Model based evaluation of plant improvement at a large wastewater treatment plant (WWTP)

Application of Machine Learning Methods for an Analysis of E-Nose Multidimensional Signals in Wastewater Treatment

The work represents a successful attempt to combine a gas sensors array with instrumentation (hardware), and machine learning methods as the basis for creating numerical codes (software), together constituting an electronic nose, to correct the classification of the various stages of the wastewater treatment process. To evaluate the multidimensional measurement derived from the gas sensors array, dimensionality reduction was performed using the t-SNE method, which (unlike the commonly used PCA method) preserves the local structure of the data by minimizing the Kullback-Leibler divergence between the two distributions with respect to the location of points on the map. The k-median method was used to evaluate the discretization potential of the collected multidimensional data. It showed that observations from different stages of the wastewater treatment process have varying chemical fingerprints. In the final stage of data analysis, a supervised machine learning method, in the form of a random forest, was used to classify observations based on the measurements from the sensors array. The quality of the resulting model was assessed based on several measures commonly used in classification tasks. All the measures used confirmed that the classification model perfectly assigned classes to the observations from the test set, which also confirmed the absence of model overfitting.

Model-Based Solution for Upgrading Nitrogen Removal for a Full-Scale Municipal Wastewater Treatment Plant with CASS Process

Aiming at providing cost-effective approach for upgrading the existing municipal wastewater treatment plants in the cold region of China to meet more stringent discharge standards of nitrogen removal, a full-scale sewage treatment plant with the CASS process was selected through focusing on biological process, key equipment and hydrodynamics in bioreactors by the activated sludge model 1 (ASM1) and computational fluid dynamics (CFD) model. Influent COD fractions and the key characteristic parameters (YH and bH) of the activated sludge were determined through the respirometry at temperatures of 10 °C and 20 °C, respectively. The layout of submerged agitator installation in the bioreactor of the CASS process was optimized through CFD simulation. The calculation of the average relative deviation (less than 20%) between simulated data and the operation data, demonstrated that the ASM1 model could be reasonably used in the wastewater treatment plant simulation. The upgrade solution based on modelling of ASM1 and CFD was successfully applied in practice, which not only made the effluent COD, NH4+-N and TN concentrations meet with the discharge standard of Grade I-A, but also reduced the energy consumption by 25% and 16.67% in summer and winter, respectively. After upgrading, microbial diversity increased in both summer and winter, with an especially significant increase of the relative abundance of denitrifying bacteria.

Advanced Supervisory Control System Implemented at Full-Scale WWTP—A Case Study of Optimization and Energy Balance Improvement

In modern and cost-effective Wastewater Treatment Plants (WWTPs), processes such as aeration, chemical feeds and sludge pumping are usually controlled by an operating system integrated with online sensors. The proper verification of these data-driven measurements and the control of different unit operations at the same time has a strong influence on better understanding and accurately optimizing the biochemical processes at WWTP—especially energy-intensive biological parts (e.g., the nitrification zone/aeration system and denitrification zone/internal recirculation). In this study, by integrating a new powerful PreviSys with data driven from the Supervisory Control and Data Acquisition (SCADA) software and advanced algorithms such as Model Predictive Control (MPC) by using the WEST computer platform, it was possible to conduct different operation strategies for optimizing and improving the energy balance at a full-scale “Klimzowiec” WWTP located in Chorzow (Southern Poland). Moreover, the novel concept of double-checking online data-driven measurements (from installed DO, NO3, NH4 sensors, etc.) by mathematical modelling and computer simulation predictions was applied in order to check the data uncertainty and develop a support operator system (SOS)—an additional tool for the widely-used in-operation and control of modern and cost-effective WWTPs. The results showed that by using sophisticated PreviSys technology, a better understanding and accurate optimization of biochemical processes, as well as more sustainable WWTP operation, can be achieved.

Aeration Process in Bioreactors as the Main Energy Consumer in a Wastewater Treatment Plant. Review of Solutions and Methods of Process Optimization

Due to the key role of the biological decomposition process of organic compounds in wastewater treatment, a very important thing is appropriate aeration of activated sludge, because microorganisms have to be supplied with an appropriate amount of oxygen. Aeration is one of the most energy-consuming processes in the conventional activated sludge systems of wastewater treatment technology (may consume from 50% to 90% of electricity used by a plant), which makes it the most cost-generating process incurred by treatment plants. The paper presents the construction of aeration systems, their classification as well as parameters and factors that significantly affect the aeration process e.g., oxygen transfer efficiency, diffuser fouling, methods of dealing with diffuser fouling, diffuser selection. Additionally, there are briefly presented “smart control” systems in wastewater treatment and effect of application control strategy based on Supervisory Control and Data Acquisition system connected with the decrease in the energy consumption for aeration of bioreactors with activated sludge. It is noted that before the process is optimized, the system should be equipped with suitable metering devices. Only when relevant data is available, the improvements can be carried out. However, it’s important, that the operator should regularly maintain good condition and high efficiency of diffusers.

The evaluation of COD fractionation and modeling as a key factor for appropriate optimization and monitoring of modern cost-effective activated sludge systems

A study was conducted to characterize the raw wastewater entering a modern cost effective municipal WWTP in Poland using two approaches; 1) a combination of modeling and carbonaceous oxygen demand (COD) fractionation using respirometric test coupled with model estimation (RT-ME) and 2) flocculation/filtration COD fractionation method combined with BOD measurements (FF-BOD). It was observed that the particulate fractions of COD obtained using FF-BOD method was higher than those estimated by RT-ME approach. Contrary to the above, the values of inert soluble fraction evaluated by FF-BOD method was significantly lower than RT-ME approach (2.4% and 3.9% respectively). Furthermore, the values for low colloidal and particulate fractions as well as soluble inert fractions were different than expected from a typical municipal wastewater. These observations suggest that even at low load (10% of the total wastewater treatment inflow), the industrial wastewater composition can significantly affect the characteristics of municipal wastewater which could also affect the performance and accuracy of respirometric tests. Therefore, in such cases, comparison of the respirometric tests with flocculation/filtration COD/BOD measurements are recommended. Oxygen uptake rate profile with settled wastewater and/or after coagulation-flocculation, however, could still be recommended as a "rapid" control method for monitoring/optimising modern cost-effective wastewater treatment plants.

Modelization of Nutrient Removal Processes at a Large WWTP Using a Modified ASM2d Model

The biodegradation of particulate substrates starts by a hydrolytic stage. Hydrolysis is a slow reaction and usually becomes the rate limiting step of the organic substrates biodegradation. The objective of this work was to evaluate a novel hydrolysis concept based on a modification of the activated sludge model (ASM2d) and to compare it with the original ASM2d model. The hydrolysis concept was developed in order to accurately predict the use of internal carbon sources in enhanced biological nutrient removal (BNR) processes at a full scale facility located in northern Poland. Both hydrolysis concepts were compared based on the accuracy of their predictions for the main processes taking place at a full-scale facility. From the comparison, it was observed that the modified ASM2d model presented similar predictions to those of the original ASM2d model on the behavior of chemical oxygen demand (COD), NH₄-N, NO₃-N, and PO₄-P. However, the modified model proposed in this work yield better predictions of the oxygen uptake rate (OUR) (up to 5.6 and 5.7%) as well as in the phosphate release and uptake rates.