Towards Auto-Building of Embedded FPGA-based Soft Sensors for Wastewater Flow Estimation

TL;DR

This paper proposes an automated, end-to-end IoT-based solution for wastewater flow estimation using deep learning soft sensors, addressing data scarcity, toolchain limitations, and hardware optimization issues.

Contribution

It introduces a novel framework that automates the development and deployment of energy-efficient DL soft sensors on resource-limited IoT devices for wastewater flow estimation.

Findings

Demonstrated reliable flow estimation on resource-constrained IoT hardware.

Provided a prototype IoT device implementing the proposed framework.

Addressed key challenges in dataset availability and hardware optimization.

Abstract

Executing flow estimation using Deep Learning (DL)-based soft sensors on resource-limited IoT devices has demonstrated promise in terms of reliability and energy efficiency. However, its application in the field of wastewater flow estimation remains underexplored due to: (1) a lack of available datasets, (2) inconvenient toolchains for on-device AI model development and deployment, and (3) hardware platforms designed for general DL purposes rather than being optimized for energy-efficient soft sensor applications. This study addresses these gaps by proposing an automated, end-to-end solution for wastewater flow estimation using a prototype IoT device.