Sludge Bulking Monitoring in Industrial Wastewater Treatment Plants Through Graphical Methods : A Dynamic Graph Embedding and Bayesian Networks Approach
The occurrence of sludge bulking is a common problem in wastewater treatment plants (WWTPs) that adversely affects effluent quality by disrupting the normal functioning of the treatment processes. To address this issue, we propose a novel graph-based monitoring framework that utilizes advanced graph-based techniques to detect and diagnose sludge bulking events. . The proposed framework leverages historical datasets under normal operating conditions to extract relevant features and causal relationships between process variables, thereby enabling operators to trigger alarms and diagnose the root cause of the bulking event. The sludge bulking event is detected using the dynamic graph embedding (DGE) method, which extracts similarities among the process variables in temporal and neighborhood dependencies, and the dynamic Bayesian network (DBN) is used to compute the prior and posterior probabilities of a belief, which are updated at each time step; variations in these probabilities indicate the potential root cause of the sludge bulking event. The results demonstrate that the DGE outperforms other linear and non-linear feature extraction methods, achieving a detection rate of 99%, zero false alarms, and less than one percent incorrect detections. In addition, the DBN-based diagnostic method identified the majority of the root causes of sludge bulking, which are primarily due to sudden drops in COD concentration, with an accuracy of 98%, 11% better than state-of-the-art methods
Year of publication: |
[2023]
|
---|---|
Authors: | Loy-Benitez, Jorge ; Tariq, Shahzeb ; Nguyen, Hai ; Heo, SungKu ; Yoo, ChangKyoo |
Publisher: |
[S.l.] : SSRN |
Saved in:
freely available
Saved in favorites
Similar items by person
-
Janghorban Esfahani, Iman, (2014)
-
Janghorban Esfahani, Iman, (2015)
-
Janghorban Esfahani, Iman, (2014)
- More ...