Faculty Publications

Now showing 1 - 3 of 3

Combustion aided in situ consolidation of high strength porous ceramic structures with a minimum thermal budget
(Elsevier B.V., 2020) Pujar, P.; Pal, A.; Mandal, S.
The exothermic reaction between a pair of combustible pore formers (urea-ammonium nitrate) is the driving force in realizing low-temperature consolidation of hydroxyapatite (HA) particles. The particles are allowed to sinter in the proximity to the combustible pore formers. The exothermic (?H°rea = -898 kJ/mol) redox reaction between combustible pore formers is successfully utilized in deriving high compressive strength (~24 MPa) of HA at 300 °C. The evolution of gaseous products of combustion results in an interconnected porous network of HA. The estimated compressive strength of sintered HA at 300 °C is comparable with high temperature (1100 °C) conventionally sintered HA, at a fixed open porosity (~40%); which depicts nearly ~82% achievement with a reduction of sintering temperature by ~72%. Also, the pellets sintered at 600 °C have shown ~90% achievement in compressive strength of sintered HA. Further, the saturated pore area of 15% requires a sintering time of 9.58 h at a sintering temperature of 600 °C. Thus, combustion-assisted sintering is an alternative technique proves its potentiality in achieving remarkable compressive strength and paves the way for low-cost porous ceramics. © 2020 Elsevier B.V.
A hybrid machine learning approach for early cost estimation of pile foundations
(Emerald Publishing, 2025) Deepa, G.; Niranjana, A.J.; Balu, A.S.
Purpose: This study aims at proposing a hybrid model for early cost prediction of a construction project. Early cost prediction for a construction project is the basic approach to procure a project within a predefined budget. However, most of the projects routinely face the impact of cost overruns. Furthermore, conventional and manual cost computing techniques are hectic, time-consuming and error-prone. To deal with such challenges, soft computing techniques such as artificial neural networks (ANNs), fuzzy logic and genetic algorithms are applied in construction management. Each technique has its own constraints not only in terms of efficiency but also in terms of feasibility, practicability, reliability and environmental impacts. However, appropriate combination of the techniques improves the model owing to their inherent nature. Design/methodology/approach: This paper proposes a hybrid model by combining machine learning (ML) techniques with ANN to accurately predict the cost of pile foundations. The parameters contributing toward the cost of pile foundations were collected from five different projects in India. Out of 180 collected data entries, 176 entries were finally used after data cleaning. About 70% of the final data were used for building the model and the remaining 30% were used for validation. Findings: The proposed model is capable of predicting the pile foundation costs with an accuracy of 97.42%. Originality/value: Although various cost estimation techniques are available, appropriate use and combination of various ML techniques aid in improving the prediction accuracy. The proposed model will be a value addition to cost estimation of pile foundations. © 2023, Emerald Publishing Limited.
Prediction of Pavement Maintenance Cost for Rural Roads at Network Level
(Springer, 2025) Arun, V.; Suresha, S.N.
Predicting pavement maintenance cost is an important factor for planning the budgetary requirements of any road agency at the network level. Pavement condition prediction models play a vital role in predicting pavement maintenance costs. Road agencies in developing countries like India still need pavement condition prediction models. The present study proposes an approach to help road agencies predict pavement conditions and annual maintenance costs. The proposed method was developed on rural roads of Shimoga district, Karnataka, India. The pavement condition data were collected using the Online Management Monitoring and Accounting System (OMMAS) database and by field visual inspection survey. A homogeneous Markov model was developed to predict the future pavement condition and estimate the rural road network's annual pavement maintenance cost. The study results indicated that 59% of the road network would come to a reconstruction state at a 10-year duty cycle if no maintenance is provided. Consequently, the annual maintenance cost predicted for 2031 was Indian Rupee (INR) 751.6 million, with an increase of 17% on average with each duty cycle. The model was validated along with the sensitivity analysis. The sensitivity analysis indicated improved pavement performance reduces maintenance costs and vice versa. The validation of the model was reliable, with a Pearson’s correlation R value of 0.92 and R square value of 0.86 at 95% confidence level. Hence, with this proposed approach, road agencies can predict the annual pavement maintenance cost so that they can plan their budget accordingly for an effective maintenance strategy at a network level. © The Institution of Engineers (India) 2025.

Faculty Publications

Browse

Filters

Settings

Sort By

Results per page

Search Results