Effects of Artificial Neural Network Speed-Based Inputs on Heavy-Duty Vehicle Emissions Prediction

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" Effects of Artificial Neural Network Speed-Based Inputs on Heavy-Duty Vehicle Emissions Prediction "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	150808
Doc. No	:	ET22600
Main Entry	:	Nastaran Hashemi
Title Proper	:	Effects of Artificial Neural Network Speed-Based Inputs on Heavy-Duty Vehicle Emissions Prediction
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	iiThe PM split study was performed in Southern California on thirty-four heavydutydiesel vehicles using the West Virginia University Transportable Heavy-DutyVehicle Emissions Testing Laboratories to gather emissions data of these vehicles. Thedata obtained from six vehicles in the 1985-2001 model year and 33,000-80,000 lbweight range exercised through three different cycles were selected in this thesis. Topredict the instantaneous levels of oxides of nitrogen (NOx), carbon dioxide (CO2),hydrocarbons (HC) and carbon monoxide (CO), an Artificial Neural Network (ANN) wasused. Axle speed, torque, their rates of change over different time periods and two othervariables as a function of axle speed were defined as the inputs for the neural network.Also, each emissions species was considered individually as the output of the ANN. TheANN was trained on the Highway cycle and applied to the City/Suburban Heavy VehicleRoute (CSHVR) and Urban Dynamometer Driving Schedule (UDDS) with four differentsets of inputs to predict the emissions for these vehicles. The research showed anexcellent emissions prediction for the neural networks that were trained with only eightinputs (speed, torque, their first and second derivatives, and two variables of Diff. and-Spd related to the speed pattern over the last 150 seconds). The Diff variable provided ameasure of the variability of speed over the last 150 seconds of operation. This variablewas able to create a moving speed-dependant window, which was used as an input for theneural networks. The results showed an average accuracy of 0.97 percent for CO2, 0.89percent for NOx, 0.70 for CO and 0.48 percent for HC over the course of the CSHVR,Highway and UDDS.....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL45824.pdf
Title and statement of responsibility and	:	Effects of Artificial Neural Network Speed-Based Inputs on Heavy-Duty Vehicle Emissions Prediction [Thesis]