Fault Detection of Wastewater Treatment Plants Based on an Improved Kernel Extreme Learning Machine Method

Round 1

Reviewer 1 Report

Abstract should be rewritten by including the following information: short intro and problem statement, objectives, methods, results, and concluding remarks. Current version contains lot information on method without any information on results and concrete concluding remarks.

Introduction

• Line 44: check this sentence “…wavelet and Fourier transform theory. in the process of wastewater treatment..”
• Define KELM. Check for the other definition throughout the manuscript

Moved problem statement section to introduction

Section 3 – change to materials and methods

Why NH3-N is not considered in this simulation.

How simulation was performed?Please specify the software used in this study

Are all equations in Section 3 developed by to authors?If not please specify the references

 

Section 4 – Lack of discussion. Authors on report the finding without any depth discussion and comparison with other techniques.

Author Response

Please see the attachment！

Author Response File: Author Response.pdf

Reviewer 2 Report

The manuscript “Fault detection of wastewater treatment plants based on an improved kernel extreme learning machine method” (ID: water-2342283) integrates several known machine learning methods and bio-inspired algorithms into one efficient algorithm for application to fault diagnosis in wastewater treatment processes.

I have the following comments:

The summary of the contributions that the authors stated in the penultimate paragraph of the Introduction is not convincing enough because it is difficult to conclude what the novelties are, since all the methods used are known from the cited literature, and in this manuscript they are just integrated into one efficient algorithm.

The authors should additionally explain what the contributions of this manuscript are compared to their previous paper:
19.  Zhou, M.; Zhang, Y.; Wang, J.; Shi, Y.; Puig, V. Water quality indicator interval prediction in wastewater treatment process based on the improved BES-LSSVM algorithm. Sensors 2022, 22, 422. https://doi.org/10.3390/s22020422

Please correct (or explain) the inappropriate dimensions of the matrices in equation (4). Namely, from expression (3) it follows that the matrix H is n x q, according to line 164 beta is q x m, while according to what was explained in line 165 it follows that y is a row vector 1 x m. y should be n x m.

I suggest adding block indentations in Algorithm 1 for clarity.

The Conclusions should be extended and future lines of research should be discussed with more care. Also, Conclusions should be supported by some data.

Author Response

Please see the attachment！

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Authors have revised the manuscript accordingly and it can be accepted for publication.

Reviewer 2 Report

This version of the manuscript “Fault detection of wastewater treatment plants based on an improved kernel extreme learning machine method” (ID: water-2342283) has been changed and additionally explained based on the reviewers' comments. I have no further specific comments or suggestions.

The manuscript can be accepted for publication after appropriate editing.