{"id":{"repo_id":"wvu","oai_identifier":"oai:researchrepository.wvu.edu:etd-2493"},"canonical_url":"https://search.dev.ndltd.org/etd/wvu/oai:researchrepository.wvu.edu:etd-2493","repository":{"repo_id":"wvu","name":"West Virginia University","base_url":"https://researchrepository.wvu.edu/do/oai/"},"display":{"title":"Effects of artificial neural network speed-based inputs on heavy-duty vehicle emissions prediction","abstract":"The PM split study was performed in Southern California on thirty-four heavy-duty diesel vehicles using the West Virginia University Transportable Heavy-Duty Vehicle Emissions Testing Laboratories to gather emissions data of these vehicles. The data obtained from six vehicles in the 1985--2001 model year and 33,000--80,000 lb weight range exercised through three different cycles were selected in this thesis. To predict the instantaneous levels of oxides of nitrogen (NOx), carbon dioxide (CO2), hydrocarbons (HC) and carbon monoxide (CO), an Artificial Neural Network (ANN) was used. Axle speed, torque, their rates of change over different time periods and two other variables 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. The ANN was trained on the Highway cycle and applied to the City/Suburban Heavy Vehicle Route (CSHVR) and Urban Dynamometer Driving Schedule (UDDS) with four different sets of inputs to predict the emissions for these vehicles. The research showed an excellent emissions prediction for the neural networks that were trained with only eight inputs (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 a measure of the variability of speed over the last 150 seconds of operation. This variable was able to create a moving speed-dependant window, which was used as an input for the neural networks. The results showed an average accuracy of 0.97 percent for CO2, 0.89 percent for NOx, 0.70 for CO and 0.48 percent for HC over the course of the CSHVR, Highway and UDDS.","abstract_html":"The PM split study was performed in Southern California on thirty-four heavy-duty diesel vehicles using the West Virginia University Transportable Heavy-Duty Vehicle Emissions Testing Laboratories to gather emissions data of these vehicles. The data obtained from six vehicles in the 1985--2001 model year and 33,000--80,000 lb weight range exercised through three different cycles were selected in this thesis. To predict the instantaneous levels of oxides of nitrogen (NOx), carbon dioxide (CO2), hydrocarbons (HC) and carbon monoxide (CO), an Artificial Neural Network (ANN) was used. Axle speed, torque, their rates of change over different time periods and two other variables 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. The ANN was trained on the Highway cycle and applied to the City/Suburban Heavy Vehicle Route (CSHVR) and Urban Dynamometer Driving Schedule (UDDS) with four different sets of inputs to predict the emissions for these vehicles. The research showed an excellent emissions prediction for the neural networks that were trained with only eight inputs (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 a measure of the variability of speed over the last 150 seconds of operation. This variable was able to create a moving speed-dependant window, which was used as an input for the neural networks. The results showed an average accuracy of 0.97 percent for CO2, 0.89 percent for NOx, 0.70 for CO and 0.48 percent for HC over the course of the CSHVR, Highway and UDDS.","abstract_has_math":false,"creators":["Hashemi, Nastaran"],"institution":null,"degree_name":"MS","degree_level":"Thesis","degree_discipline":"Mechanical and Aerospace Engineering","degree_department":null,"school":null,"contributors":["Nigel N. Clark."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2004,"date_issued":"2004-08-01T07:00:00Z","date_published":"2004-08-01T07:00:00Z","updated_at":"2026-07-24T06:15:47Z","subjects":["Mechanical engineering","Environmental engineering","Artificial intelligence"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://researchrepository.wvu.edu/etd/1490"],"render_values":[{"text":"https://researchrepository.wvu.edu/etd/1490","href":"https://researchrepository.wvu.edu/etd/1490","code":true}]}]},"links":{"outbound_url":"https://doi.org/10.33915/etd.1490","outbound_label":"DOI","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Nigel N. Clark."]},{"key":"dc:creator","label":"Author","values":["Hashemi, Nastaran"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-01-17T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mechanical and Aerospace Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Mechanical engineering","Environmental engineering","Artificial intelligence"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://doi.org/10.33915/etd.1490","https://researchrepository.wvu.edu/etd/1490"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The PM split study was performed in Southern California on thirty-four heavy-duty diesel vehicles using the West Virginia University Transportable Heavy-Duty Vehicle Emissions Testing Laboratories to gather emissions data of these vehicles. The data obtained from six vehicles in the 1985--2001 model year and 33,000--80,000 lb weight range exercised through three different cycles were selected in this thesis. To predict the instantaneous levels of oxides of nitrogen (NOx), carbon dioxide (CO2), hydrocarbons (HC) and carbon monoxide (CO), an Artificial Neural Network (ANN) was used. Axle speed, torque, their rates of change over different time periods and two other variables 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. The ANN was trained on the Highway cycle and applied to the City/Suburban Heavy Vehicle Route (CSHVR) and Urban Dynamometer Driving Schedule (UDDS) with four different sets of inputs to predict the emissions for these vehicles. The research showed an excellent emissions prediction for the neural networks that were trained with only eight inputs (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 a measure of the variability of speed over the last 150 seconds of operation. This variable was able to create a moving speed-dependant window, which was used as an input for the neural networks. The results showed an average accuracy of 0.97 percent for CO2, 0.89 percent for NOx, 0.70 for CO and 0.48 percent for HC over the course of the CSHVR, Highway and UDDS."]},{"key":"dc:title","label":"Title","values":["Effects of artificial neural network speed-based inputs on heavy-duty vehicle emissions prediction"]}]}],"canonical_facts":{"dc:contributor":["Nigel N. Clark."],"dc:creator":["Hashemi, Nastaran"],"dc:date.available":["2019-01-17T08:00:00Z"],"dc:description.abstract":["The PM split study was performed in Southern California on thirty-four heavy-duty diesel vehicles using the West Virginia University Transportable Heavy-Duty Vehicle Emissions Testing Laboratories to gather emissions data of these vehicles. The data obtained from six vehicles in the 1985--2001 model year and 33,000--80,000 lb weight range exercised through three different cycles were selected in this thesis. To predict the instantaneous levels of oxides of nitrogen (NOx), carbon dioxide (CO2), hydrocarbons (HC) and carbon monoxide (CO), an Artificial Neural Network (ANN) was used. Axle speed, torque, their rates of change over different time periods and two other variables 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. The ANN was trained on the Highway cycle and applied to the City/Suburban Heavy Vehicle Route (CSHVR) and Urban Dynamometer Driving Schedule (UDDS) with four different sets of inputs to predict the emissions for these vehicles. The research showed an excellent emissions prediction for the neural networks that were trained with only eight inputs (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 a measure of the variability of speed over the last 150 seconds of operation. This variable was able to create a moving speed-dependant window, which was used as an input for the neural networks. The results showed an average accuracy of 0.97 percent for CO2, 0.89 percent for NOx, 0.70 for CO and 0.48 percent for HC over the course of the CSHVR, Highway and UDDS."],"dc:identifier":["https://doi.org/10.33915/etd.1490","https://researchrepository.wvu.edu/etd/1490"],"dc:subject":["Mechanical engineering","Environmental engineering","Artificial intelligence"],"dc:title":["Effects of artificial neural network speed-based inputs on heavy-duty vehicle emissions prediction"],"thesis:degree_discipline":["Mechanical and Aerospace Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["MS"]},"updated_at":"2026-07-24T06:15:47Z"}