Water Consumption Monitoring System with Fixture Recognition

Date of Award

2020

Document Type

Thesis

Degree Name

Master of Science in Electronics Engineering

Department

Electronics, Computer, and Communications Engineering

First Advisor

Erees Queen B. Macabebe, PhD

Abstract

Water is an essential resource for humans as it is used in many activities for both leisure and hygiene. However, the technology available in monitoring water consumption is limited to the traditional flowmeter. Households and small buildings rely only on the end-of-month billing by the water distributor. This study presents a water monitoring system that uses a non-intrusive sensor. Aside from calculating the volume of water consumed, the system implements fixture recognition using machine learning. This provides more information to users allowing them to identify appliances or fixtures that consume a lot of water. Multiple test sites were used with varying pipe networks from building restrooms to single detached housings to see its viability. Results show that the use of a higher resolution ADC and the implementation of a low pass filter aids the system’s performance. Results also show that using pre-processing techniques such as FFT, the first derivative, a low pass filter, or a combination of these for fixture recognition improved its performance to up to 100 % in all metrics for some datasets.

This document is currently not available here.

Share

COinS