Intelligent, Data-Driven, Emerging & Adaptive Systems Technology (IDEASTech) Laboratory
at Louisiana Tech University
Research
The integration of energy harvesting, embedded sensing, additive manufacturing, multifunctional materials and data-driven modeling has given rise to novel technologies that are fundamentally transforming our capacity to approach the realization of smart cities' vision. Our lab conducts cross-disciplinary research to develop intelligent systems capable of implementing self-sensing and multifunctional abilities, as well as delivering long-term autonomous monitoring data to enhance infrastructure resilience and sustainability while mitigating the impacts of hazards on the built environment. We are interested in advancing the development of novel sensing systems tailored for monitoring the built environment, multifunctional structures utilizing engineered material systems with advanced functionalities, and data analytics platforms proficient in the swift transformation of collected data into practical insights. In addition, we aim to integrate socioeconomic insights to enhance post-disaster recovery efforts and foster resilient communities. Our research portfolio covers a wide range of areas including:
-
Resilient and sustainable urban infrastructure and communities
-
Intelligent and energy-efficient structural monitoring
-
Self-powered sensing with embedded computational intelligence
-
Real-time data-driven modeling for the built environment
Our research is supported by NSF, NASA, the Louisiana Space Grant Consortium (LaSPACE, a NASA EPSCoR center), LADOTD, Louisiana Transportation Research Center (LTRC), the Louisiana Materials Design Alliance (LAMDA, supported by NSF EPSCoR and Louisiana Board of Regents), and the start-up funds provided by the College of Engineering and Science at Louisiana Tech University.
Smart Bridge Monitoring Employing Deep Learning and Unmanned Aerial Vehicles
Significant attention should be devoted to develop new platforms to continuously monitor our existing infrastructure. Conventional bridge monitoring techniques mainly use vision-based inspection methods that suffer from several shortcomings, such as dealing with limited accessible areas, the performance being highly dependable on the inspector’s experience, the inspector’s safety, and time consumption. To tackle the noted challenges, this project aims to develop a data-driven framework for smart bridge monitoring through the integration of deep learning and unmanned aerial vehicle (UAV) using images collected from reinforced concrete bridges. The computer vision-based framework employing convolutional neural networks indicated great performance in accurately detecting the presence and location of cracks, despite being trained on a limited dataset, leading to autonomous bridge monitoring.
Data-driven Mechanical Properties Characterization of 3D Printed Materials
Machine learning (ML)-guided materials design is a powerful tool in advancing additive manufacturing (AM) processes. This study introduces an ML-based framework aimed at accurately predicting and optimizing the mechanical properties of 3D-printed plastic. Through systematically analyzing the interaction between processing parameters and the resulting material characteristics, this work not only predicts the tensile strength of 3D-printed plastic but also identifies critical factors affecting its performance. The results indicated the satisfactory performance of the ML framework to expand the predictive capabilities of ML in AM, optimizing print conditions for enhanced material properties.
High-dimensional Data Analytics in Civil Infrastructure Systems
Recent developments in sensing and monitoring techniques have led to the generation of high-dimensional data in the domain of civil engineering. Traditional tensor decomposition methods like CANDECOMP/PARAFAC (CP) and Tucker adopted for data analysis in civil infrastructure have several limitations, including lack of scalability and flexibility when dealing with high-dimensional data. This project explores the applicability of a new algorithmic framework that utilizes a more efficient tensor decomposition method called tensor-train for data imputation in civil infrastructure systems. The performance of the framework is evaluated using real traffic data set constructed as higher-order tensors. The results indicate that the proposed framework can effectively impute high-dimensional missing data while being accurate even in the presence of large rates of missing data.
Structural Response Prediction of Concrete Members Utilizing Machine Learning
The mechanical properties of concrete are known to have strong nonlinear relations between the constituents and the macroscale material characteristics. Therefore, the development of reliable models is of great interest to explore material mechanical properties in a way that optimizes cost and time. The potential of ML has been harnessed in this project to model such properties. In this study, computational frameworks employing machine learning are developed to predict failure mode, shear and flexural strengths of ultra high performance concrete (UHPC) beams, as well as spalling in fire-tested reinforced concrete columns using comprehensive datasets on tests reported on concrete members with different geometric, fiber properties, loading and material characteristics. The results indicate the effectiveness of the frameworks for structural response prediction of UHPC beams.
Characterization of Eco-friendly 3D Printed Concrete with Fine Aggregate Replacements
Following the integration of engineered cementitious composites in 3D printing, the most recent research interests of 3D printed concrete have been shifted towards recycling aggregates and the incorporation of by-products. This study explores the mechanical performance of the eco-friendly 3D printed concrete by utilizing silica fume, glass fiber, and ground waste rubber tire (replacing fine aggregates) in the mix proportions. Numerical simulations are performed to simualte the mechanical performance of the fabricated 3D printed concrete cubes and beams. A machine learning-based model is developed to predict the compressive and flexural strengths of the aggregate-mixed 3D printed concrete.
Energy-efficient Structural Health Monitoring Integrating Self-powered Sensing and Data Analytics
Self‐powered sensors have become a reality by overcoming the gap between the achievable scavenged energy and the energy required for sensing, computing, and communication. In this study, a novel structural monitoring platform is developed based on the integration of energy harvesting, self-powered sensing, and data analytics. The integrated sensing systems is unique due to its ability to harvesting energy from the environment to operate and wirelessly transmit a binary pulse when its measurement exceeds a defined threshold. In addition, an algorithmic framework employing advanced data analytics and machine learning is developed to interpret self-powered sensor data. The effectiveness of the smart structural monitoring platform for energy-lean health monitoring of civil infrastructure and aerospace vehicles is evaluated through numerical and experimental studies.
Data-driven Structural Condition Assessment of Civil Structures with Wireless Sensor Data
The effectiveness of traditional SHM methods strongly depends on the availability of continuous time-history data, and such data availability is substantially affected when dealing with discrete data. An image-based pattern recognition approach using anomaly detection is proposed to represent sensor nodes’ responses as a pattern and to identify failure patterns. To implement the approach, the arrangement of sensor nodes and the distribution of binary values generated from structural response are considered as a pattern/image. The results indicate that the proposed image-based pattern recognition approach can effectively identify the presence and location of damage with discrete binary data collected from a network of self-powered sensors.
