{"id":{"repo_id":"ets-quebec","oai_identifier":"oai:espace.etsmtl.ca:3138"},"canonical_url":"https://search.ndltd.org/etd/ets-quebec/oai:espace.etsmtl.ca:3138","repository":{"repo_id":"ets-quebec","name":"ETS (Quebec)","base_url":"https://espace.etsmtl.ca/cgi/oai2"},"display":{"title":"Hot mix asphalt volumetric optimization using artificial intelligence","abstract":"The empirical procedure of HMA volumetric design requires time and effort. This procedure is a common practice when adjusting the job formula due to eventual changes in aggregates and binder properties imposing upon asphalt plants. This empirical method is based on gradation specifications limits in which correlations between the desire state of voids and aggregate gradation remain unclear, thereby producing a material (HMA) with uncertain performance at which validation test is essential. This work compares 4 gradation factors in which aggregate gradation is quantified as a number. This evaluation permits knowing which gradation factor has the highest correlation with HMA volumetric properties, thereby reducing the endeavor implied in the empirical design due to a simple calculation of the factor could produce an effective estimation of volumetric properties. This study applies deep neural networks (DNNs) based on supervised machine learning method to predict two volumetric properties: 1) the maximum specific gravity (Gmm) which is obtained by running the Rice test and 2) the bulk specific gravity (Gmb) in which the aggregate packing is compacted when SGC test is applied, and asphalt binder content produces bulk density changes at the same level of energy compaction for the same aggregate blend. These neural networks are built based on aggregate and binder properties as input variables and HMA volumetric properties as output variables. These DNNs are training to use raw data collected from the Long-Term Pavement Performance (LTPP) database. This research explores how to accurately establish links between aggregate and binder properties with HMA volumetric properties (Gmb and Gmm). A strong correlation was found between the aggregate volumetric property Gsb and Gmm prediction. Moreover, the generalization of the Rice test phenomenon to adequately predict Gmm using DNNs could allow designers to precisely estimate the HMA volumetric property (Gmm), thus avoiding running this test to calculate the volumetric values.","abstract_html":"The empirical procedure of HMA volumetric design requires time and effort. This procedure is a common practice when adjusting the job formula due to eventual changes in aggregates and binder properties imposing upon asphalt plants. This empirical method is based on gradation specifications limits in which correlations between the desire state of voids and aggregate gradation remain unclear, thereby producing a material (HMA) with uncertain performance at which validation test is essential. This work compares 4 gradation factors in which aggregate gradation is quantified as a number. This evaluation permits knowing which gradation factor has the highest correlation with HMA volumetric properties, thereby reducing the endeavor implied in the empirical design due to a simple calculation of the factor could produce an effective estimation of volumetric properties. This study applies deep neural networks (DNNs) based on supervised machine learning method to predict two volumetric properties: 1) the maximum specific gravity (Gmm) which is obtained by running the Rice test and 2) the bulk specific gravity (Gmb) in which the aggregate packing is compacted when SGC test is applied, and asphalt binder content produces bulk density changes at the same level of energy compaction for the same aggregate blend. These neural networks are built based on aggregate and binder properties as input variables and HMA volumetric properties as output variables. These DNNs are training to use raw data collected from the Long-Term Pavement Performance (LTPP) database. This research explores how to accurately establish links between aggregate and binder properties with HMA volumetric properties (Gmb and Gmm). A strong correlation was found between the aggregate volumetric property Gsb and Gmm prediction. Moreover, the generalization of the Rice test phenomenon to adequately predict Gmm using DNNs could allow designers to precisely estimate the HMA volumetric property (Gmm), thus avoiding running this test to calculate the volumetric values.","abstract_has_math":false,"creators":["Useche, Jesus"],"institution":"École de technologie supérieure","degree_name":"Mémoire de maîtrise électronique","degree_level":"masters","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-11-24","date_published":"2022-11-24","updated_at":"2026-11-18T22:09:45Z","subjects":["enrobés, conception volumétrique, optimisation, intelligence artificielle, réseaux de neurones profonds pour la conception des enrobés"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["INSERT-YOUR-LIBRARY-ID-HERE3138"],"render_values":[{"text":"INSERT-YOUR-LIBRARY-ID-HERE3138","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null,"record_url":null,"record_label":null,"record_kind":null,"record_source":null,"download_url":"https://espace.etsmtl.ca/id/eprint/3138/1/USECHE_Jesus.pdf","download_label":"Download PDF","download_source":"dc:identifier","access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://espace.etsmtl.ca/cgi/oai2?