scholarly journals Principal Component Neural Networks for Modeling, Prediction, and Optimization of Hot Mix Asphalt Dynamics Modulus

2019 ◽  
Vol 4 (3) ◽  
pp. 53 ◽  
Author(s):  
Parnian Ghasemi ◽  
Mohamad Aslani ◽  
Derrick K. Rollins ◽  
R. Christopher Williams
Keyword(s):  
Neural Networks ◽  
Predictive Models ◽  
Dynamic Modulus ◽  
Hot Mix Asphalt ◽  
Optimization Problems ◽  
Linear Regression Analysis ◽  
Asphalt Binder ◽  
Real Life ◽  
Principal Component ◽  
Design Parameters

The dynamic modulus of hot mix asphalt (HMA) is a fundamental material property that defines the stress-strain relationship based on viscoelastic principles and is a function of HMA properties, loading rate, and temperature. Because of the large number of efficacious predictors (factors) and their nonlinear interrelationships, developing predictive models for dynamic modulus can be a challenging task. In this research, results obtained from a series of laboratory tests including mixture dynamic modulus, aggregate gradation, dynamic shear rheometer (on asphalt binder), and mixture volumetric are used to create a database. The created database is used to develop a model for estimating the dynamic modulus. First, the highly correlated predictor variables are detected, then Principal Component Analysis (PCA) is used to first reduce the problem dimensionality, then to produce a set of orthogonal pseudo-inputs from which two separate predictive models were developed using linear regression analysis and Artificial Neural Networks (ANN). These models are compared to existing predictive models using both statistical analysis and Receiver Operating Characteristic (ROC) Analysis. Empirically-based predictive models can behave differently outside of the convex hull of their input variables space, and it is very risky to use them outside of their input space, so this is not common practice of design engineers. To prevent extrapolation, an input hyper-space is added as a constraint to the model. To demonstrate an application of the proposed framework, it was used to solve design-based optimization problems, in two of which optimal and inverse design are presented and solved using a mean-variance mapping optimization algorithm. The design parameters satisfy the current design specifications of asphalt pavement and can be used as a first step in solving real-life design problems.

scholarly journals Laboratory Performance Evaluation of Hot-Mix Asphalt Mixtures with Different Design Parameters

2020 ◽  
Vol 10 (9) ◽  
pp. 3038
Author(s):  
Yining Zhang ◽  
Lijun Sun ◽  
Huailei Cheng
Keyword(s):  
Low Temperature ◽  
Dynamic Modulus ◽  
Hot Mix Asphalt ◽  
Raw Materials ◽  
Asphalt Binder ◽  
Variable Parameter ◽  
Bending Test ◽  
Design Parameters ◽  
Unconfined Compression Test ◽  
Aggregate Gradation

Aggregate gradation and asphalt type are traditional variables that affects mix design of Hot-Mix Asphalt (HMA). Recently, the number of design gyrations (Ndes) has been increasingly accepted as another variable parameter during the design process. Due to the growing shortage of high-quality raw materials, it is necessary to make full use of the combined roles between these design parameters, instead of solely relying on their individual effect, to improve the HMA properties. Therefore, this study comprehensively explored the effect of aggregate gradation, Ndes, and asphalt type on the performance of HMAs. Seven different combinations of aggregate gradation, Ndes, and asphalt type were evaluated. The volumetric indicators, uniaxial penetration shear test (UPST), unconfined compression test (UCT), low-temperature bending test (LBT), four-point bending test (FPBT), and dynamic modulus test (DMT) were used to assess the performance of HMAs designed by various parameter combinations. It was found that the contribution of adopting harder asphalt binder was able to make up for the high-temperature resistance loss caused by lower Ndes or coarser gradation. The dynamic modulus exhibited the similar phenomenon. By contrast, the harder asphalt binder led to the worse tenacity of HMAs at low temperature; however, the tenacity can be restored through using lower Ndes or coarser gradation by increasing asphalt content. In addition, the fatigue life of HMAs went up significantly by about 36 ~ 41%, when both Ndes and asphalt penetration grade decreased to one lower level.

scholarly journals Development of two models for estimation of rapid chloride penetration and investigation on effective parameters using Artificial Neural Networks (ANNs)

