO2 emissions. However, the potential of such a plug-in hybrid powertrain needs to be evaluated for heavy-duty trucks.This study focuses on the development of control strategies for the Energy Management System (EMS) of the above powertrain concept. First, a control strategy for the non-predictive EMS’s start/stop functionality and optimization of the torque split between the combustion engine and electric machine is developed and calibrated for efficient engine operation depending on the battery state of charge. In addition, a predictive EMS’s control strategy is developed that uses horizon information of the driving route for optimal utilization of electrical energy within the prediction horizon, thereby further enhancing fuel consumption reduction. The predictive EMS uses Adaptive Equivalent Consumption Minimization Strategy (A-ECMS) with Pontryagin’s Minimization Principle (PMP) for online equivalence factor adaptation, providing local optimal solutions in real-time. The study concludes with the energy savings achieved through the implementation of these strategies using real-world driving cycles in the heavy-duty transport sector.

Research on the adaptability of energy management to thermal management of PEMFCs

Abstract The stable output of power and the effective control of stack temperature play a very important role in the durability and stability of fuel cell hybrid vehicles. In actual working conditions, energy management of power system and thermal management of Proton Exchange Membrane Fuel Cells (PEMFCs) need to be coordinated with each other to jointly ensure the efficient and stable operation of vehicles, however, most of the research in these two directions is independent. In response to the research gaps mentioned above, the concept of adaptability has been proposed for the first time with the aim of combining these two systems for research. This paper takes the fuel cell hybrid vehicle as the research object and establishes the energy management system and thermal management system model based on Matlab/Simulink software. In order to investigate the adaptability of energy management strategies to the temperature control system, two representative types of rule-based and optimization-based energy management strategies (power-following strategy, PFS, and adaptive equivalent hydrogen consumption minimization strategy, A-EHMS) are designed to be numerically simulated in the driving cycle condition of the UDDS, and then combined with the temperature control system of the fuel cell to comparatively analyze the above two types of energy management strategies from the perspectives of power allocation and the impact on the thermal management system. The results show that the PFS provides better protection for the battery under the same operating conditions. And from the perspective of fuel economy and adaptability to the temperature control system, the fuel consumption of A-EHMS is reduced by 12.5% and the adaptability to the temperature control system is improved by about 13.5% compared to PFS.

Scenario-oriented adaptive ECMS using speed prediction for fuel cell vehicles in real-world driving

To exploit the energy-saving potential and optimize the battery state of charge (SOC) maintaining capability of energy management strategies for fuel cell hybrid vehicles in specific driving scenarios, this study proposes a scenario-oriented adaptive equivalent consumption minimization strategy (SA-ECMS) based on a Nanjing-oriented driving cycle (NODC) and future speeds predicted via a hybrid neural network model. The proposed strategy determines the initial value of the equivalent factor (EF) and the proportional coefficient of the adaptive increment based on the NODC. Then, it periodically adjusts the EF via local optimization process according to the predicted speed to enhance scenario-specific adaptability and energy efficiency performance. Simulation results show that the hybrid neural network model achieves an average calculation time of 0.0033 s with a root-mean-square error of 0.85 m/s for 10 s prediction horizon, outperforming existing speed prediction models. Compared with the existing SOC feedback-based ECMS, the proposed SA-ECMS effectively suppresses the battery SOC within a narrower fluctuation range of −0.12% to 0.33%, achieves a deviation of only 0.0026 from the SOC reference value, and reduces the equivalent hydrogen-fuel consumption by 2.49% to 7.06 g/km.

Online battery aging calculation in plug-in hybrid electric vehicle considering driving condition

