ÃÛÌÒÊÓƵ

The Mariner Safety Research Initiative (MSRI) is a product of the collaborative effort between American Bureau of Shipping (ABS), ÃÛÌÒÊÓƵ University, and International Industry Partners. The MSRI includes a large international database of more than 100,000 maritime injury and close call (near miss) reports from over 31 data sources. Dr. Craig (PI), Dr. Curry (CO-PI), and Dr. Zhu (CO-PI) have worked on this project since 2010.

The incident databases have enabled us to create the MSRI, a public forum to share safety related materials and resources with not only industry partners, but the maritime industry as a whole. The incident data has been analyzed to identify trends, possible causes and lessons learned and develop safety related guidance materials including benchmarking statistics and relevant training tools. The overall goal of the MSRI is to improve mariner safety through sharing these data findings and providing safety related documents in a useable context.

The MSRI is broken up into two parts: the Public Site and the Industry Partner Site. The public site includes a general “sampling” of the documents and information that is available to the MSRI Industry Partners. For more information about this project, please see http://maritime.lamar.edu/.

Dr. Craig and Dr. Curry are the ÃÛÌÒÊÓƵ participants on a multi-year grant project for The Gulf Research Program (GRP) of the National Academies of Sciences, Engineering, and Medicine titled "Developing an Integrated Offshore Energy Industry Safety Culture Evaluation, Benchmarking, and Improvement Toolbox" with ABS and the University of Houston. Read More.

This Research Experiences for Teachers (RET) in Engineering and Computer Science Site, entitled, Incorporating Engineering Design and Manufacturing into High School Curriculum, at ÃÛÌÒÊÓƵ University (LU) Beaumont, will provide opportunities for STEM high school teachers from underserved school districts in Southeast Texas to engage in cutting-edge advanced engineering design and manufacturing research and develop curriculum modules based on their research. Advanced design and manufacturing is an industry with growing opportunities for creating the next generation workforce.

For more information, please see:

Sponsor: Sabine Neches Navigating District

Research Team:
Dr. Victor Zaloom, Principal Investigator, Professor of Industrial Engineering
Drs. Qin Qian, Xing Wu, Mien Jao, Co-Principal Investigators, Dept. of Civil Engineering
Mr. Ben Kolkmeier, MESCE Student, ÃÛÌÒÊÓƵ College of Engineering
Dr. Keh-Han Wang, Professor of Civil Engineering, University of Houston

Funding: $99,742

Project Summary:
The force and velocity of waves especially those produced by passing ships was measured at two strategic locations in the Sabine Neches Water Way. We measured flow velocity and wave characteristics including wave height, speed and orientation. Data analysis included wave height and wave energy especially those produced by passing ships. We obtained ship data from the USCG and correlated ship size, speed, and other parameters to wave impacts on the river bank and subsequent erosion. Erosion is a problem for two reasons. It causes loss of land but more important to our sponsor the Sabine Neches Navigation District the much of the material that results from river bank erosion ends up in the deep draft ship navigation channel thus reducing the depth of the channel. This material must then be dredges out of the Navigation channel and deposited elsewhere. It is usually deposited in placement areas. This is an expensive process. Phase II will be devoted to evaluating and recommending wave attenuation remedies that will result in less erosion and subsequent need to dredge the material from the navigation channel.

Design and evaluation of engineering systems to reduce erosion caused by ship generated and other waves will be accomplished in Phase II of this project.

Dr. Hamidi and Dr. Craig are working on a project to develop a unique rail yard software tool for an industry sponsored project. Read more.

The need for safe operation and effective maintenance of pipelines grows as oil and gas demand rises. Thereby, it is increasingly imperative to monitor and inspect the pipeline system, detect causes contributing to developing pipeline damage, and perform preventive maintenance in a timely manner. Currently, pipeline inspection is performed at pre-determined intervals of several months, which is not sufficiently robust in terms of timeliness. This research proposes a drone and artificial intelligence reconsolidated technological solution (DARTS) by integrating drone technology and deep learning technique. This solution is aimed to detect the targeted potential root problems—pipes out of alignment and deterioration of pipe support system—that can cause critical pipeline failures and predict the progress of the detected problems by collecting and analyzing image data periodically. The test results show that DARTS can be effectively used to support decision making for preventive pipeline maintenance to increase pipeline system safety and resilience.

Team

Premkumar Ravishankar, Seokyon Hwang, Jing Zhang, Ibrahim X. Khalilullah  and Berna Eren-Tokgoz 

Publications

https://doi.org/10.1007/s13753-022-00439-w

Acknowledgement

This project was partially supported by the Center for Midstream and Management Science at ÃÛÌÒÊÓƵ University, Beaumont, Texas, USA.

