A One-Class-Based Supervision System to Detect Unexpected Events in Wastewater Treatment Plants
, Míriam Timiraos 1,2,†, Antonio Díaz-Longueira 1,3,†, Álvaro Michelena 1,3,*,†, Esteban Jove 1,3,† and José Luis Calvo-Rolle 1,3,†Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThis paper proposes a detection method for unexpected events in waste water treatment plants. Some issues need to be solved.
1. The references need to be further optimized, and there are two other issues that I hope to add.
-
[1] H. Lin, C. Lin, D. Xie, P. Acuna and W. Liu, "A Counter-Based Open-Circuit Switch Fault Diagnostic Method for a Single-Phase Cascaded H-Bridge Multilevel Converter," in IEEE Transactions on Power Electronics, vol. 39, no. 1, pp. 814-825, Jan. 2024.
[2] H. Lin, C. Cai, J. Chen, Y. Gao, S. Vazquez and Y. Li, "Modulation and Control Independent Dead-Zone Compensation for H-Bridge Converters: A Simplified Digital Logic Scheme," in IEEE Transactions on Industrial Electronics, doi: 10.1109/TIE.2024.3370975.
[3] Murei, A., Kamika, I., & Momba, M. N. B. (2024). Selection of a diagnostic tool for microbial water quality monitoring and management of faecal contamination of water sources in rural communities. Science of The Total Environment, 906, 167484.
-
2. In the design of wastewater detection, monitoring variables and thresholds are key to influencing the sensitivity of the classifier, and further clarification is needed on how to select effective detection variables and improve classification sensitivity.
-
3. The experimental test results for the classifier should be further supplemented to graphically demonstrate the robustness of the classifier under different variables and test conditions.
Minor editing of English language required.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsThis article presents an important contribution in the field of monitoring and optimizing wastewater treatment plants (WWTPs). The authors describes the detection of unexpected events in these facilities and propose the use of various one-class techniques for this task. I appreciate the amount of data from the realised experiments and the graphic quality of the article.
The article is very good structured, allowing for easy understanding of the presented issues and procedures. The authors provide detailed descriptions of the methods used and their experimental settings, enabling the replication of research results. There is no discussion. I suggest adding a discussion in the separate part of the article.
It is necessary to explain more Fig. 2 and 3. At the page 5 is table, and 2 pictures only with short explanation at the previous page.
Please use full title for the chapter 2.3.4, not only shortcut.
Consider changing the title of chapter 2.3.3 kmeans to The kmeans algorithm or Application of the kmeans algorith
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsComments and suggestions for authors
The research is well related, I just suggest some points for improvement.
1- Why do chemists believe that these are the critical variables? COD_S, 170, NH3_S and NTK_S.
2- It is important to mention if there prevision a for other critical variables.
3- What are the input data of the neural network?
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
