Search

Advanced internal combustion engine technologies have afforded an increase in the number of controllable variables and the ability to optimize engine operation. Values for these variables are determined during engine calibration by means of a tabular static correlation between the controllable variables and the corresponding steady-state engine operating points to achieve desirable engine performance, for example, in fuel economy, pollutant emissions, and engine acceleration. In engine use, table values are interpolated to match actual operating points. State-of-the-art calibration methods cannot guarantee continuously the optimal engine operation for the entire operating domain, especially in transient cases encountered in the driving styles of different drivers. This article presents brief theory and algorithmic implementation that make the engine an autonomous intelligent system capable of learning the required values of controllable variables in real time while operating a vehicle. The engine controller progressively perceives the driver's driving style and eventually learns to operate in a manner that optimizes specified performance criteria. A gasoline engine model, which learns to optimize fuel economy with respect to spark ignition timing, demonstrates the approach. [DOI: 10.1115/1.4000819]

Modeling dynamic systems incurring stochastic disturbances for deriving a control policy is a ubiquitous task in engineering. However, in some instances obtaining a model of a system may be impractical or impossible. Alternative approaches have been developed using a simulation-based stochastic framework, in which the system interacts with its environment in real time and obtains information that can be processed to produce an optimal control policy. In this context, the problem of developing a policy for controlling the system's behavior is formulated as a sequential decision-making problem under uncertainty. This paper considers the problem of deriving a control policy for a dynamic system with unknown dynamics in real time, formulated as a sequential decision-making under uncertainty. The evolution of the system is modeled as a controlled Markov chain. A new state-space representation model and a learning mechanism are proposed that can be used to improve system performance over time. The major difference between the existing methods and the proposed learning model is that the latter utilizes an evaluation function, which considers the expected cost that can be achieved by state transitions forward in time. The model allows decision-making based on gradually enhanced knowledge of system response as it transitions from one state to another, in conjunction with actions taken at each state. The proposed model is demonstrated on the single cart-pole balancing problem and a vehicle cruise-control problem. [DOI: 10.1115/1.3117200]

The increasing complexity of engineering systems has motivated continuing research on computational learning methods toward making autonomous intelligent systems that can learn how to improve their performance over time while interacting with their environment. These systems need not only to sense their environment, but also to integrate information from the environment into all decision-makings. The evolution of such systems is modeled as an unknown controlled Markov chain. In a previous research, the predictive optimal decision-making (POD) model was developed, aiming to learn in real time the unknown transition probabilities and associated costs over a varying finite time horizon. In this paper, the convergence of the POD to the stationary distribution of a Markov chain is proven, thus establishing the POD as a robust model for making autonomous intelligent systems. This paper provides the conditions that the POD can be valid, and be an interpretation of its underlying structure. [DOI: 10.1115/1.3117202]

Compression ignition engine technologies have been advanced in the past decade to provide superior fuel economy and high performance. These technologies offer increased opportunities for optimizing engine calibration. Current engine calibration methods rely on deriving static tabular relationships between a set of steady-state operating points and the corresponding values of the controllable variables. While the engine is running, these values are being interpolated for each engine operating point to coordinate optimal performance criteria, e.g., fuel economy, emissions, and acceleration. These methods, however, are not efficient in capturing transient engine operation designated by common driving habits, e.g., stop-and-go driving, rapid acceleration, and braking. An alternative approach was developed recently, which makes the engine an autonomous intelligent system, namely, one capable of learning its optimal calibration for both steady-state and transient operating points in real time. Through this approach, while the engine is running the vehicle, it progressively perceives the driver's driving style and eventually learns to operate in a manner that optimizes specified performance criteria. The major challenge to this approach is problem dimensionality when more than one controllable variable is considered. In this paper, we address this problem by proposing a decentralized learning control scheme. The scheme is evaluated through simulation of a diesel engine model which learns the values of injection timing and variable geometry turbocharging vane position that optimize fuel economy and pollutant emissions over a segment of the FTP-75 driving cycle. [DOI: 10.1115/1.3019331]

Widespread use of alternative hybrid powertrains currently appears inevitable and many opportunities for substantial progress remain. The necessity for environmentally friendly vehicles, in conjunction with increasing concerns regarding U.S. dependency on foreign oil and climate change, has led to significant investment in enhancing the propulsion portfolio with new technologies. Recently, plug-in hybrid electric vehicles (PHEVs) have attracted considerable attention due to their potential to reduce petroleum consumption and greenhouse gas (GHG) emissions in the transportation sector. PHEVs are especially appealing for short daily commutes with excessive stop-and-go driving. However, the high costs associated with their components, and in particular, with their energy storage systems have been significant barriers to extensive market penetration of PHEVs. In the research reported here, we investigated the implications of motor/generator and battery size on fuel economy and GHG emissions in a medium duty PHEV. An optimization framework is proposed and applied to two different parallel powertrain configurations, pretransmission and post transmission, to derive the Pareto frontier with respect to motor/generator and battery size. The optimization and modeling approach adopted here facilitates better understanding of the potential benefits from proper selection of motor/generator and battery size on fuel economy and GHG emissions. This understanding can help us identify the appropriate sizing of these components and thus reducing the PHEV cost. Addressing optimal sizing of PHEV components could aim at an extensive market penetration of PHEVs. [ABSTRACT FROM AUTHOR]