2018 ◽  
Author(s):  
Payam Vosoughi ◽  
Mahmoud Motahari Karein ◽  
Ali Kazemian ◽  
Sasan Tavakol ◽  
Ali A. Ramezanianpour
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Linear Regression Analysis ◽  
Real Life ◽  
Chloride Penetration ◽  
Surface Resistivity ◽  
Training Data ◽  
Research Center ◽  
Design Parameters ◽  
Artificial Neural

In this paper Artificial Neural Networks (ANNs) are employed to develop a model which could estimate the RCPT value of various mixtures according to the mix design parameters, age and surface resistivity of concrete specimens. Furthermore, sensitivity analysis is carried out on the best ANN model to determine the influence of each input on the concrete resistance to the rapid chloride penetration. 258 experimental datasets, resulted from 79 mix designs, were used as training data for ANN models; all of which prepared and tested in Concrete Technology and Durability Research Center of Amirkabir University of Technology (CTDRC). Another simplified model is proposed using linear regression analysis; which estimates the RCPT value simply according to surface resistivity measure. Finally, eight mixtures prepared in Building and Housing Research Center (BHRC) and six mixtures obtained from real-life projects, are employed to compare and validate the proposed models.

scholarly journals Assistive HCI-Serious Games Co-design Insights: The Case Study of i-PROGNOSIS Personalized Game Suite for Parkinson’s Disease

2021 ◽  
Vol 11 ◽  
Author(s):  
Sofia Balula Dias ◽  
José Alves Diniz ◽  
Evdokimos Konstantinidis ◽  
Theodore Savvidis ◽  
Vicky Zilidou ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Health Status ◽  
Game Design ◽  
Serious Games ◽  
Linear Regression Analysis ◽  
Real Life ◽  
Design Parameters ◽  
Online Questionnaire ◽  
Design Elements

Human-Computer Interaction (HCI) and games set a new domain in understanding people’s motivations in gaming, behavioral implications of game play, game adaptation to player preferences and needs for increased engaging experiences in the context of HCI serious games (HCI-SGs). When the latter relate with people’s health status, they can become a part of their daily life as assistive health status monitoring/enhancement systems. Co-designing HCI-SGs can be seen as a combination of art and science that involves a meticulous collaborative process. The design elements in assistive HCI-SGs for Parkinson’s Disease (PD) patients, in particular, are explored in the present work. Within this context, the Game-Based Learning (GBL) design framework is adopted here and its main game-design parameters are explored for the Exergames, Dietarygames, Emotional games, Handwriting games, and Voice games design, drawn from the PD-related i-PROGNOSIS Personalized Game Suite (PGS) (www.i-prognosis.eu) holistic approach. Two main data sources were involved in the study. In particular, the first one includes qualitative data from semi-structured interviews, involving 10 PD patients and four clinicians in the co-creation process of the game design, whereas the second one relates with data from an online questionnaire addressed by 104 participants spanning the whole related spectrum, i.e., PD patients, physicians, software/game developers. Linear regression analysis was employed to identify an adapted GBL framework with the most significant game-design parameters, which efficiently predict the transferability of the PGS beneficial effect to real-life, addressing functional PD symptoms. The findings of this work can assist HCI-SG designers for designing PD-related HCI-SGs, as the most significant game-design factors were identified, in terms of adding value to the role of HCI-SGs in increasing PD patients’ quality of life, optimizing the interaction with personalized HCI-SGs and, hence, fostering a collaborative human-computer symbiosis.

scholarly journals Inverse design of organic light-emitting diode structure based on deep neural networks

Nanophotonics ◽  
2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Sanmun Kim ◽  
Jeong Min Shin ◽  
Jaeho Lee ◽  
Chanhyung Park ◽  
Songju Lee ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Inverse Problem ◽  
Optical Properties ◽  
Extraction Efficiency ◽  
Optimization Problems ◽  
Light Extraction ◽  
Light Extraction Efficiency ◽  
Design Parameters ◽  
Light Emitting