ABSTRACT Online calculation of battery capacity loss and its instantaneous remaining life for electric and hybrid electric vehicles is a challenging subject, particularly for designing and optimizing vehicle energy management in real-life driving conditions. This paper presents an online method for estimating plug-in hybrid electric vehicle battery degradation, considering the driving conditions. For this purpose, a national parallel plug-in hybrid electric vehicle is employed, where its components have been sized based on some experimental map characteristics using a genetic algorithm. Also, a real-world driving cycle is developed based on the data gathered in the actual traffic conditions in Tehran. The vehicle’s energy management system is designed using an adaptive equivalent consumption minimization strategy. In addition, an empirical battery life model combined with an online cycle counting method is used for battery aging calculation. To evaluate the effectiveness of the proposed approach, the capacity fade of the vehicle battery over various driving cycles has been calculated. The comparison of the results confirms the efficacy of the proposed algorithm compared to the Rainflow counting algorithm. Applying the Rainflow to all driving cycles yields consistent outcomes. However, when employing the suggested method, capacity losses of approximately 2.4%, 1.9%, 2.1%, and 1.4% are detected in Tehran, FTP-75, WLTP, and NEDC, respectively, following one hundred driving cycles. This means the capacity loss increases by 35%, 50%, and 71% for FTP-75, WLTP, and Tehran, respectively, compared with the NEDC driving cycle.

A controllable neural network-based method for optimal energy management of fuel cell hybrid electric vehicles

Neural Networks (NNs) can be used for energy management of hybrid vehicles, but they are hard to tune in inference to adapt to different driving conditions. To make the NN-based energy management strategy more flexible, this paper proposes a controllable NN for optimal energy management of fuel cell hybrid electric vehicles. Inspired by the equivalent factor in the Equivalent Consumption Minimization Strategy (ECMS), we introduce an adjustable target variable for the final state as an input to the NN-based strategy. During training, classification and regression networks with single-step and multi-step inputs are considered. An efficient shooting method and an adaptive method are then introduced to realize the precise control of the final state and online parameter adaptation. Simulations of the proposed method and the benchmarking method are carried out in different battery discharge modes. Results demonstrate that the proposed shooting neural classifier can achieve 99.7% fuel optimality of dynamic programming in a similar computational time to the shooting ECMS, and the proposed adaptive neural classifier can adapt to different driving conditions and has better fuel economy than the adaptive ECMS.

Improvised energy management control through neuro-fuzzy based adaptive ECMS approach for an optimal battery utilization in non-plugin parallel hybrid electric vehicle

This work proposed to integrate intelligent techniques in an adaptive equivalent consumption minimization strategy (AECMS) for a robust equivalence factor correction based on the demand torque and battery state of charge (SOC). The two intelligent approaches of fuzzy logic and genetic algorithmically optimized adaptive neuro-fuzzy inference system (ANFIS) have been employed. The entire performance is validated using the prepared three hybrid standard driving cycles and also for training the fuzzy inference system (FIS). The proposed ANFIS-ECMS delivers a narrow battery charging and discharging profile within the optimal battery utilization zone. Also, it delivers the higher fuel economy for the three driving cycles in the D1 4.20%, D2 1.175%, and D3 0.90% improvisation is occurred compared to fuzzy-PI AECMS. Even in the reliability assessment of ANFIS-AECMS, the performance has been tested on the self-developed real-world driving cycle. The fuel economy increases by 1.26% and 0.80% are compared to rule-based and fuzzy-PI AECMS. The entire results of this work evidence that the proposed strategy achieves significant improvement in battery and fuel energy utilization and also the reduction in emissions compared with rule-based, conventional fixed PI ECMS and fuzzy-PI based ECMS.

Reinforcement Learning‐Based Co‐Optimization of Adaptive Cruise Speed Control and Energy Management for Fuel Cell Vehicles

With the development of intelligent autodriving vehicles, the co‐optimization of speed control and energy management under the insurance of safe and comfortable driving has become a vital issue. Herein, the adaptive cruise control scenario is discussed. A co‐optimization method for speed control and energy management for fuel cell vehicles is suggested to delay the degradation of energy sources while preserving fuel cell efficiency. A reward function based on a reinforcement learning (RL) algorithm is developed to optimize the safety coefficient, comfortability, car‐following efficiency, and economy at the speed control level. The RL agent learns to control vehicle speed while avoiding collisions and maximizing the cumulative rewards. To handle the problem of energy management, an adaptive equivalent consumption minimization strategy, which takes into account the deterioration of energy sources, is implemented at the energy management level. The results indicate that the suggested method reduces the demand power by 1.7%, increases the lifetime of power sources, and reduces equivalent hydrogen consumption by 9.4% compared to the model predictive control.

