Brief Description:
Corrosion is a major problem in bridges and space frames such as industry
buildings, chimneys, telecommunication towers etc especially in coastal
and industrial environment. Corrosion is not simply a financial cost if
left unattended; the endangerment of lives may also be a real risk. In
most cases, corrosion is detected by conducting visual inspection procedure
which can be slow, potentially dangerous, labor intensive, inaccurate
and may not be even possible due to accessibility difficulties. Recently,
Drones have proven to be a viable and safer solution to perform such inspections
in many adverse conditions by flying up-close to the structures and take
a very large number of high-resolution images from multiple angles. However,
manual processing of these images to identify corrosion may require highly
qualified engineers and may lead to high costs in terms of man-hours and
inconsistencies. Recent publications have highlighted the effectiveness
of utilizing deep learning (DL) for identifying corrosion in building
structures. In this research we propose to develop a novel Deep Learning
(DL)-based framework for detecting corrosion by processing high resolution
images captured by drones.
We are looking for a dynamic candidate who meets the above qualifications.
If you are interested in this project, apply through the following link on or before 20th March 2021
https://tinyurl.com/hzanbm76If you have any queries or needs any further information, please contact Dr. M.C.M. Nasvi, Coordinator of the split PhD Programme [Email:nasvimcm@eng.pdn.ac.lk]
(08/03/2021)
Brief Description:
The growing concern about global climate change and its adverse impacts
on societies is putting severe pressure on the construction industry
as one of the largest producers of greenhouse gases. Given the environmental
issues associated with cement production, Geopolymer/Alkali Activated
Concrete has emerged as a sustainable construction material. Many research
studies have been conducted during recent years on the topic of geopolymer/alkali
activated materials based on the engineering performance of the concrete
although the commercialisation is limited. What has been missing is
the combination of this research in a way that would provide a simple
to use design tool for geopolymer/alkali activated concrete as a replacement
to concrete based on Portland Cement. This research project will address
this requirement by developing a standard mix design method and guideline
for geopolymer and alkali activated concretes using Advanced machine
learning techniques, namely Artificial Neural Network (ANN), Multivariate
Adaptive Regression Spline (MARS) model and Support Vector Machine (SVM)
techniques. Outcomes of this research will deliver significant benefits
in terms of environmentally friendly concrete to the construction industry.
We are looking for a dynamic candidate who meets the above qualifications.
If you are interested in this project, apply through the following link on or before 16th March 2021
https://tinyurl.com/5db9rhusIf you have any queries or needs any further information, please contact Dr. M.C.M. Nasvi, Coordinator of the split PhD Programme [Email:nasvimcm@eng.pdn.ac.lk]
(03/03/2021)