Abstract The optical properties of thin-film light emitting diodes (LEDs) are strongly dependent on their structures due to light interference inside the devices. However, the complexity of the design space grows exponentially with the number of design parameters, making it challenging to optimize the optical properties of multilayer LEDs with rigorous electromagnetic simulations. In this work, we demonstrate an artificial neural network that can predict the light extraction efficiency of an organic LED structure in 30 ms, which is ∼103 times faster than the rigorous simulation in a single-treaded execution with root-mean-squared error of 1.86 × 10−3. The effective inference time per structure is brought down to ∼0.6 μs with unaltered error rate with parallelization. We also show that our neural networks can efficiently solve the inverse problem – finding a device design that exhibits the desired light extraction spectrum – within the similar time scale. We investigate the one-to-many mapping issue of the inverse problem and find that the degeneracy can be lifted by incorporating additional emission spectra at different observing angles. Furthermore, the forward neural network is combined with a conventional genetic algorithm to address additional large-scale optimization problems including maximization of light extraction efficiency and minimization of angle dependent color shift. Our approach establishes a platform for tackling computation-heavy optimization tasks with one-time computational cost.

scholarly journals Accuracy of Predictive Models for Dynamic Modulus of Hot-Mix Asphalt

2009 ◽  
Vol 21 (6) ◽  
pp. 286-293 ◽  
Author(s):  
Halil Ceylan ◽  
Charles W. Schwartz ◽  
Sunghwan Kim ◽  
Kasthurirangan Gopalakrishnan
Keyword(s):  
Predictive Models ◽  
Dynamic Modulus ◽  
Hot Mix Asphalt

scholarly journals How the Mix Factors Affect the Dynamic Modulus of Hot-Mix Asphalt

2019 ◽  
Vol 3 (3) ◽  
pp. 72
Author(s):  
Md Rashadul Islam ◽  
Sylvester A. Kalevela ◽  
Guy Mendel
Keyword(s):  
High Temperature ◽  
Low Temperature ◽  
Dynamic Modulus ◽  
Hot Mix Asphalt ◽  
Asphalt Binder ◽  
Asphalt Mixture ◽  
Performance Grade ◽  
Reduced Frequency ◽  
Nominal Size ◽  
S 100

Hot-mix asphalt (HMA) is a composite material consisting of stone-aggregates, sand, asphalt binder and additives. The properties of this combined material are dependent on the volumetric parameters used in the mix design. This study investigates the effects of volumetric mix factors on the dynamic moduli (E*) of eleven categories of HMAs. For each category of asphalt mixture, the variations in dynamic modulus for different contractors, binder types, effective binder content (Vbe), air void (Va), voids-in-mineral aggregates (VMA), voids-filled-with asphalt (VFA) and asphalt content (AC) are assessed statistically. Results show that the S(100) mixture (nominal size of 19 mm, 100 gyrations) with the Performance Grade (PG) binder of PG 64-22 has the highest value of E* at low temperature or high reduced frequency. At high temperature or lower reduced frequency, S(100) PG 76-28 has the highest E* value. The SX(75) mixture (nominal size of 12.5 mm, 75 gyrations) with the binder of PG 64-28 has the lowest E* value at high temperature or lower reduced frequency. At low temperature or high reduced frequency, SX(75) PG 58-34 has the lowest E* value. The Stone Mix Asphalt (SMA) mix has a lower E* compared to S(100) and SX(100) mixes ((nominal size of 12.5 mm, 100 gyrations) with the Performance Grade (PG) binder of) at low temperature. The E* increases with an increase in Vbe, Va, and VFA, and decreases with an increase in VMA and AC. The E* of a mix can vary from 200 ksi (1380 MPa) to about 1000 ksi (6900 MPa) for a particular frequency (10 Hz) and temperature (21.1 °C), even if samples are from the same contractor.

New predictive models for the dynamic modulus of hot mix asphalt

2015 ◽  
Vol 76 ◽  
pp. 221-231 ◽  
Author(s):  
Maryam S. Sakhaeifar ◽  
Y. Richard Kim ◽  
Pooyan Kabir
Keyword(s):  
Predictive Models ◽  
Dynamic Modulus ◽  
Hot Mix Asphalt
Sign in / Sign up

Export Citation Format

Share Document