Predictive hierarchical eco-driving control involving speed planning and energy management for connected plug-in hybrid electric vehicles

The connected vehicle technique has offered great opportunities to improve further plug-in hybrid electric vehicles (PHEVs) fuel economy. In this context, a predictive hierarchical eco-driving control scheme is proposed for connected PHEVs under a car-following scenario containing a cloud-layer speed planner and vehicle-layer energy management. In the cloud layer, based on the traffic data separately processed by the dynamic programming (DP) algorithm and k-means clustering method, the reference state of charge (SOC) model, the energy consumption model, the equivalent factor model and the variable-horizon speed predictor can be constructed, respectively. And for ensuring safety, comfort and fuel economy in the car-following process, the energy and SOC models are used separately as the index and state equation in the data-driven speed planning problem. Then, with the driving pattern recognition technique, the power allocation under the planned speed can be conducted by integrating the adaptive equivalent consumption minimization strategy (ECMS) with the model predictive control (MPC), thus guaranteeing fuel economy, adaptability and near-global optimality with high computational efficiency. Compared with other strategies, the effectiveness and advantages of the proposed scheme are validated in the joint simulation platform of MATLAB/Simulink and GT-SUITE.

An improved A-ECMS energy management for plug-in hybrid electric vehicles considering transient characteristics of engine

The plug-in hybrid electric vehicles (PHEVs) are playing an increasingly important role in urban public transportation systems for their unique potential for energy saving and emission reduction. However, as an enabling technology for the cost-efficient operation of PHEVs, the current energy management strategies (EMSs) rarely consider the transient characteristics of the engine, especially the limit of engine transient performance and the extra fuel consumption due to engine state changes. To improve the energy-saving effect of EMSs, an optimization study on energy management considering engine transient characteristics for PHEV is carried out in this paper. Firstly, a high-precision transient fuel consumption model is established based on artificial neural network (ANN) to accurately evaluate the real fuel consumption of engine under steady and unsteady states. Secondly, an adaptive equivalent consumption minimization strategy (A-ECMS) is constructed for PHEV, and the engine transient performance boundary is defined in the strategy to avoid unreasonable engine power surge decision. Thirdly, the transient fuel consumption model is incorporated into the equivalent fuel consumption cost function of A-ECMS to fully consider the impact of engine transient fuel consumption on the real-time power allocation of PHEV. The results show that the improved strategy weakens the state fluctuation of the engine, and makes the engine run more smoothly, resulting in a 99.16% reduction in the extra fuel consumption due to engine state changes. Finally, the fuel economy of the PHEV under the combined driving cycle based on the C-WTVC improved by 3.37%.

Adaptive neuro fuzzy inference system-based energy management controller for optimal battery charge sustaining in biofuel powered non-plugin hybrid electric vehicle

In the hybrid electric vehicle, better performance can be acquired by implementing an optimized energy management strategy. The purpose of this work is to improve the efficiency of the energy management strategy for a biofuel-powered hybrid electric vehicle (HEV). The energy management system opted for this work is adaptive equivalent consumption minimization strategy (AECMS) with PI, fuzzy and adaptive neuro-fuzzy logic-based equivalence factor (EF) value adjustment. The appropriate selection of equivalence factor value in AECMS decides the optimal performance of an energy management. This entire work uses three standard combined driving cycles for training the intelligent controller and has been tested using a real-time driving cycle. The proposed adaptive neuro-fuzzy controller implemented in the AECMS energy management strategy provides the best results in terms of charging and discharging within defined operating limit of 40%-70% state of charge, delivers lower fuel economy and emissions compared to rule-based and fuzzy-PI AECMS. Adaptive neuro-fuzzy AECMS improves the fuel economy by 3% compared to 25.3 km/l of fuzzy-PI AECMS for the standard combined driving cycle (D1). Whereas for the D2 and D3 driving cycles 0.5–1% improvement has occurred. This work strives to prove that the proposed adaptive neuro-fuzzy AECMS controller is efficient and provide better fuel economy and lesser emissions.

