Energy Management Strategy of Hybrid Electric Vehicles Based on Driving Condition Prediction

Liu, Qifang; Dong, Shiying; Yang, Zheng; Xu, Fang; Chen, Hong

doi:10.1016/j.ifacol.2021.10.174

Cited by 6 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cadete et al (2021) studied long short-term memory and autoregressive and moving average models to predict charging loads with temporal profiles from three EV charging stations [24]. modeled a driving condition prediction model based on a BP neural network for parallel hybrid electric vehicles [25]. Zhao et al (2021) presented a novel data-driven framework for large-scale charging energy predictions by individually controlling the strongly linear and weakly nonlinear contributions of EVs [26].…”

Section: Related Work and Motivationsmentioning

confidence: 99%

“…Variants of machinelearningtechniques Only for short-term prediction Zhang et al (2020) [12] Extreme learning machine algorithm Stuck with algorithmic stagnation issues Sun et al (2020) [14] Hybrid artificial intelligence techniques Accuracy was not guaranteed due to rule base employed Thorgeirsson et al (2021) [22] Probabilistic prediction models Invariant time frame of analysis Shahriar et al (2021) [23] Hybrid Machine learning algorithms Longer session duration of prediction with higher error Cadete et al (2021) [24] Autoregressive and moving average models Higher error variations with minimized accuracy Liu et al (2021) [25] Back propagation neural network Over-fitting and under-fitting problems Zeng et al (2021) [32] Optimization-oriented adaptive training predictor Difficulty in data sharing Ye et al (2021) [34] Deep learning algorithm Increased layer complexity and delayed convergence Asensio et al (2022) [44] Kalman Filter scheme and auto regressive models Difficulty in handling temporal files [45] Intelligent sensing system Difficulty in handling non-linear time dependent data…”

Section: Conflicts Of Interestmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning LSTM Recurrent Neural Network Model for Prediction of Electric Vehicle Charging Demand

Shanmuganathan

Victoire

Balraj³

et al. 2022

Sustainability

View full text Add to dashboard Cite

The immense growth and penetration of electric vehicles has become a major component of smart transport systems; thereby decreasing the greenhouse gas emissions that pollute the environment. With the increased volumes of electric vehicles (EV) in the past few years, the charging demand of these vehicles has also become an immediate requirement. Due to which, the prediction of the demand of electric vehicle charging is of key importance so that it minimizes the burden on the electric grids and also offers reduced costs of charging. In this research study, an attempt is made to develop a novel deep learning (DL)-based long-short term memory (LSTM) recurrent neural network predictor model to carry out the forecasting of electric vehicle charging demand. The parameters of the new deep long-short term memory (DLSTM) neural predictor model are tuned for its optimal values using the classic arithmetic optimization algorithm (AOA) and the input time series data are decomposed so as to maintain their features using the empirical mode decomposition (EMD). The novel EMD—AOA—DLSTM neural predictor modeled in this study overcomes the vanishing and exploding gradients of basic recurrent neural learning and is tested for its superiority on the EV charging dataset of Georgia Tech, Atlanta, USA. At the time of simulation, the best results of 97.14% prediction accuracy with a mean absolute error of 0.1083 and a root mean square error of 2.0628 × 10−5 are attained. Furthermore, the mean absolute error was evaluated to be 0.1083 and the mean square error pertaining to 4.25516 × 10−10. The results prove the efficacy of the prediction metrics computed with the novel deep learning LSTM neural predictor for the considered dataset in comparison with the previous techniques from existing works.

show abstract

Section: Related Work and Motivationsmentioning

confidence: 99%

Section: Conflicts Of Interestmentioning

confidence: 99%

Deep Learning LSTM Recurrent Neural Network Model for Prediction of Electric Vehicle Charging Demand

