Date of Last Revision

2023-05-03 12:51:12

Major

Civil Engineering - Cooperative Education

Degree Name

Bachelor of Science

Date of Expected Graduation

Spring 2019

Abstract

Effective management of runoff from rain and snowmelt is critical as increased water flows can negatively affect efficiency and reliability at treatment facilities, as well as potentially damage property or the natural environment. Implementation of artificial intelligence for real-time decision making and support in wet weather infrastructure is a recent technological development; as such, a problem has emerged: experience and knowledge of best practices for successful implementation is limited. Artificial intelligence is being employed to inform operational decisions that are intended to improve the efficiency and reliability of physical wet weather infrastructure. The goal of municipalities and utilities in utilizing artificial intelligence is to maximize use of the existing physical infrastructure and reduce the need for future capital investment. Because artificial intelligence for real-time decision making and support in wet weather infrastructure is a relatively new technology, experience and knowledge of best practices for successful implementation is limited. In addition, staff have been reluctant to embrace or trust the decisions and support made by the AI systems in certain cases. This study approaches the problem through comprehensive review of recent literature and interviews of those responsible for previous implementations of artificial intelligence in Saint Paul, MN, Buffalo, NY, and Kansas City, MO. Best practices include continuous operator input and ongoing training throughout the project, effective and proper maintenance of the “inputs” to the artificially intelligent system, and incorporation of failsafe mechanisms in the design. As artificial intelligence becomes more prevalent in the civil engineering industry and computers are increasingly given real-time control of systems, this study could provide future designers with a framework for successful implementation of artificial intelligence in wet weather infrastructure projects.

Research Sponsor

Dr. Christopher Miller

First Reader

Dr. David Roke

Second Reader

Dr. Stephen Duirk

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.