Energy management of plug-in hybrid electric vehicles based on speed prediction fused driving intention and LIDAR

Driving intention and speed prediction are essential factors in the energy management of plug-in hybrid electric vehicles (PHEVs). This paper proposes an improved energy management strategy for the subject vehicle by speed prediction fused with driving intention and LIDAR data in a vehicle-following scenario. A driving intention recognition model is developed based on the gated recurrent unit (GRU), which takes the vehicle speed, throttle opening, and brake pedal force of the subject vehicle as input. Then integrating the LIDAR point cloud data and driving intention result of the subject vehicle to achieve more accurate speed prediction, where joint probabilistic data association and interacting multiple models methods are used to process LIDAR data. The more accurate speed prediction is then applied to design a prediction-informed adaptive equivalent consumption minimization strategy (PIA-ECMS) for real-time energy management optimization. Experimental results demonstrate the recognition accuracy of up to 88%, indicating that the driver’s driving intention can be identified effectively. The speed prediction has an error margin of no more than 5.9 km/h. Compared with existing adaptive ECMS without speed prediction, the proposed PIA-ECMS can enhance fuel economy by 1.3–2.7% while achieving better SOC charge sustainability.

Research on Energy Management for Ship Hybrid Power System Based on Adaptive Equivalent Consumption Minimization Strategy

This paper analyzes a hybrid power system containing a fuel cell (FC) and proposes an improved scheme involving the replacement of a single energy storage system with a hybrid energy storage system. In order to achieve a reasonable power distribution between fuel cells and energy storage units and stable operation of the power grid, an efficient energy management system (EMS) based on the equivalent consumption minimization strategy (ECMS) is proposed. To enhance the dynamic response capability of hybrid energy storage systems, a low-pass filter with a variable time constant based on the ultracapacitor SOC feedback is proposed. This paper describes the design of a fuzzy logic controller that adaptively improves the equivalent consumption minimization control strategy, adjusts the equivalent factor in real time, optimizes the operating points of the fuel cell system, and improves system efficiency. The simulation model of the fuel cell hybrid system was established using MATLAB/Simulink. The proposed adaptive equivalent consumption minimization strategy (A-ECMS) was simulated and compared to the state-based and fuzzy logic energy management systems under the simulation of the real operating conditions of the ship. The results show that the proposed strategy can maintain a fuel cell system efficiency above 60% under most operating conditions and can significantly suppress the fluctuation of a fuel cell’s output power. The proposed strategy outperforms the state-based and fuzzy logic-based EMS in terms of stabilizing the hybrid power system and reducing hydrogen consumption. The effectiveness of the proposed strategy has been verified.

Adaptive equivalent consumption minimization strategy based on road grade estimation for a plug-in hybrid electric truck

Road grade plays an important role in deciding power repartition and improving energy management performances. In this paper, instead of predictive energy management strategies where terrain information is obtained from GIS maps, an adaptive equivalent consumption minimization strategy (A-ECMS) considering current road grade information is proposed, aiming to design an instantaneous feedback supervisory controller based on the estimation of current road grade without using external devices. To achieve real-time control for a plug-in hybrid electric truck (PHET), the bounds of the optimal equivalent factor (EF) are analyzed considering comprehensive performances, then the sensitivity of EF is evaluated towards road grade. According to the effect of different road grade scenarios on control performances, the real-time EF adaptation is divided into two conditions, i.e. SOC-based adaptation and Estimation-based adaption. The proposed A-ECMS can achieve good performances on both fuel economy improvement and emission reduction, which approximates the results obtained from the DP algorithm, and the high computing load can be avoided for real-time implementation.

A real-time operational management strategy for vehicular hybrid propulsion system based on GRNN-AECMS

The driving characteristics of a hybrid propulsion system (HPS) depend on operational management strategies. However, the differences in output and response of various types of power sources make real-time management of operating conditions complex. In this study, an operational management strategy, which combines adaptive equivalent consumption minimization strategy (AECMS) and general regression neural network (GRNN), is proposed for optimizing power controls within hybrid power sources. Under this strategy, the optimal function of the AECMS is adaptively calculated by the load profile changes based on GRNN’s prediction results, and it is more suitable for the HPS. Furthermore, the proposed GRNN-AECMS method can minimize fuel consumption and meet requirements for power tracking. From simulation results, fuel consumption under GRNN-AECMS method can be reduced by 2.715 kg, or 31.8%.

