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.

No abstract

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.

No abstract

This paper presents the modeling and control of an opposed piston (OP) engine in a novel hybrid architecture. The OP engine was selected for this work due to the inherent thermody-namic benefits and the balanced nature of the engine. The typical geartrain required on an OP engine was exchanged for two electric motors, significantly reducing friction and decoupling the crankshafts. By using the motors to control the crankshaft motion profiles, this configuration introduces capabilities to dynamically vary compression ratio, combustion volume, and scavenging dynamics. To realize these opportunities, a model of the system capturing the instantaneous engine dynamics is essential along with methodology to regulate the crankshaft’s rotational dynamics utilizing the electric motors. The modeling presented here couples a 1D model capturing the gas exchange process during scavenging and a 0D model of the crankshaft dynamics and the heat release profile due to combustion. With the use of this model, a linear quadratic controller with reference feedforward was designed to track the crankshaft motion trajectory. Experimental results are used to validate the model and controller performance. These results highlight the sensitivity to model uncertainty at points with high cylinder pressure, leading to large differences in control input near minimum volume. The proposed controller is, however, still able to maintain tracking error for crankshaft position below ± 1 degree.