Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Building and Real Estate | en_US |
| dc.contributor.advisor | Zayed, Tarek (BRE) | en_US |
| dc.creator | Alshami, Ahmad Ass'ad Mohammad | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/11204 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Smart monitoring system for sewer overflow in Hong Kong | en_US |
| dcterms.abstract | Efficient, operational monitoring of sewer networks is crucial for sustainable infrastructure management, but it has received inadequate research attention globally. To facilitate real-time decision making for maintenance and operational purposes, studies in the past decade focused on developing sensor-based monitoring systems. However, there is a dearth of literature presenting effective sensor-based overflow sewer monitoring systems. Thus, in this research, four main objectives were addressed in two phases, starting with a literature review to suggest the main mechanisms required to develop effective sewer monitoring systems. And ends with the development of a smart system for sewer overflow monitoring and validating it under real operating conditions and within a typical urban environment. In the first phase, a scientometric and systematic reviews were conducted on 71 relevant research papers published between 1990 and 2020 to highlight the global trends in publication outlets, co-occurrence of keywords, co-authorships, and active research countries. The study revealed that only 11% of all countries worldwide were involved in sewer monitoring system research and the top two countries were the United States and United Kingdom. Furthermore, systematic review examined the different types of communication mechanisms and sensor systems that were utilized as well as their advantages, disadvantages, and applications. It was also observed that less than 10% of monitoring systems used artificial intelligence methods to predict results in real-time. This review assessed the characteristics of effective monitoring systems and identified some research gaps. These included the use of new technologies in sensor systems, and the application of information technology in developing efficient communication mechanisms between sensors and servers. | en_US |
| dcterms.abstract | The second phase of this research, which included the second, third, and fourth objectives, was the development of an effective, integrated and interactive monitoring system for sewage flooding. This phase included the adoption of the sensing system, data collection, big data analysis, study of sewage system challenges and problems, statement of risks and solutions, artificial intelligence modeling, application development, implementation, and verification. Through this process, 3 million readings were collected from the level sensors, and 2 million was the final number of readings after the cleaning process. The results of the analysis showed that the performance of the sewage network differs from one site to another. In addition, complete and partial blockages can lead to a high risk of overflow within minutes, and regular cleaning work can improve network performance and reduce risk by more than 30%. Moreover, it was found that flow sensors will not give accurate results when used in sewage networks with small pipe sizes, and to solve this problem the vertical velocity inside the manhole was proposed as an alternative method. It was also found that modeling based on data patterns will not provide us with integrated models. Hence, different adaptive decision trees have been developed based on key features rather than data patterns. The F1 score for this model was 100%, and it could work anywhere. These models are included in the developed application, which has the ability to predict overflow states, remaining time to overflow, and blockage situations. The results of this tool will be displayed in an interactive GIS map, as well as warning emails with analysis results will be sent, and daily, weekly and monthly reports will be produced. This research provides a very useful reference for researchers and practitioners interested in sewage network monitoring systems. | en_US |
| dcterms.extent | xiv, 147 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2021 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Sewerage -- Management -- China -- Hong Kong | en_US |
| dcterms.LCSH | Combined sewer overflows | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5687.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 8.61 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/11204