A Toll-based Approach for Regulating Hazmat Transportation Network Considering Boundedly Rational Route Choice
Honggang Zhang, Southeast UniversityShow Abstract
Zhiyuan Liu, Southeast University
Wei Wang, Ocean University
In this paper, we propose a novel toll policy to regulate the use of roads for hazardous materials (hazmat) shipments considering that the hazmat carriers are bounded rational. Firstly, by using a link-based perception error model to describe hazmat carriers’ bounded rational route choice behavior, we propose a bi-level programming model. The upper level problem is addressed by the authority who aims at minimizing the combination of the total tolls and the maximum total risk of hazmat transportation network, and the lower level problem represents that hazmat carriers choose the shortest path based on their perception error on each link. Then, we decompose the above model into two sub-problems and design a particle swarm optimization algorithm and the K-shortest paths algorithm to solve them, respectively. In addition, we further present the extended model that can achieve a fair hazmat transport risk distribution which modifies the upper level objective and imposes the constraint on the upper bound of the maximum link risk. To illustrate the advantages of the proposed models and algorithms, numerical experiments are conducted based on the Sioux Falls network. The results of our work show that, on the one hand, the authority can effectively control the maximum total risk of hazmat transportation network by implementing toll policy considering carriers’ boundedly rational route choice; on the other hand, the fair hazmat transport risk distribution among different links can be achieved by imposing the constraint on the upper bound of the maximum link risk.
Development of a Novel Framework for Hazardous Materials Placard Recognition System to Conduct Commodity Flow Studies Using Artificial Intelligence AlexNet Convolutional Neural Network
Sherif Gaweesh, University of WyomingShow Abstract
MD Nasim Khan, University of Wyoming
Mohamed Ahmed, University of Wyoming
Conducting Hazardous Materials (HAZMAT) Commodity Flow Studies (CFS) are crucial for Emergency Management Agencies. Identifying the types and amounts of hazardous materials being transported through a specified geographic area will ensure timely response if a HAZMAT incident took place. CFSs are usually conducted using manual data collection methods, which may pose the personnel to some risks by being subjected to road traffic and different weather conditions for several hours. On other hand, the quality and accuracy of the collected HAZMAT data is impacted by the skill and alertness of the data collectors. This study introduces a framework to collect HAZMAT transportation data exploiting advanced image processing and machine learning techniques on video feed. A promising Convolutional Neural Network (CNN), named AlexNet was used to develop and test the automatic HAZMAT placard recognition framework. A solar powered mobile video recording system was developed using high resolution Infra-Red (IR) cameras, connected to Network Video Recorder (NVR) mounted on a mobile trailer. The developed system was used as the incessant data collection system. Manual data collection was also conducted at the same locations to calibrate and validate the new developed system. The results showed that the proposed framework could achieve an accuracy of 95% to identify HAZMAT placards information. The developed system showed significant benefits in reducing the cost of conducting HAZMAT CFS, as well as eliminating the associated risks that data collection personnel could face.
Analysis of Emergency Incidents Regarding Natural Gas Distribution Pipelines
Praveena Penmetsa, University of AlabamaShow Abstract
Md Abu Sufian Talukder, University of Alabama
Naima Islam, University of Alabama
Emmanuel Adanu, University of Alabama
Xiaobing Li, University of Alabama
Kristopher Harbin, Texas A&M Transportation Institute
Alexander Hainen, University of Alabama
Natural gas distribution infrastructure is critical to the daily operation of society. To improve the safety of gas distribution systems, it is vital to understand the combination and interaction of factors that contribute to the severity of incidents involving natural gas distribution pipelines. Hence, this study analyzes five years of PHMSA data using discrete outcome modeling to identify specific factors and their effects on the severity of emergency incidents involving gas distribution systems. Three discrete outcome categories were created based on both the cost of the incident and quantity of gas released to be used as the dependent variable. A multinomial logit model was fitted to the data with several independent variables. Excavation damage, explosion, incorrect operation, and public properties increased the severity of pipeline incidents. Variables such as facility shutdowns, steel pipes, and daylight decreased the severity of the incident. This study serves as a basis for introducing econometric discrete choice modeling to utility researchers, where more findings can be revealed and understood.
DISCLAIMER: All information shared in the TRB Annual Meeting Online Program is subject to change without notice. Changes, if necessary, will be updated in the Online Program and this page is the final authority on schedule information.