M. K. Nivedya

Bio: M. K. Nivedya is an academic researcher from Worcester Polytechnic Institute. The author has contributed to research in topics: Moisture & Discounted cash flow. The author has an hindex of 3, co-authored 13 publications receiving 35 citations.

Artificial neural network-based prediction of field permeability of hot mix asphalt pavement layers

Abstract: Field permeability of Hot Mix Asphalt (HMA) needs to be controlled to prevent excessive ingress of water into asphalt pavements, which leads to premature failure. Existing literature shows scatter ...

Microstructural Evolution of Asphalt Binder under Combined Action of Moisture and Pressure

Abstract: Moisture-induced damage in asphalt mixes can lead to various distresses in the pavement. The primary cause of such distresses is the loss in adhesion and cohesion properties of the asphalt ...

A framework for the assessment of contribution of base layer performance towards resilience of flexible pavement to flooding

Abstract: Flood-induced moisture damage of flexible pavements is a serious concern for many road authorities. Reports from several studies confirm the significant structural damage that is caused by flooding...

A multi-structure multi-run range (MSMRR) approach for using machine learning with constrained data in pavement engineering

Abstract: In pavement engineering, the data sets that are typically obtained from experiments are small and cannot be classified as big data. The effective use of machine learning techniques such as artificial neural networks (ANN) for small data is a challenge because of poor accuracy of models. This paper presents a method of multiple structure multiple run and ranging to optimize ANN to produce models with small data sets with high accuracy. In this method, a large number of data fitting ANNs, with different number of neurons, layers, training and validation ratios, and randomized layer weights and biases are run in parallel, and the most accurate ANN is filtered out on the basis of the lowest MSE or highest R. The process is demonstrated with weather and pavement temperature data for a hot mix asphalt (HMA) and an open graded friction course (OGFC) pavement. Models are generated to predict the temperature at a depth of 12.5 mm below the surface. For the HMA pavement, an accuracy of 99.73% was obtained and an optimum structure was found to be with 4 layers, 11 neurons, 70% training ratio, 15% validation ratio. In the case of the OGFC pavement, an accuracy of 99.75% was obtained for an optimum structure with 3 layers, 11 neurons, 75% training ratio, 15% validation ratio. Furthermore, the fitting/regression problem was converted to a classification problem with different ranges, and then ANNs were utilized to develop very accurate classification models with small datasets.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Influence of Six Rejuvenators on the Performance Properties of Reclaimed Asphalt Pavement (RAP) Binder and 100% Recycled Asphalt Mixtures

Abstract: 100% recycled hot mix asphalt lab samples were modified with five generic and one proprietary rejuvenators at 12% dose and tested for binder and mixture properties. Waste Vegetable Oil, Waste Vegetable Grease, Organic Oil, Distilled Tall Oil, and Aromatic Extract reduced the Superpave performance grade (PG) from 94–12 of extracted binder to PG 64-22 while waste engine oil required higher dose. All products ensured excellent rutting resistance while providing longer fatigue life when compared to virgin mixtures and most lowered critical cracking temperature. Rejuvenated samples required more compaction energy compared to virgin and some oils reduced moisture resistance slightly.

Microstructure of synthetic composite interfaces and verification of mixing order in cold-recycled asphalt emulsion mixture

Abstract: Cold recycling technology is getting more and more attention due to economic and environmental benefits by reduced energy consumption and resource conservation. However, its application has been limited to the base and subbase layer because of complicated components and poor crack resistance for the last decades. The design method has shortcomings especially the traditional mixing order, which may be one of the reasons for poor crack resistance. To support the viewpoint above, synthetic composite interfaces were designed to simulate the worst situation during the traditional mixing process and observed in micro scale by scanning electron microscopy. In the microstructure of the traditional mixing order, it was apparent that cement paste had a number of microdefects, a signal of lower interfacial adhesive strength. Moreover, based on the microscopic observation, the adding sequence of cement ought to be changed and two optimized mixing orders were designed of which the difference was verified by the SEM observation of synthetic composite interfaces and the mechanical experiments for different curing time. It can be summarized that mechanical performance was consistent with the microscopic observation. The traditional mixing order was the worst one both in the strength and moisture sensitivity. Finally, the optimal mixing order is put forward to decrease the possibility of the adverse interface, that is, the graded aggregates are mixed with additional water first to reach the workability, while cement, asphalt emulsion and mineral powder are mixed to form cement-asphalt emulsion mortar, finally mixing them all up.

Prediction of the crack condition of highway pavements using machine learning models

Abstract: Departments of Transportation regularly evaluate the condition of pavements through visual inspections, nondestructive evaluations, image recognition models and learning algorithms. The above metho...

Investigation of Microscale Aging Behavior of Asphalt Binder Using Atomic Force Microscopy

Abstract: Abstract Atomic force microscopy (AFM) has the capacity to distinguish among different phases at high resolution, and it is widely used in obtaining topography and mechanical property maps for asphalt binders. This study investigated the effects of long-term aging on both SBS-modified asphalt and base asphalt using AFM. In describing the study findings, this paper introduces two new indices used to quantify changes in the microstructures of asphalt, namely, the percentage of elliptical bee structures and surface roughness. In addition, the Derjaguin-Muller-Toporov modulus and adhesive force were measured to quantify the mechanical properties of the micro-phases. Finally, to evaluate the influence of aging on composite phase properties, a parallel model from the field of composite materials was introduced and applied. The results indicate that aging significantly affected the microstructures and mechanical behavior of micro-phases of asphalt binders. Aging also had a significant influence on the microstructures of the asphalt, especially in the bee structures. The percentage of bee structures increased or decreased after aging depending on the asphalt binder type, while surface roughness always decreased. Aging also increased the composite modulus of the micro-phases and decreased the composite adhesion of the micro-phases. These findings are in agreement with the macroscale aging behavior of asphalt binders.