A series hybrid powertrain provides ultimate freedom in controlling the engine. The flexibility enabled with hybridization creates chances for a synergistic approach, in which the hybrid supervisory control can be augmented to address both the emissions and the efficiency. In this paper, two policy optimization techniques are proposed, namely stochastic dynamic programming and neurodynamic programming, for designing power management controllers. These controllers are then compared with a baseline rule-based controller. The intention is to investigate the additional benefits possible through application of policy optimization algorithms and a systematic framework capable of representing complex system-level effects. The power management of a series hydraulic hybrid vehicle is pursued as a sequential decision-making problem under uncertainty (stochastic control). The low energy density of the hydraulic accumulator adds to the control challenge. First, stochastic dynamic programming and neurodynamic programming are applied to design a controller based on the fuel economy objective. The problem is subsequently expanded to include minimization of transient diesel engine emissions. This poses additional challenges due to the increased state space. The problem is computationally intractable by stochastic dynamic programming and is solved using the newly proposed neurodynamic programming framework. Finally, the supervisory controllers are implemented and evaluated using simulations and an engine-in-the-loop facility. It is shown that, by designing an intelligent multi-objective controller, significant reduction in both the fuel consumption and the emissions can be achieved compared with strategies which focus solely on the fuel consumption.
A series hydraulic hybrid concept (SHHV) has been explored as a potential pathway to an ultra-efficient city vehicle. Intended markets would be congested metropolitan areas, particularly in developing countries. The target fuel economy was ~100 mpg or 2.4 l/100km in city driving. Such an ambitious target requires multiple measures, i.e. low mass, favorable aerodynamics and ultra-efficient powertrain. The series hydraulic hybrid powertrain has been designed and analyzed for the selected light and aerodynamic platform with the expectation that (i) series configuration will maximize opportunities for regeneration and optimization of engine operation, (ii) inherent high power density of hydraulic propulsion and storage components will yield small, lowcost components, and (iii) high efficiency and high power limits for accumulator charging/discharging will enable very effective regeneration. The simulation study focused on the SHHV supervisory control development, to address the challenge of the low storage capacity of the accumulator. Two approaches were pursued, i.e. the thermostatic SOC control, and Stochastic Dynamic Programming for horizon optimization. The stochastic dynamic programming was setup using a set of naturalistic driving schedules, recorded in normal traffic. The analysis included additional degree of freedom, as the engine power demand was split into two variables, namely engine torque and speed. The results represent a significant departure from the conventional wisdom of operating the engine near its "sweet spot" and indicate what is preferred from the system standpoint. Predicted fuel economy over the EPA city schedule is ~93 mpg with engine idling, and ~110 mpg with engine shutdowns.
Diesel engine combustion and emission formation is highly nonlinear and thus creates a challenge related to engine diagnostics and engine control with emission feedback. This paper presents a novel methodology to address the challenge and develop virtual sensing models for engine exhaust emission. These models are capable of predicting transient emissions accurately and are computationally efficient for control and optimization studies. The emission models developed in this paper belong to the family of hierarchical models, namely the “neuro-fuzzy model tree.” The approach is based on divide-and-conquer strategy, i.e., to divide a complex problem into multiple simpler subproblems, which can then be identified using a simpler class of models. Advanced experimental setup incorporating a medium duty diesel engine is used to generate training data. Fast emission analyzers for soot and NOx provide instantaneous engine-out emissions. Finally, the engine-in-the-loop is used to validate the models for predicting transient particulate mass and NOx.
This paper proposes a self-learning approach to develop optimal power management with multiple objectives, e.g. to minimize fuel consumption and transient engine-out NOx and particulate matter emission for a series hydraulic hybrid vehicle. Addressing multiple objectives is particularly relevant in the case of a diesel powered hydraulic hybrid since it has been shown that managing engine transients can significantly reduce real-world emissions. The problem is formulated as an infinite time horizon stochastic sequential decision making/markovian problem. The problem is computationally intractable by conventional Dynamic programming due to large number of states and complex modeling issues. Therefore, the paper proposes an online self-learning neural controller based on the fundamental principles of Neuro-Dynamic Programming (NDP) and reinforcement learning. The controller learns from its interactions with the environment and improves its performance over time. The controller tries to minimize multiple objectives and continues to evolve until a global solution is achieved. The control law is a stationary full state feedback based on 5 states and can be directly implemented. The controller performance is then evaluated in the Engine-in-the-Loop (EIL) facility.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.