Neural learning of driving environment prediction for vehicle power management

Murphey, Yi Lu; Chen, Zhi Hang; Kiliaris, L.; Park, Jungme; Kuang, Ming; Masrur, Abul; Phillips, Anastasia

doi:10.1109/ijcnn.2008.4634337

Cited by 33 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vehicle telemetry mining in the automotive domain has been applied in various domains, including safety improvement, fault detection, and efficiency gains (Crossman, Guo, Murphey, & Cardillo, 2003;Murphey, Crossman, Chen, & Cardillo, 2003;Murphey et al, 2008;Kruse, Steinbrecher, & Moewes, 2010;X. Huang, Tan, & He, 2011).…”

Section: Data Mining Of the Dmdmentioning

confidence: 99%

Investigating the Feasibility of Vehicle Telemetry Data as a Means of Predicting Driver Workload

Taylor

Griffiths

Bhalerao

et al. 2017

International Journal of Mobile Human Computer Interaction

View full text Add to dashboard Cite

Driving is a safety critical task that requires a high level of attention and workload from the driver. Despite this, people often also perform secondary tasks such as eating or using a mobile phone, which increase workload levels and divert cognitive and physical attention from the primary task of driving. If a vehicle is aware that the driver is currently under high workload, the vehicle functionality can be changed in order to minimize any further demand. Traditionally, workload measurements have been performed using intrusive means such as physiological sensors. Another approach may be to use vehicle telemetry data as a performance measure for workload. In this paper, we present the Warwick-JLR Driver Monitoring Dataset (DMD) and analyse it to investigate the feasibility of using vehicle telemetry data for determining the driver workload. We perform a statistical analysis of subjective ratings, physiological data, and vehicle telemetry data collected during a track study. A data mining methodology is then presented to build predictive models using this data, for the driver workload monitoring problem

show abstract

Section: Data Mining Of the Dmdmentioning

confidence: 99%

Investigating the Feasibility of Vehicle Telemetry Data as a Means of Predicting Driver Workload

Taylor

Griffiths

Bhalerao

et al. 2017

International Journal of Mobile Human Computer Interaction

View full text Add to dashboard Cite

show abstract

“…Based on the traditional gearbox power loss [16], the power loss of hybrid transmission system could be expressed as Fig. 7.…”

Section: Components Power Loss and Transmission Efficiency Modelmentioning

confidence: 99%

Neural network and efficiency-based control for dual-mode hybrid electric vehicles

Wang

Chen

2015

2015 34th Chinese Control Conference (CCC)

View full text Add to dashboard Cite

Now hybrid electric vehicle (HEV) control strategies are mainly aiming at the optimal fuel economy. The performance of most control strategies depends on the driving cycle pre-known. Changing driving condition will influence the optimal results greatly. Therefore, a neural network controller (NNC) is proposed for a dual-mode hybrid vehicle, which can improve fuel efficiency and maintain battery's state of charge (SOC) in most driving conditions. The NNC combined with an efficiency-based strategy can further reducing vehicle fuel consumption by improving the transmission efficiency. The proposed NNC is testified through the hardware-in-the-loop simulation. The test results show that, the control strategy combined neural network and efficiency-based strategy can reduce vehicle fuel consumption and control the battery SOC in a reasonable range. The control strategy has good prospects in the controller design for dual-mode HEVs.

