Computationally Efficient Reduced-Order Powertrain Model of a Multi-Mode Plug-In Hybrid Electric Vehicle for Connected and Automated Vehicles

Rama, Neeraj; Robinette, Darrell

doi:10.4271/2019-01-1210

Cited by 13 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A significant contributor to the high computational power requirements of MPC is the inherent complexity of the model, often characterized by nonlinearity and a high order. Various approaches have been devised to address this challenge, including the development of linearized building models [38], online-linearization techniques [39], and developing reducedorder models of system dynamics, as seen in [40], [41], which enable faster optimization and control computations. Leveraging artificial intelligence to emulate MPC and reduce the computational burden is another effective approach, as demonstrated by [42], which utilized artificial neural networks to dramatically shorten the computation time of MPC in solar parabolic-trough plants, offering an efficient solution for computational optimization.…”

mentioning

confidence: 99%

Neural-Network Based MPC for Enhanced Lateral Stability in Electric Vehicles

Hassan,

Ruiz-Moreno,

Frejo

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Distributed electric drive vehicles offer maneuver-ability but face stability challenges under different driving conditions. Model Predictive Control (MPC) algorithms can improve lateral stability, but their high computational demands hinder real-time implementation. To address this, the proposed strategy combines Nonlinear Autoregressive Exogenous (NARX) neural networks with MPC in two ways, namely, Nonlinear Prediction-Nonlinear Optimization (NMPC-NO) and Nonlinear Prediction-Linearization (MPC-NPL). While NMPC-NO involves online nonlinear optimization, MPC-NPL uses local linearization, reducing both the computational load significantly to about 40% of the computation time of MPC and 0.05% of that of nonlinear model predictive control (NMPC). The neural networks are trained and validated on 20 different datasets, with alternative training methods investigated. MATLAB/Simulink simulations under various standardized tests demonstrate the effectiveness of the proposed techniques, highlighting improved handling performance, reduced computation time, and real-time deployment capabilities. Recent research underscores Direct Yaw Moment Control (DYC) as effective for improving handling stability [6]-[8]. DYC comprises two control levels, with the upper controller

show abstract

mentioning

confidence: 99%

Neural-Network Based MPC for Enhanced Lateral Stability in Electric Vehicles

Hassan,

Ruiz-Moreno,

Frejo

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The possible conditions for turning off the engine is when the required Once the signal to turn OFF the engine is received, the controller uses a model to predict when the engine would need to turn on later, using the route velocity profile and elevation data. Once, the period of predicted engine off is available, the controller uses the Reduced-Order Powertrain model [3] to predict the energy that would be needed by the vehicle to operate during the period. The look ahead horizon for this optimizer is the period between the time at which the Engine ON signal is generated to the predicted Engine OFF instant.…”

Section: Engine Start-stop Optimizermentioning

confidence: 99%

Energy Consumption and Savings Analysis of a Phev in Real World Driving Through Vehicle Connectivity Using Vehicle Platooning, Blended Mode Operation and Engine Start-Stop Optimizers

Santhosh¹

View full text Add to dashboard Cite

“…The output of this model is energy consumption in megajoules. More information about this model can be found in [54].…”

Section: Energy Modelmentioning

confidence: 99%

Real-Time Predictive Control of Connected Vehicle Powertrains for Improved Energy Efficiency

Oncken¹

View full text Add to dashboard Cite

show abstract

Computationally Efficient Reduced-Order Powertrain Model of a Multi-Mode Plug-In Hybrid Electric Vehicle for Connected and Automated Vehicles

Cited by 13 publications

References 15 publications

Neural-Network Based MPC for Enhanced Lateral Stability in Electric Vehicles

Neural-Network Based MPC for Enhanced Lateral Stability in Electric Vehicles

Energy Consumption and Savings Analysis of a Phev in Real World Driving Through Vehicle Connectivity Using Vehicle Platooning, Blended Mode Operation and Engine Start-Stop Optimizers

Real-Time Predictive Control of Connected Vehicle Powertrains for Improved Energy Efficiency

Contact Info

Product

Resources

About