Shanmuganathan

Victoire

Balraj³

et al. 2022

Sustainability

View full text Add to dashboard Cite

show abstract

“…Research on vehicle condition prediction is mainly divided into two categories: known and unknown driving conditions [22][23][24]. The known driving cycle refers to the driving process on a fixed route.…”

Section: Introductionmentioning

confidence: 99%

Equivalent Consumption Minimization Strategy of Hybrid Electric Vehicle Integrated with Driving Cycle Prediction Method

Yao

Zheng

et al. 2023

Machines

View full text Add to dashboard Cite

Hybrid electric vehicles that can combine the advantages of traditional and new energy vehicles have become the optimal choice at present in the face of increasingly stringent fuel consumption restrictions and emission regulations. Range-extended hybrid electric vehicles have become an important research topic because of their high energy mixing degree and simple transmission system. A compact traditional fuel vehicle is the research object of this study and the range-extended hybrid system is developed. The design and optimization of the condition prediction energy management strategy are investigated. Vehicle joint simulation analysis and bench test platforms were built to verify the proposed control strategy. The vehicle tracking method was selected to collect real vehicle driving data. The number of vehicles in the field of view and the estimation of the distances between the front and following vehicles are calculated by means of the mature algorithm of the monocular camera and by computer vision. Real vehicle cycle conditions with driving environment and slope information were constructed and compared with all driving data, typical working conditions under NEDC, and typical working conditions under UDDS. The BP neural network and fuzzy logic control were used to identify the road conditions and the driver’s intention. The results showed that the equivalent fuel consumption of the control strategy was lower than that of the fixed-point power following control strategy and vehicle economy improved.

show abstract

“…Among the examples of new technology includes combustion cylinder deactivation (CDA) [5][6][7], gasoline direct injection (GDI) [8][9][10], variable valve timing and lift [11,12]. Some manufacturer even introduces more radical solutions to decrease the emission and obtain more energy efficient vehicle through introduction to electric hybrid vehicle and fully electric vehicle [13][14][15][16][17]. Other than that, car manufacturers also use downsized engine to achieve lower emission level together with lower fuel consumption.…”

Section: Introductionmentioning

confidence: 99%

Heat Generation Inside Turbocharger Without External Heat Source

Hamzah

Alias²

2022

ARFMTS

View full text Add to dashboard Cite

Recently, many vehicle manufacturers started to invest in new technology to reduce the emission produced by their engines. Due to the emission regulations that become more stringent and the rising demand for highly efficient vehicles, many new technologies were introduced to achieve the demand. One of the technologies that gain popularity in modern vehicles is applying force induction systems such as turbocharging and supercharging the engine. By using the turbocharger, two major advantages can be achieved which are increasing engine efficiency and engine size reduction. However, turbocharger performance will be affected by the amount of heat that is generated due to friction inside the bearing, air compression process and also the heat transfer from the exhaust gas that has high temperature and pressure. In this paper, the heat generation inside the turbocharger unit without any external heat source was measured and analysed. A turbocharger unit from Garrett Turbocharger where the model is GT2056 was used for this experiment. The operating speed in the study is recorded between 20 000 rpm until 70 000 rpm and the temperature at the turbine inlet and compressor inlet is at room temperature. The parameters that were measured are the temperature difference at the turbine side, bearing housing and also compressor side. From the results obtained, it can be concluded that the bearing housing produces a higher amount of heat compared to the compressor side while the turbine side will experience heat loss.

show abstract

Energy Management Strategy of Hybrid Electric Vehicles Based on Driving Condition Prediction

Cited by 6 publications

References 8 publications

Deep Learning LSTM Recurrent Neural Network Model for Prediction of Electric Vehicle Charging Demand

Deep Learning LSTM Recurrent Neural Network Model for Prediction of Electric Vehicle Charging Demand

Equivalent Consumption Minimization Strategy of Hybrid Electric Vehicle Integrated with Driving Cycle Prediction Method

Heat Generation Inside Turbocharger Without External Heat Source

Contact Info

Product

Resources

About