Response Surface Methodology Optimization of Operation Conditions of Dynamic Cloth Media Filtration Used in Primary Wastewater Treatment

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Abstract Operation of wastewater treatment facilities (WWTF) is essential for human and environmental health but is energy intensive, prompting the need for optimal operation to minimize energy consumption while providing high-quality effluent. Our goal is to identify optimal operational set points for a primary cloth media filtration system under dynamic influent conditions. Machine learning techniques such as reinforcement learning are gaining traction in WWTF, but many facilities lack the automation to adopt these advanced methods. As a practical alternative, response surface methodology is paired with constrained optimization to identify optimal operational settings, such as maximum water level in the tank and backwash time. We target reductions in effluent total suspended solids (TSS) to maintain high effluent quality and backwashes per hour to minimize energy consumption. Water level changes are monitored as a proxy for long-term performance of the filter. Data are collected from the system operating at specific combinations of set points, models are constructed for multiple different responses, optimal operating set points are identified, and the performance of one of the models is validated in real time. With a fixed influent flow rate, dynamically optimized set points improve filter operation. In varied flow scenarios, static optimal inputs enhance TSS removal and minimize energy consumption.