PSA - Perform a Study of the Potential Benefits to Deploy the BLU-X Treatment Discovery Project for SB WWTP - EmNet LLC

Home Browse Search

strategy for aeration energy reduction and other critical parameters within the WWTP based on the plant's needs at that moment and in the near -term future. In principle, BLU- X applies the same process strategies as human operators; however, it can make predictive decisions, accounting for all available data and forecasting water quality of the final effluent. This helps to raise the level of precision to a new standard. At any point in time, BLU-X Treatment considers all parameters (e.g. ammonium, nitrate, etc.) and can adjust process setpoints (e.g. nitrification, den itrification) to optimal conditions. In each stage of project delivery, even before any software is implemented, the careful analysis of data leads to the discovery of valuable information that can be used to improve the performance of the plant. Through this process, many of our clients have gained insights that helped to significantly reduce costs and improve process stability while ensuring water quality compliance. Real world measuremients are the intuits: Influent quantity Temperature Loads Total Solids W Aeration Intensity Recirculation..............................................................................._w. Dosings Artificial Neural Network -Model empirical, data driver" -------------- -* Degradation Rates - ........................ Effluent Concentrations Eniergy Consumption - .......................... Efficiency Setpoi nts 41Reliability of prediction Figure 2. Representation of a data driven neural network developed to create a digital twin in BLU-X treatment. As an example, the BLU-X Treatment solution was applied to the Cuxhaven Wastewater Treatment Plant in Cuxhaven, Germany in early 2017. BLU-X provided a real time digital twin of the entire plant so that each process receives optimal aeration and chemical inputs to match the needed chemical and biological oxygen demand. Since the utility had limited online sensors available to take real time measurements of influent concentrations, several "virtual" or "soft" sensors were developed to calculate an estimate of the incoming carbon, nitrogen, and phosphorous loads of the influent. In the absence of traditional sensor data, these virtual sensors helped the utility accurately estimate influent concentration to operate the aeration process in the most efficient way while meeting regulatory requirements. The optimized operation of the plant resulted in a drastic reduction in these fluctuations and prevented situational peak energy consumption (Figure 3). Page 3 of 6