Multi Time-Scale Engine and Powertrain Control for Autonomous Vehicles via Lagrange Multipliers

Connected and Autonomous vehicles (CAVs) have the ability to use information obtained via Vehicle-to-Infrastructure (V2I), Vehicle-to-Vehicle communication (V2V), and sensors to improve their fuel economy through predictive strategies, including velocity trajectory optimization and optimal traffic light arrival and departure. These powertrain control strategies operate on a slow timescale relative to the engine dynamics, hence assume that the engine torque production is instantaneous. This assumption results in a torque command profile that may lead to engine dynamics constraint violation, actuator saturation, poor tracking performance, decreased efficiency, poor drivability, and increased emissions. To address this issue, a supplemental controller based on an iterative hierarchical Model Predictive Control (MPC) is proposed in this paper. The constraint satisfaction is achieved through a novel two-way communication of the Lagrange multipliers. The proposed methodology is demonstrated on an autonomous Diesel semi-truck on two maneuvers. Compared to a traditional centralized approach, the proposed method achieves systematic constraints satisfaction with negligible effect on fuel economy, less than 1%, and significantly improved computation time, more than 10 times.

Transient Hybrid Electric Vehicle Powertrain Control Based on Iterative Dynamic Programing

This research proposes an iterative dynamic programing (IDP) algorithm that generates an optimal supervisory control policy for hybrid electric vehicles (HEVs) considering transient powertrain dynamics. The proposed algorithm tries to solve the “curse of dimensionality” and the “curse of modeling” of conventional dynamic programing (DP). The proposed IDP algorithm iteratively updates the DP formulation using a machine learning-based powertrain model. The machine learning model is recursively trained using the outputs from the driving cycle simulation with a high-fidelity model. Once the reduced model converges to the high-fidelity model accuracy, the resulting control policy yields a 9.1% fuel economy (FE) improvement compared to the baseline nonpredictive rule-based control for the urban dynamometer driving schedule (UDDS) driving cycle. A conventional DP control strategy based on a quasi-static powertrain model and a perfect preview of future power demand yields 14.2% FE improvement. However, the FE improvement reduces to 5.7% when the policy is validated with the high-fidelity model. It is concluded that capturing the transient powertrain dynamics is critical to generating a realistic fuel economy prediction and relevant powertrain control policy. The proposed IDP strategy employs targeted state-space exploration to leverage the improving state trajectory from previous iterations. Compared to conventional fixed state-space sampling methods, this method improves the accuracy of the DP policy against discretization error. It also significantly reduces the computational load of the relatively high number of states of the transient powertrain model.

Multiple Sensor Fail-Operational Architecture for Electric Vehicle Powertrain Control System

With the expanding demand to meet specific safety requirements, a new definition of the architecture at the system level is required to keep the powertrain system still operational after the fault emerge of some sensors. This work proposes a fail-operational architecture by integrating battery management and motor control system, which implements heterogeneous sensor signal reconstruction and model-based signal estimation for redundant signal generation and adopts random forest for signal arbitration. The proposed architecture can reduce the system failure rate and allow a fault-toleration of up to three sensors at any given time without increasing costs. Finally, the proposed architecture was verified by comparing the fault detection performance among three arbitration algorithms in a model in the loop (MIL) platform.