Machine learning for energy cost modelling in wastewater treatment plants.
Understanding the energy cost structure of wastewater treatment plants is a relevant topic for plant managers due to the high energy costs and significant saving potentials. Currently, energy cost models are generally generated using logarithmic, exponential or linear functions that could produce not accurate results when the relationship between variables is highly complex and non-linear. In order to overcome this issue, this paper proposes a new methodology based on machine-learning algorithms that perform better with complex datasets. In this paper, machine learning was used to generate high-performing energy cost models for wastewater treatment plants, using a database of 317 wastewater…
A data-driven methodology to support pump performance analysis and energy efficiency optimization in Waste Water Treatment Plants
Abstract Studies and publications from the past ten years demonstrate that generally the energy efficiency of Waste Water Treatment Plants (WWTPs) is unsatisfactory. In this domain, efficient pump energy management can generate economic and environmental benefits. Although the availability of on-line sensors can provide high-frequency information about pump systems, at best, energy assessment is carried out a few times a year using aggregated data. Consequently, pump inefficiencies are normally detected late and the comprehension of pump system dynamics is often not satisfactory. In this paper, a data-driven methodology to support the daily energy decision-making is presented. This innovati…
Pump Efficiency Analysis of Waste Water Treatment Plants: A Data Mining Approach Using Signal Decomposition for Decision Making
In Waste Water Treatment Plants (WWTPs), the pump systems are one of the most energy intensive processes. An efficient energy management of pumps should produce environmental and economic benefits. In this paper, we propose a daily data-driven approach for a detailed pump efficiency analysis that reduces the time gap between an inefficiency and its detection, provides detailed information for decision making by using new Key Performance Indicators (KPIs), and detects inefficient pump set-ups and designs. The proposed approach based on signal decomposition relies on sensors generally available in WWTPs, e.g. daily pump inflow and energy consumption. Moreover, it allows decomposing the data s…
A Tool for Energy Management and Cost Assessment of Pumps in Waste Water Treatment Plants
Waste Water Treatment Plants (WWTPs) are generally considered energy intensive. Substantial energy saving potentials have been identified by several authors. Pumps consume around 12% of the overall WWTP energy consumption. In this paper we propose a methodology that uses the sensors commonly installed in WWTPs, such as volume and energy sensors, to perform energy benchmarking on pumps. The relationship between energy efficiency and flow rate is used to detect specific problems, and potential solutions are proposed, taking into consideration economical and environmental criteria (cost of externalities in energy production). The methodology integrates energy benchmarking, data-mining, and eco…