Structural Engineering Commons^™

Hyperspectral Imaging And Data Analytics For Civil Infrastructure Inspection, Genda Chen

INSPIRE Archived Webinars

In this 50-minute lecture, the fundamental concept of hyperspectral imaging is reviewed. Each hyperspectral image represents a narrow, contiguous wavelength range of an electromagnetic spectrum, which could be indicative of a chemical substance. All the images in the spectral range of a hyperspectral camera are combined to form a three-dimensional hyperspectral data cube with two spatial dimensions and one spectral dimension. A hyperspectral cube can be sampled in four ways: spatial scanning, spectral scanning, snapshot imaging, and spatio-spectral scanning. This presentation will be focused on spatial scanning from a line-scan camera. The feasibility of horizontal imaging from a synchronized hyperspectral …

Naturally Occurring Van Der Waals Heterostructure Lengenbachite With Strong In-Plane Structural And Optical Anisotropy, Arindam Dasgupta, Xiaodong Yang, Jie Gao

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Lengenbachite is a naturally occurring layered mineral formed with alternating stacks of two constituent PbS-like and M₂S₃-like two-dimensional (2D) material layers due to the phase segregation process during the formation. Here, we demonstrate to achieve van der Waals (vdW) heterostructures of lengenbachite down to a few layer-pair thickness by mechanical exfoliation of bulk lengenbachite mineral. The incommensurability between the constituent isotropic 2D material layers makes the formed vdW heterostructure exhibit strong in-plane structural anisotropy, which leads to highly anisotropic optical responses in lengenbachite thin flakes, including anisotropic Raman scattering, linear dichroism, and anisotropic third-harmonic generation. Moreover, …

Faster Post-Earthquake Damage Assessment Based On 1d Convolutional Neural Networks, Xinzhe Yuan, Dustin Tanksley, Liujun Li, Haibin Zhang, Genda Chen, Donald C. Wunsch

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Contemporary deep learning approaches for post-earthquake damage assessments based on 2D convolutional neural networks (CNNs) require encoding of ground motion records to transform their inherent 1D time series to 2D images, thus requiring high computing time and resources. This study develops a 1D CNN model to avoid the costly 2D image encoding. The 1D CNN model is compared with a 2D CNN model with wavelet transform encoding and a feedforward neural network (FNN) model to evaluate prediction performance and computational efficiency. A case study of a benchmark reinforced concrete (r/c) building indicated that the 1D CNN model achieved a prediction …

Machine Learning For High-Fidelity Prediction Of Cement Hydration Kinetics In Blended Systems, Rachel Cook, Taihao Han, Alaina Childers, Cambria Ryckman, Kamal Khayat, Hongyan Ma, Jie Huang, Aditya Kumar

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The production of ordinary Portland cement (OPC), the most broadly utilized man-made material, has been scrutinized due to its contributions to global anthropogenic CO₂ emissions. Thus -- to mitigate CO₂ emissions -- mineral additives have been promulgated as partial replacements for OPC. However, additives -- depending on their physiochemical characteristics -- can exert varying effects on OPC's hydration kinetics. Therefore -- in regards to more complex systems -- it is infeasible for semi-empirical kinetic models to reveal the underlying nonlinear composition-property (i.e., reactivity) relationships. In the past decade or so, machine learning (ML) has arisen as a promising, …

Semi-Annual Progress Report #9, Missouri University Of Science And Technology. Inspire - University Transportation Center

Semi-Annual Progress Reports

No abstract provided.