PIs: Berna Eren Tokgoz, Seokyon Hwang, Jing Zang
Students: Md. Morshedul Alam (Master of Science in Industrial Engineering), Zanbo Zhu (Master of Science in Computer Science

The electric power distribution network is one of the infrastructures that experience frequent and large-scale damages caused by storms. In particularly, the wooden poles carrying power from local substations to customers are found to be extremely vulnerable to storms. There are several reasons for pole failure such as pole inclination angle, decay over the time, falling trees or branches, etc. Among them, the pole inclination angle is assumed to have significant impacts and not much addressed in existing literature. However, pole failure inevitably leads to power outages for hours, days, or even weeks, depending on the intensity of storms and the severity of damages. A methodology was developed by utilizing the deep learning-based vision technologies integrated with a drone system to determine the pole inclination angle. Then, the angular deflection of a pole was determined by applying wind and gravitational forces. Resilience conditions of a pole are determined based on the angular deflection. A cost-benefit analysis was performed to compare losses and savings for different pole conditions. Different strategies were examined based on an angular deflection during the service life of a pole.

There is a visible paradigm shift in debris management to developing framework for community resilience. Debris management has always been one of many competing priorities that agencies must managed especially in waterways and shorelines. It is necessary that debris be properly managed to comply with regulations, conserve disposal capacity, protect human health and minimizing environmental impacts. A community should be prepared with a recovery plan for removing debris from waterways and sensitive habitats such as shorelines and wetlands before the presence of any event that might cause debris formation to recover fast and to have a better response towards the removal of the debris formed. In this research, the Port of Port Arthur was selected for the analysis of the debris formation along with the waterway streamline and assessing the debris formation by using remote sensing and spatial analysis. A Mavic 2 Pro drone was used to capture the videos from Port Arthur Independent School District, TX, with coordinates 29°55'41.0"N 93°52'18.1"W, and a height between 29 to 375 feet above the waterway. To assess the debris formed on the shores of the waterway of the port and inside the water streamline, the drone videos were analyzed by a deep learning neural network to segment water regions from video frames and the debris on the water surface were detected using an adaptive thresholding method.

Methodology

Drone technology has received intensive attention in many research areas recently because of its impressive data collection capability. UAV can provide high-resolution photos and videos in a much more convenient and flexible way compared to traditional methods. Meanwhile, the rapid development of advanced machine learning (ML) and deep learning (DL) algorithms have achieved many impressive breakthroughs in various research areas. Therefore, in this project a deep learning neural network is applied to detect and segment debris on the water surface from drone videos and then used computer vision algorithms to estimate debris area.

Team

Nader Madkour, Berna Eren-Tokgoz, Jing Zhang, Seakyon Hwang, and Zhe Luo

Acknowledgments

This work was funded by the Center for Advances in Port Management at ÃÛÌÒÊÓƵ University, Beaumont, TX

A methodology will be presented for a temporary closure scheduling of the Houston Ship Channel in order to construct a new bridge over the channel. A poor closure scheduling can cause a substantial loss in revenue for both port authorities and vessels. In this study, we will first analyze historical data for a good estimation of vessels’ traffic and shipping inside the channel, next we will develop a model in ARENA software to simulate the traffic and queue in the ship channel, under different closure scenarios. Constraints will be considered for the working rules of the channel such as daylight restrictions and combined beam rules. Finally, simulation results will be presented for number of the ships affected and also for the total ship time lost as a result of closures, and accordingly, the optimal channel closure schedule will be determined. Besides, policies would be recommended to the port authorities to substitute the current first come, first serve policy.  Please see Dr. Hamidi webpage for more information about her port research effort.

Rahimi, B.*, Abtahi, A., Hamidi, M., Cho, J. & Stromberg, E. “Optimal ship channel closure scheduling for a bridge construction”. In: Proceedings of Institute of Industrial Engineers Annual Conference, May 2017. Accepted.

Dr. Maryam Hamidi on receiving funding to study using deep learning to identify anomalies in compressors.  The industry sponsored project is a collaboration between Computer Science and Industrial and Systems Engineering.

Deep Learning-based Auditory Anomaly Detection and Classification for Natural Gas Compressors, Phase I, (Awarded $40,000, 2021). PI - Zhang, J., Co-PI - Hamidi, M. Funded by Well Checked Systems International, OK and Center for Midstream Management and Science, ÃÛÌÒÊÓƵ University.  See this LU News article for more information.