show abstract

“…In addition, in the study of Carter et al, the rule‐based control strategy is proposed, but the method is analyzed from the cost performance further without the whole vehicle performance; the dual closed‐loop control structure is adopted, the outer loop is used to acquire the best size of HESS, although the algorithm parameters are adjusted in the inner loop, the structure is depended on the rules, and the results cannot be optimized . In recent years, the intelligent control methods such as neural network and fuzzy control are also applied in vehicle energy management technology, when the fuel consumption and gas emissions are as design indicators; the data of different road cycles can be trained to predicted the vehicle behavior on the neural network model; the neural network is used to predict road cycles and traffic jam degree online for energy management; in the study of Millo et al, the energy management system for hybrid electric vehicle (HEV) with HESS is developed on the neural network; in the study of Marie et al, the neural network is used to manage the power flow between the storage energy system and the load. Fuzzy control has strong robustness, which is applied in the vehicle management strategy; in the fuzzy controller, the control rules are designed based on the driving command, the state of charge (SOC) of the battery, and the vehicle speed; the output variables are the reasonable power distribution between the motor and the engine; the aim of adopting fuzzy control is to optimize the drive system and improve the battery recovery efficiency; in the study of Dawei et al, the fuzzy energy management strategy is used to the power flow for uniaxial parallel hybrid vehicle; the membership functions in the controller are optimized by genetic algorithm; the results show fuzzy control can effectively avoid the production of the engine peak torque and improve the overall vehicle performance.…”

Section: Introductionmentioning

confidence: 99%

Energy flow analysis of an electric city bus based on wavelet transform with Mallet prolongation

Zhang

Meng

Zhou

et al. 2017

Int. Trans. Electr. Energ. Syst.

View full text Add to dashboard Cite

In this paper, we propose a Haar wavelet with Mallet prolongation energy management strategy, a pure electric city bus produced by CENS Energy Tech Co, Ltd with a hybrid energy storage system that combines a lithium battery with an ultracapacitor is tested and modeled under a MATLAB-CRUISE joint simulation environment based on the experiments. In verifying its validity, the proposed method is compared with the common rule-based control strategy from the charging and discharging characteristics of the battery, the feedback efficiency of the ultracapacitor, and the overall system efficiency during China City Road Cycle. The results show in the proposed method that state of charge of the battery is more stable avoiding from the peak current shock, the battery life has been protected effectively, the ultracapacitor has been utilized more fully, and the vehicle performance is better for the tracking performance and control flexibility than the rule-based control strategy. KEYWORDS energy flow analysis, Haar wavelet, hybrid energy storage system (HESS), Mallat prolongation 1 | INTRODUCTIONHigh-energy consumption and traffic pollution have become serious problems in China. Electric vehicles, which emit no pollutants or environmentally harmful gases, offer a promising solution but are hampered by short driving range and limited battery life. To overcome this problem, in recent years, many researchers have proposed hybrid storage energy systems (HESS) with additional energy storage devices, such as fuel cells and ultracapacitors. 1,2 Under the conditions of the identified vehicle type and road conditions, the management strategy for controlling the power flow is regarded as research hotspot, the power flow between the elements of HESS, and drive system is equally worthy of further study. 3 Although there are numerous results and related literatures in researching vehicle energy management methods, these are relatively more dispersed and HESS is rarely mentioned together. Because of the cost functions being expressed as the vehicle's performance indicators, the optimal control is the most commonly used method in the energy management analysis, in which the driving conditions are known. However, this method is not suitable for real-time vehicle control, only providing a method to solve the offline problem. 4,5 Dynamic programming (DP) is a typical control method in optimal control; in the operation process, the overall decision making is gradually shifted. This multiple-step optimal control problem is converted into several single-step ones. This greatly simplifies the overall solution process. In the study of Kobayashi and Miyatake, 6 DP is adopted to reduce the fuel consumption for parallel hybrid electric vehicles (PHEVs) with HESS; similarly, the fuel economy, battery life, and cost for PHEV with HESS are compared with sole energy storage while DP is used in the study of Ou and Sun. 7 Dynamic programming is very conventional to solve the optimal control problem. However, the more dimensions of the problem, the longer ca...

show abstract

Neural learning of driving environment prediction for vehicle power management

Cited by 33 publications

References 9 publications

Investigating the Feasibility of Vehicle Telemetry Data as a Means of Predicting Driver Workload

Investigating the Feasibility of Vehicle Telemetry Data as a Means of Predicting Driver Workload

Neural network and efficiency-based control for dual-mode hybrid electric vehicles

Energy flow analysis of an electric city bus based on wavelet transform with Mallet prolongation

Contact Info

Product

Resources

About