Three-Dimensional Printing Of Reinforced Concrete And Nozzle Therefor, Chenglin Wu, Genda Chen, Dimitri Feys, Guirong Grace Yan, Bryce Tyler Tafolla

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

A three-dimensional printing system for reinforced concrete and a nozzle therefor. The system employs an extruder for extruding unreinforced concrete and a concrete reinforcement feeder is for feeding one or more elongate reinforcement members. The nozzle has an outlet and is operatively connected to the extruder and the concrete reinforcement feeder to receive the unreinforced concrete from the extruder and to receive the one or more elongate reinforcement members from the concrete reinforcement feeder. The nozzle combines the unreinforced concrete from the extruder and the one or more elongate reinforcement members from the concrete reinforcement feeder into a reinforced concrete …

Image-Based Bridge Defect Detection And Monitoring Technologies, Jian Zhang

INSPIRE Archived Webinars

Computer-vision is an emerging technology which has been widely used in the field of structural health monitoring. This seminar will cover the latest achievements of our research group in defect detection, health monitoring, and construction control using image-based technologies. For defect detection, advanced unmanned aerial vehicles (UAVs) have been developed to automatically detect surface cracks and other types of structural damages based on digital image processing techniques. An integrated navigation system combining binocular camera and inertial sensor enables automated route planning for the developed UAVs in case of GPS failure. Specifically, a wall-climbing UAV is designed to acquire detailed surface …

Evaluation Of Guayule Resin As An Innovative Bio-Based Asphalt Alternative In Mix Performance -- Preprint, Ahmed Hemida, Magdy Abdelrahman

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Literature revealed the potential of using guayule resin for asphalt cement replacement from the binder’s perspective. However, monitoring guayule resin through binder-aggregate mixture could disclose its performance through field. In this study, designated binders were employed to investigate the applicability of such an innovative replacer through mixture, which were neat asphalt and guayule-based binders (neat guayule, asphalt-rubber-guayule, guayule-rubber binders). Consecutively, field-simulated lab mixtures were prepared to investigate the major distresses. Moisture damage, rutting, fatigue cracking, and thermal cracking resistances were investigated using the modified Lottman (TSR) test, rut test by asphalt pavement analyzer (APA), semi-circular bending (SCB) test, and disk-shaped …

Poster Awards Ceremony, Hongyan Ma

INSPIRE-UTC Annual Meetings

• 1st Place: Dongbin Kim, Missouri S&T, A Human-Embodied Drone for Dexterous Aerial Manipulation
• 2nd Place: Yu Otsuki, Georgia Tech, Autonomous ultrasonic thickness measurement using Martlet wireless sensing system integrated with a steel climbing mobile robot
• 3rd Place: Pu Jiao, Missouri S&T, INSPIRE UTC Bridge Inspection Field Campaign Update, 2021

Closing Remarks And Winners Announced, Hongyan Ma

INSPIRE-UTC Annual Meetings

Closing Remarks and Winners Announced by INSPIRE UTC Graduate Student Poster Session Chair Dr. Hongyan Ma, Assistant Professor, Civil, Architectural & Environmental Engineering, Missouri S&T

Improving 3d Metric Gpr Imaging Using Robotic Data Collection And Dnn Based Processing, Jinglun Feng

INSPIRE-UTC Annual Meetings

GPR is one of the most important NDE devices to detect subsurface objects and reconstruct the underground scene. There are two challenges for GPR- based inspection, which are GPR data collection and subsurface object imaging. To address these challenges, we propose a robotic solution that automates the GPR data collection process with a free motion pattern. It facilitates the 3D metric GPR imaging by tagging the pose information with GPR measurement in real-time. We also introduce a DNN based GPR data analysis method which includes a noise removal segmentation module to clear the noise in GPR raw data and a …

Encoding Time-Series Ground Motions As Images For Convolutional Neural Networks-Based Seismic Damage Evaluation, Xinzhe Yuan

INSPIRE-UTC Annual Meetings

Earthquake records can be encoded as images to classify their resulting damage states to structures based on convolutional neural networks (CNNs). Different encoding techniques such as Recurrence Plot (RP) and Wavelet Transform (WT) can be used to transfer earthquake records to images. Presently, no consensus has been reached on the understanding of the most suitable encoding technique for CNN-based seismic damage classification. In this study, we develop a new encoding technique based on Time-series Segmentation (TS) and compare it to state-of-the-art RP and WT techniques. These techniques are mainly compared based on their classification accuracy and computation efficiency.