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aespace.etsmtl.ca%3A3138","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Useche, Jesus"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-11-24"]},{"key":"dc:publisher","label":"Institution","values":["École de technologie supérieure"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Mémoire de maîtrise électronique"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["École de technologie supérieure"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["enrobés, conception volumétrique, optimisation, intelligence artificielle, réseaux de neurones profonds pour la conception des enrobés"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["INSERT-YOUR-LIBRARY-ID-HERE3138","https://espace.etsmtl.ca/id/eprint/3138/1/USECHE_Jesus.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The empirical procedure of HMA volumetric design requires time and effort. This procedure is a common practice when adjusting the job formula due to eventual changes in aggregates and binder properties imposing upon asphalt plants. This empirical method is based on gradation specifications limits in which correlations between the desire state of voids and aggregate gradation remain unclear, thereby producing a material (HMA) with uncertain performance at which validation test is essential. This work compares 4 gradation factors in which aggregate gradation is quantified as a number. This evaluation permits knowing which gradation factor has the highest correlation with HMA volumetric properties, thereby reducing the endeavor implied in the empirical design due to a simple calculation of the factor could produce an effective estimation of volumetric properties. This study applies deep neural networks (DNNs) based on supervised machine learning method to predict two volumetric properties: 1) the maximum specific gravity (Gmm) which is obtained by running the Rice test and 2) the bulk specific gravity (Gmb) in which the aggregate packing is compacted when SGC test is applied, and asphalt binder content produces bulk density changes at the same level of energy compaction for the same aggregate blend. These neural networks are built based on aggregate and binder properties as input variables and HMA volumetric properties as output variables. These DNNs are training to use raw data collected from the Long-Term Pavement Performance (LTPP) database. This research explores how to accurately establish links between aggregate and binder properties with HMA volumetric properties (Gmb and Gmm). A strong correlation was found between the aggregate volumetric property Gsb and Gmm prediction. Moreover, the generalization of the Rice test phenomenon to adequately predict Gmm using DNNs could allow designers to precisely estimate the HMA volumetric property (Gmm), thus avoiding running this test to calculate the volumetric values."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Hot mix asphalt volumetric optimization using artificial intelligence"]}]}],"canonical_facts":{"dc:creator":["Useche, Jesus"],"dc:date":["2022-11-24"],"dc:description":["The empirical procedure of HMA volumetric design requires time and effort. This procedure is a common practice when adjusting the job formula due to eventual changes in aggregates and binder properties imposing upon asphalt plants. This empirical method is based on gradation specifications limits in which correlations between the desire state of voids and aggregate gradation remain unclear, thereby producing a material (HMA) with uncertain performance at which validation test is essential. This work compares 4 gradation factors in which aggregate gradation is quantified as a number. This evaluation permits knowing which gradation factor has the highest correlation with HMA volumetric properties, thereby reducing the endeavor implied in the empirical design due to a simple calculation of the factor could produce an effective estimation of volumetric properties. This study applies deep neural networks (DNNs) based on supervised machine learning method to predict two volumetric properties: 1) the maximum specific gravity (Gmm) which is obtained by running the Rice test and 2) the bulk specific gravity (Gmb) in which the aggregate packing is compacted when SGC test is applied, and asphalt binder content produces bulk density changes at the same level of energy compaction for the same aggregate blend. These neural networks are built based on aggregate and binder properties as input variables and HMA volumetric properties as output variables. These DNNs are training to use raw data collected from the Long-Term Pavement Performance (LTPP) database. This research explores how to accurately establish links between aggregate and binder properties with HMA volumetric properties (Gmb and Gmm). A strong correlation was found between the aggregate volumetric property Gsb and Gmm prediction. Moreover, the generalization of the Rice test phenomenon to adequately predict Gmm using DNNs could allow designers to precisely estimate the HMA volumetric property (Gmm), thus avoiding running this test to calculate the volumetric values."],"dc:format":["application/pdf"],"dc:identifier":["INSERT-YOUR-LIBRARY-ID-HERE3138","https://espace.etsmtl.ca/id/eprint/3138/1/USECHE_Jesus.pdf"],"dc:language":["en"],"dc:publisher":["École de technologie supérieure"],"dc:subject":["enrobés, conception volumétrique, optimisation, intelligence artificielle, réseaux de neurones profonds pour la conception des enrobés"],"dc:title":["Hot mix asphalt volumetric optimization using artificial intelligence"],"dc:type":["Electronic Thesis or Dissertation"],"thesis:degree_level":["masters"],"thesis:degree_name":["Mémoire de maîtrise électronique"],"thesis:institution_name":["École de technologie supérieure"]},"updated_at":"2026-11-18T22:09:45Z"}