Requirements regarding high fuel efficiency, low pollutants and CO 2 emission impact of the internal combustion (IC) engine results in high control calibration complexity. Modern IC engines are equipped with numerous electronically controlled subsystems, whose usage leads to almost exponential growth of stationary operating points that need to be evaluated and optimised. In that perspective, the methodology for fast preknowledge acquisition of examined system is presented through the application of Slow Dynamic Slope experiments -SDS. Continual slow change of a control parameter excites the system, in such a way, that allow obtaining of an approximately stationary operating regime, without the time-consuming operating point settling period. By analysing stationary-based approximation results of Slow Dynamic Slope experiments, conducted within the IC engine global operation domain (engine speed and load), certain zones could be identified. Within those zones, increased number of stationary tests is desirable in order to provide a more precise approximative model of observed engine output parameters. In this way, relatively fast dynamic SDS experiments could be used to optimise the stationarybased test plan leading to overall time savings dedicated to IC engine testing.
Significant research efforts are invested in the quest for solutions that will increase the fuel economy and reduce the environmental impacts of ICE-powered vehicles. The main objective of the study presented in this paper has been to analyze and assess the performance of a control methodology for a parallel hydraulic hybrid powertrain system of a transit bus. A simulation model of the vehicle has been calibrated by analyzing data obtained during an experiment conducted in real-world traffic conditions aboard a Belgrade transit bus. A Dynamic Programming optimization procedure has been applied on the calibrated powertrain model and an optimal configuration that minimizes the fuel consumption has been selected. A Neural Network-based, implementable control algorithm has then been formed through a machine learning process involving data from the optimal, non-implementable Dynamic Programming-based control. Several Neural Network configurations have been tested to obtain the best fuel economy for the range of conditions encountered during normal transit bus operation. It has been shown that a considerable fuel consumption reduction on the order of 30% could be achieved by implementing such a system and calibration method.
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.