Reveal Underground Defects Through Impact Sounding (Is) And Impact Echo (Ie), Ejup Hoxha

INSPIRE-UTC Annual Meetings

Impact Echo (IE) and Impact Sounding (IS) are well-developed non-destructive evaluation (NDE) methods that are widely used for inspection of concrete structures to ensure safety and sustainability. However, it is a tedious work to collect IE and IS data along grid lines covering large target area for characterization of subsurface defects. On the other hand, data processing is very complicated and requires domain experts to interpret the results. To address the above problems, we present a robotic inspection system, to automate the data collection process and introduce data analytics software to visualize the inspection results allowing non-professionals to easily understand …

Autonomous Ultrasonic Thickness Measurement Using Martlet Wireless Sensing System Integrated With A Steel Climbing Mobile Robot, Yu Otsuki

INSPIRE-UTC Annual Meetings

The objective of this research is to develop an autonomous ultrasonic thickness measurement system for steel bridge members through the integration of wireless sensing and robotics. The ultrasonic thickness measurement is achieved using a transducer that requires access to only one side of a steel bridge member. Building upon the Martlet wireless sensing platform, this project first develops pulser and ultrasonic daughter boards to generate a pulse excitation and to filter and amplify the received ultrasonic signal. The developed Martlet wireless ultrasonic device is next integrated with a steel climbing mobile robot developed by University of Nevada, Reno (UNR). The …

Drone Vision-Based Clamping Strategy For Bridge Inspection, Bo Shang

INSPIRE-UTC Annual Meetings

Most bridges in the United States are near their designed lifetime. So, policy needs bridges to be inspected every two years. Currently, most of those inspections are done by human which needs to block the traffic and can cause injury. MST INSPIRE-UTC’s project Bridge Inspection Robot Deployment Systems (BIRDS) tries to develop a flying and climbing platform that has the following benefit:

• Capturing high quality data for inspection without vibration;
• Free of blocking traffic;
• Operator and inspector are safe.

Gas Leakage Detection With Hyperspectral Imagery-Based Vegetation Stress Indices, Pengfei Ma

INSPIRE-UTC Annual Meetings

The objective of this research is to provide a basis for gas leakage detection with hyperspectral cameras. The gas leakage attacks vegetations, which yields some spectral signature changes. As the vegetation under different stressors may induce similar effect. The spectral signature changes can be similar. A lab test was arranged to test three kinds of plants under four common natural stressors with a reference. All plants are routinely scanned with hyperspectral cameras every three days to obtain every developmental stage. Linear discriminant analysis (LDR) was applied in the data analysis to discriminate the plant with gas leakage treatment from the …

A Human-Embodied Drone For Dexterous Aerial Manipulation, Dongbin Kim

INSPIRE-UTC Annual Meetings

Current drones passively surveil. Drones equipped with robotic arms shift this paradigm: the drone is actively interacting with the environment rather than simply sensing it. This would be needed to robotically enhance bridge-related work, called dexterous aerial manipulation: drones could hose decks; drilling on surfaces; and epoxy cracks. Such research is important to advancing bridge maintenance and repair.

Recently, the worker’s experience was integrated in aerial manipulation using haptic technology. The net effect is such system could enable the worker to leverage drones to collaborative perform haptic assessments of the objects and complete tasks on the bridge remotely. However, the …

Probability Of Detection In Corrosion Monitoring With Fe-C Coated Lpfg Sensors, Ying Zhuo

INSPIRE-UTC Annual Meetings

This project aims to develop two statistical methods for determining the probability of detection in corrosion monitoring using long period fiber gratings (LPFG) sensors with thin Fe-C coating, validate these methods from independent laboratory tests, and determine the steel mass loss at 90% probability of detection and the largest steel mass loss that may miss from a corrosion inspection at 95% upper confidence bounds. LPFG sensors could reflect the corrosion process by the wavelength shift in the transmission spectrum due to the change of the refractive index of the Fe-C coating. POD is a method used to determine the capability …

