Aos meus pais Walkiria e Domingos, pelo amor, ensinamentos e incentivos. Aos meus irmãos André e Gabriela, pelos bons e maus exemplos. Aos meus sobrinhos Neto, Carol, Camila, Andrézinho e Pedro, por todos os momentos felizes. À minha orientadora Professora Kamilla Vasconcelos, pelo o aprendizado, carinho, dedicação e paciência. À Professora. Liedi Bernucci por toda a disposição em ensinar, orientar e aconselhar. À minha grande amiga Amanda Marcandali, por tantas contribuições positivas a esse trabalho. Aos alunos de Iniciação Científica Pedro, Letícia, Caio e Edigar, que fizeram parte desse projeto. A toda a equipe do LTP, em especial os laboratoristas Erasmo e Cleyton e os técnicos Kendi, Robson e Vanderley, por toda ajuda na realização dos ensaios. À amiga Diomária dos Santos, peça fundamental no funcionamento do LTP. À Renata Monte, pela disponibilidade e prontidão para a realização de ensaios no Laboratório do PCC. Às amigas Larissa e Tathiane pelos momentos de descontração e os de silêncio. Ao Grupo OHL Brasil, pela parceria na realização desta pesquisa. À ANTT, por possibilitar a realização de pesquisas práticas em parceria com a Universidade. Ao CNPq, pela bolsa de mestrado. RESUMO Esta pesquisa avaliou a técnica de reciclagem de solo-agregado com adição de cimento para a reconstrução de pavimentos asfálticos deteriorados. A técnica utilizada consiste da adição de cimento a uma base de solo-brita, configurando assim uma base cimentada de solo-brita-cimento. A utilização de agregados reciclados na pavimentação é prática crescente no Brasil e no mundo, recebendo incentivos públicos e sociais, além de representar grandes benefícios ambientais associados à redução do bota-fora, da exploração de recursos naturais e transporte de insumos. Tais agregados apresentam características únicas, inerentes a sua origem e utilização prévia, portanto necessitam de estudos quando de sua utilização em qualquer camada de pavimento. Os materiais utilizados nesta pesquisa são provenientes da base de solo-brita existente na rodovia Fernão Dias. A esses materiais foi adicionado cimento Portland para compor novos materiais de sub-base reciclada. Por apresentar função estrutural bastante significativa no sistema de camadas do pavimento, a camada cimentada necessita de uma criteriosa e abrangente caracterização mecânica. Esse estudo foi dividido em duas frentes distintas de avaliação: estudos laboratoriais e estudos de campo. Nos estudos laboratoriais foram testadas cinco misturas de material reciclado com cimento, com variações do tipo de materiais reciclado, teor de cimento e energia de compactação. Avaliam-se também diferentes métodos de ensaio, comparando resultados obtidos para procedimento de ensaio de concretos e argamassas, e de materiais granulares. Todas as variáveis testadas em laboratório apresentaram influência no comportamento mecânico das misturas cimentadas. Os estudos de campo consistem da construção e do monitoramento estrutural do trecho experimental, além de ensaios mecânicos em corpos de prova extraídos de pista...
With improvements in data collection, storage, and processing, machine learning (ML) is gaining momentum as a behavior prediction method in the field of engineering. Several studies have evaluated these algorithms’ potential to predict pavement serviceability, however some challenges limit its use. Training data preprocessing has a great impact on the model’s predictive performance, is highly dependent on the modeler’s experience, and is not typically reported in engineering-related literature. The objective of this study was to assess the effects of data preprocessing, hyperparameter selection, and time series size on the model’s evaluation metrics. Therefore, this paper analyzes the performance of three ML algorithms on maximum deflection (D0) and international roughness index (IRI) prediction: support vector machine, random forest (RF), and artificial neural network (ANN). An R2 and mean square error (MSE) analysis was conducted on 12 training datasets, with two sizes of historical data and five stages of data preprocessing. The results indicated that ANN was the most accurate technique with an R2 of 0.99 and MSE of 20 ×10−3 mm on the D0 prediction and an R2 of 0.91 and MSE of 0.03 m/km on the IRI prediction. RF was also identified as an effective technique, generating similar results with less data preprocessing. The addition of structural and traffic categorical features to the training dataset resulted in the most significant improvement of the support vector regression and ANN performance metrics; the hyperparameter selection was effective only on IRI prediction, especially with the ANN algorithm.
The accurate forecast of pavement performance is crucial for Pavement Management Systems, as they guide maintenance decisions and budget allocation. With improvements in data collection, storage and processing, machine learning (ML) is gaining visibility as a behavior prediction method in the field of engineering. Several studies evaluated these algorithms' potential to predict pavement serviceability, however some challenges limit its use. The pavement performance history, structural information, and traffic load characteristics are not always available on data-oriented manner. The training dataset preprocessing has great impact on the model's predictive performance, is highly dependent on the modeler experience, and are not typically reported on the engineering related literature. Also, the long-term prediction using ML algorithms usually demand long historical time-series, which are not always available on a large scale. Therefore, the objective of this dissertation is to develop a methodology for the use of machine learning algorithms on the Asphalt Pavement Performance Prediction, comprehending: data collection and organization; training dataset definition; algorithm selection and configuration; and long-term performance model definition. The pavement's performance was based on the Surface Maximum Deflection (D0) and International Roughness Index (IRI). To achieve this goal, the three most used ML algorithms -Support Vector Machine (SVM); Random Forest (RF); and Artificial Neural Network (ANN) -in D0 and IRI short-term prediction were tested using 10 training datasets, composed of the data collected from 21,568 traffic lane kilometers. The long-term prediction model was based: on the short-term ML model; the Markov chain principle; and the recursive method. The results indicated that ANN is the most accurate technique with a RMSE of 16x10 -3 mm on the D0 prediction; and a RMSE of 0.19m/km on IRI prediction. The models' evaluation of the long-term prediction was obtained by the comparison of 20 pavement segments field data with simulated data. The best results were also obtained with ANN: they presented an average RMSE of 23x10 -3 mm on the D0 prediction; and a RMSE of 0.17m/km on IRI prediction. RF was also identified as an effective technique, generating similar results with less data preprocessing.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.