Abstract
dc:descriptionDigitalisation can greatly improve process control in wastewater systems but requires increased sensing and monitoring that can provide actionable information. Audio is underutilised as a sensor input despite fluid flow naturally generating sound through different physical processes. This thesis investigates low-cost non-invasive microphones for flow monitoring, laying the groundwork with a qualitative interview study of barriers and opportunities in the wastewater industry before deploying microphones in three fluid flow applications of increasing complexity. High accuracy is achieved with either linear or machine learning-based predictive models, and it is shown that the audio characteristics of importance are dependent on the application.<p></p>
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Jess Holland (21042506)
Subjects
dc:subject × 15Rights
dc:rights- Statement dc:rights
-
- All rights reserved
Identifiers
dc:identifier.*- Identifier
- 10779/exe.32907479.v1
- OAI identifier oai:identifier
- oai:figshare.com:article/32907479