Smart Sounding System For Autonomous Evaluation Of Concrete Structures, Deepak Kumar

INSPIRE-UTC Annual Meetings

Impact sounding has been used successfully to detect defects in concrete structures. Recent research has shown that the sounding, such as chirp signal, can be generated by electronic speakers, and can be designed with controlled frequency characteristics to excite defects in concrete decks. The bottom of a deck cannot be conventionally sounded, and precise location of the damaged area is a challenge. The focus of this research is on development of a “Smart Sounding System” that can be used to inspect the underdeck and pier surfaces effectively and autonomously.

Inspire Utc Bridge Inspection Field Campaign Update, 2021, Pu Jiao

INSPIRE-UTC Annual Meetings

Bridge inspection activities using robotic sensing system are surging in the recent years due to the increasing demand of infrastructure maintenance and development of commercial drones and open-source robotic platforms. On the other hand, the data acquired through bridge inspection is also booming, which stimulated the application of machine learning in infrastructure.

At INSPIRE UTC of Missouri University of Science and Technology, bridge inspection equipment’s are being developed and tested for comprehensive data collection using multiple sensing technologies. This paper presents and evaluates the drone-carried sensors’ abilities and applications after 3 bridge inspections in Missouri in 2021 and sketches the …

Multi-Directional Bicycle Robot For Steel Bridge Inspection, Son Thanh Nguyen

INSPIRE-UTC Annual Meetings

In contrast to the current climbing robots, this research presents a new design and implementation of a roller chain-based climbing robot to provide a practical solution for steel structure inspection (bridges, poles, pipes, etc.)

The proposed roller chain-like robot has 12 joints for moving and 3 pairs of joints for turning, which makes the robot very flexible. This setup allows the robot to traverse areas of complex geometry on steel bridges. The robot utilizes permanent magnets to be able to well adhere on steel structures while moving.

Inspire Utc Bridge Inspection Field Campaign Update, 2021, Pu Jiao

INSPIRE-UTC Annual Meetings

Bridge inspection activities using robotic sensing system are surging in the recent years due to the increasing demand of infrastructure maintenance and development of commercial drones and open-source robotic platforms. On the other hand, the data acquired through bridge inspection is also booming, which stimulated the application of machine learning in infrastructure.

At INSPIRE UTC of Missouri University of Science and Technology, bridge inspection equipment’s are being developed and tested for comprehensive data collection using multiple sensing technologies. This paper presents and evaluates the drone-carried sensors’ abilities and applications after 3 bridge inspections in Missouri in 2021 and sketches the …

2021 Technical Program, Inspire - University Transportation Center

INSPIRE-UTC Annual Meetings

INSPIRE University Transportation Center 2020 Annual Meeting
August 10-11, 2021

Mrda-Mgfsnet: Network Based On A Multi-Rate Dilated Attention Mechanism And Multi-Granularity Feature Sharer For Image-Based Butterflies Fine-Grained Classification, Maopeng Li, Guoxiong Zhou, Weiwei Cai, Jiayong Li, Mingxuan Li, Mingfang He, Yahui Hu, Liujun Li

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Aiming at solving the problems of high background complexity of some butterfly images and the difficulty in identifying them caused by their small inter-class variance, we propose a new fine-grained butterfly classification architecture, called Network based on Multi-rate Dilated Attention Mechanism and Multi-granularity Feature Sharer (MRDA-MGFSNet). First, in this network, in order to effectively identify similar patterns between butterflies and suppress the information that is similar to the butterfly's features in the background but is invalid, a Multi-rate Dilated Attention Mechanism (MRDA) with a symmetrical structure which assigns different weights to channel and spatial features is designed. Second, fusing the …

Fiber Optic Sensor Based Corrosion Assessment In Reinforced Concrete Members, Genda Chen

