Emission legislation has forced the pace of development of engine management functions. Legislation that will be applied to diesel engines during the period 2010-2020 continue to put great emphasis on both nitrogen oxides NOx and particulate matter (PM). With the increasing effort to reduce emissions and maintain fuel economy manufacturers are focussing on engine control. Engine control requires data acquisition and acquisition requires sensors, but hardware in the form of sensors adds further cost to the production. As a result, so called virtual sensors are introduced. These are estimators that predict the required data, which is costly to measure or simply incapable of measurement.In this paper a parallel neural network structure is built. It consists of three Non-linear autoregressive exogenous input (NLARX) neural network models used to predict the smoke emissions of a diesel engine operated in a Non-Road-TransientCycle. Existing resources from Matlab toolboxes are used in order to monitor both the cost and computational expenses of analysis. The data is re-ordered into training and validation sets and processed. To overcome the weakness of the neural network approach in respect of high frequency signals, the data is divided into layers to split up the frequencies and cut high amplitudes. Three horizontal layers of the signal are processed in parallel through independent NLARX-models and their performances are added to give an overall result.
Current control implementations for engines are proving unwieldy for emerging emissions standards and fuel economy demand. Calibration is becoming progressively more complex as the number of controlled variables increases. The issues are acute with diesels. We describe a project in which a detailed investigation of the fuel path dynamics in a modern engine is made. This is an initial work about diesel engine fuel path control. In order to facilitate the control development, a medium speed (1550 rpm) and low torque (250Nm) point is chosen to develop the control strategy as it is believed that this is the safe point to start with the fuel path work. The development of fuek path control is difficult as the nature of fuel injection parameters affects the whole engine performance significantly and quickly. This paper demonstrates a closed-loop control and an architecture of controllable injection for C6.6 engine based on predictive control that could control exhaust temperature, of nitrogen oxides (NOx) and particular matters (PM) without changing the fuel quantity at medium speed and low load point.
One of the most critical challenges ahead for diesel engines is to identify new techniques for fuel economy improvement without compromising emissions regulations. One technique is the precise control of air/fuel ratio, which requires the measurement of instantaneous fuel consumption. Measurement accuracy and repeatability for fuel rate is the key to successfully controlling the air/fuel ratio and real-time measurement of fuel consumption. The volumetric and gravimetric measurement principles are well-known methods for measurement of fuel consumption in internal combustion engines. However, the fuel flow rate measured by these methods is not suitable for either real-time control or real-time measurement purposes because of the intermittent nature of the measurements. This paper describes a technique that can be used to find the minimum data [consisting of data from just 2.5% of the non-road transient cycle (NRTC)] to solve the problem concerning discontinuous data of fuel flow rate measured using an AVL 733S fuel meter for a medium or heavy-duty diesel engine using neural networks. Only torque and speed are used as the input parameters for the fuel flow rate prediction. Power density analysis is used to find the minimum amount of the data. The results show that the nonlinear autoregressive model with exogenous inputs could predict the particulate matter successfully with R(2) above 0.96 using 2.5% NRTC data with only torque and speed as inputs.
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.