Prediction of Filamentous Sludge Bulking using a State-based Gaussian Processes Regression Model

Abstract

Activated sludge process has been widely adopted to remove pollutants in wastewater treatment plants (WWTPs). However, stable operation of activated sludge process is often compromised by the occurrence of filamentous bulking. The aim of this study is to build a proper model for timely diagnosis and prediction of filamentous sludge bulking in an activated sludge process. This study developed a state-based Gaussian Process Regression (GPR) model to monitor the filamentous sludge bulking related parameter, sludge volume index (SVI), in such a way that the evolution of SVI can be predicted over multi-step ahead. This methodology was validated with SVI data collected from one full-scale WWTP. Online diagnosis and prediction of filamentous bulking sludge with real-time SVI prediction was tested through a simulation study. The results showed that the proposed methodology was capable of predicting future SVIs with good accuracy, thus providing sufficient time for predicting and controlling filamentous sludge bulking.

Effect of Physicochemical Wastewater Parameters and Abiotic Factor on Activated Sludge Sedimentation Capacity

“…These relationships were found by Bagheri et al [6] and by Szeląg and Gawdzik [10], who used artificial intelligence methods to estimate the sedimentation of activated sludge in municipal wastewater treatment plants. This approach, as well as confirmation of the results obtained in the paper, can be found in the works of Han and Qiao [7], Lou and Zhao [9] and Liu et al [15].…”

“…Mathematical models have been used on numerous occasions to predict sludge sedimentation capabilities [8][9][10][11][12][13][14][15], whereby due to the complex nature of the processes occurring in activated sludge they were black-box models, in which the structure of the model is generated at the stage of learning without having to know the physical laws that describe the analyzed phenomenon. The disadvantage of these models is that one cannot clearly determine the impact of particular explanatory variables on the dependent variable.…”

Uncertainty of Forecast and Control of Activated Sludge Sedimentation Capacity

“…These relationships were found by Bagheri et al [14] and by Szeląg and Gawdzik [5], who used artificial intelligence methods to estimate the sedimentation of activated sludge in municipal wastewater treatment plants. This approach, as well as confirmation of the results obtained in the paper, can be found in the works of Han et al [2], Lou and Zhao [3] and Liu et al [15]. In addition, based on the obtained η = f(x i ) curves (Fig.…”

Stochastic Filtering Approach for Condition-Based Maintenance Considering Sensor Degradation

“…However, scheduled operation of activated sludge process is often impeded in presence of filamentous bulking. Sludge bulking occurs largely due to the growth of filamentous bacteria, which can be modeled as a degradation process [46], [47]. In practice, an empirical measurement, Sludge Volume Index (SVI), is commonly used to characterize the degradation of filamentous sludge bulking.…”

“…Fig. 3 shows a schematic of the oxidation ditch process [47]. On the other hand, due to the existence of filamentous bacteria and corrosive materials in the wastewater, the sensor dedicated to inspecting the degradation level of sludge bulking is subject to degradation.…”