INSPIRE Archived Webinars

In this 50-minute lecture, the fundamental concepts of fiber optic sensors for both distributed and point corrosion measurements are reviewed. For the distributed monitoring of a line bridge component such as steel reinforced girders, Brillouin scattering and fiber Bragg gratings (FBG) can be coupled to measure both temperature and radial strain as an indirect indicator of corrosion process. For the point monitoring of steel structures, long period fiber gratings (LPFG) are specially designed for a direct measurement of mass loss or the loss in cross sectional area of the component. In particular, a Fe-C coated LPFG sensor is introduced for …

Case Studies Of Problematic Expansive Soils: Characterization Challenges, Innovative Stabilization Designs, And Novel Monitoring Methods, Anand J. Puppala

Abbett Distinguished Seminar Series

This presentation describes key research works on expansive soils, the methods employed to characterize them, and fallacies in the current characterization of expansive soils. Novel swell characterization models that account for hydro, chemical, and mechanical behaviors of soils are introduced and used in various case studies to improve expansive soil stabilization practices. An innovative design method for successful stabilization of expansive soil is introduced in one case study which incorporated both basic clay mineralogy and unsaturated soil behaviors, as well as performance-based durability studies. Sulfate soil stabilization works on medium-to-high sulfate soils are presented in another case study. The last …

Investigating The Relationship Between The Fatigue Cracking Resistance And Thermal Characteristics Of Asphalt Binders Extracted From Field Mixes Containing Recycled Materials, Eslam Deef-Allah, Magdy Abdelrahman

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Asphalt components have a significant contribution to the fatigue cracking resistance of asphalt mixes. Softer asphalt binders, characterized through the Superpave grading system, resist fatigue cracking more than stiffer binders. During the long-term aging, the binders’ components changed from lower- to higher-molecular-weight constituents that increased binders’ stiffnesses. Using recycled materials in the mixes increases the stiffnesses of the binders inside these mixes by altering the binders’ components. The binders were extracted and recovered (E & R) from field mixes containing different percentages of recycled materials [reclaimed asphalt pavement (RAP) and recycled asphalt shingles] and binders’ performance grades. The fatigue resistance …

Semi-Annual Progress Report #8, Missouri University Of Science And Technology. Inspire - University Transportation Center

Semi-Annual Progress Reports

No abstract provided.

Encoding Time-Series Ground Motions As Images For Convolutional Neural Networks-Based Seismic Damage Evaluation, Xinzhe Yuan, Dustin Tanksley, Pu Jiao, Liujun Li, Genda Chen, Donald C. Wunsch

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Traditional methods for seismic damage evaluation require manual extractions of intensity measures (IMs) to properly represent the record-to-record variation of ground motions. Contemporary methods such as convolutional neural networks (CNNs) for time series classification and seismic damage evaluation face a challenge in training due to a huge task of ground-motion image encoding. Presently, no consensus has been reached on the understanding of the most suitable encoding technique and image size (width × height × channel) for CNN-based seismic damage evaluation. In this study, we propose and develop a new image encoding technique based on time-series segmentation (TS) to transform acceleration …

Establishment Of Regional Phytoremediation Buffer Systems For Ecological Restoration In The Great Lakes Basin, Usa. Ii. New Clones Show Exceptional Promise, Andrej Pilipović, Ronald S. Zalesny, Elizabeth R. Rogers, Bernard G. Mcmahon, Neil D. Nelson, Joel Gerard Burken, Richard A. Hallett, Chung Ho Lin

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Poplar tree improvement strategies are needed to enhance ecosystem services’ provisioning and achieve phytoremediation objectives. We evaluated the establishment potential of new poplar clones developed at the University of Minnesota Duluth, Natural Resources Research Institute (NRRI) from sixteen phytoremediation buffer systems (phyto buffers) (buffer groups: 2017 × 6; 2018 × 5; 2019 × 5) throughout the Lake Superior and Lake Michigan watersheds. We divided clones into Experimental (testing stage genotypes) and Common (commercial and/or research genotypes) clone groups and compared them with each other and each NRRI clone (NRRI group) at the phyto buffers. We tested for differences in clone …