Adaptive ECMS based on speed forecasting for the control of a heavy-duty fuel cell vehicle for real-world driving

Aiming at reducing pollutant emissions, hydrogen and fuel cell hybrid electric vehicles (FCVs) represent a promising technological solution. In this scenario, this paper proposes an adaptive energy management strategy (A-EMS) based on speed forecasting for a heavy-duty FCV, in order to achieve stable battery charge sustenance in realistic driving conditions. A validated and optimized fuel cell system model has been integrated into a complete vehicle model developed in the GT-Suite environment. A short-term velocity prediction layer based on a long short term memory (LSTM) neural network has been built in the A-EMS framework. The network has been trained and tested with realistic driving data simulated by GT-Real Drive for routes of the Trans-European Transport Network. The vehicle speed prevision has been realized over different forecasting horizons (5, 10, and 20 s). The adaptive equivalent consumption minimization strategy (A-ECMS) combined with short-term vehicle speed prediction is the A-EMS core algorithm of the presented work. Its results are here compared with the standard ECMS (S-ECMS) for four different driving cycles, including both standardized (HDDT) and realistic driving profiles. Three different European routes, with varying characteristics and from different countries, have been selected to test the proposed strategy in various conditions. The short-term prediction layer achieves satisfactory forecasting accuracy, with a RMSE ranging from 1.76 km/h to 13.37 km/h. The A-ECMS provides an improved by an order of magnitude battery charge sustenance, evaluated in terms of maximum battery state of charge (SoC) variation and fluctuation degree, with a hydrogen consumption increase ranging from 3.76% to 11.40% compared to the S-ECMS, for which the driving cycle is supposed to be known beforehand. As an example, in the HDDT cycle, the absolute maximum SoC variation and its fluctuation degree are lowered by about 76% and 79%, respectively. In conclusion, the proposed A-ECMS demonstrated that it is applicable for real driving conditions without prior knowledge of the driving cycle while improving battery charge sustaining for a FCV.

Adaptive Equivalent Consumption Minimization Strategy for Fuel Cell Buses Based on Driving Style Recognition

Driving style has a significant effect on the operating economy of fuel cell buses (FCBs). To reduce hydrogen consumption and prolong the fuel cell life of FCBs, this paper proposes an online adaptive equivalent consumption minimum strategy (A-ECMS) based on driving style recognition. Firstly, driving data from various drivers is collected, and a standard driving cycle is created. Neural networks are then used to identify driving conditions, and three fuzzy logic recognizers are developed to identify driving styles for different driving conditions. The driving style factor is associated with the equivalent factor using an optimization algorithm that incorporates hydrogen consumption cost and fuel cell degradation cost into the objective function. Simulation results demonstrate that the proposed A-ECMS can reduce equivalent hydrogen consumption, prolong fuel cell life, and result in a 6.2% reduction in total operating cost compared to the traditional method.

A predictive control strategy based on A-ECMS to handle Zero-Emission Zones: Performance assessment and testing using an HiL equipped with vehicular connectivity

Recently, several metropolitan cities introduced Zero-Emissions Zones where the use of the Internal Combustion Engine is forbidden to reduce localized pollutants emissions. This is particularly problematic for Plug-in Hybrid Electric Vehicles, which usually work in depleting mode. So, the risk of not having enough energy stored to carry out the driving mission and then paying a fee is substantial. This work presents a viable solution by exploiting vehicular connectivity to retrieve navigation data of the urban event along a selected route. The battery energy needed, in the form of a minimum State of Charge (SoC), is calculated by a Speed Profile Prediction algorithm and a Backward Vehicle Model. That value is then fed to both a Rule-Based Strategy, developed specifically for this application, and an Adaptive Equivalent Consumption Minimization Strategy (A-ECMS). The effectiveness of this approach has been tested with a Connected Hardware-in-the-Loop (C-HiL) on a driving cycle measured on-road, stimulating the predictions with multiple re-routings. The tests have been conducted with different initial SoC values for each strategy, showing a maximum error in the SoC prediction of 2.4% and up to 26.1% of CO2 saving with the A-ECMS.