Next Article in Journal
Optimization of Pre-Splitting Blasting Hole Network Parameters and Engineering Applications in Open Pit Mine
Next Article in Special Issue
Model-Free Adaptive Control Based on Fractional Input-Output Data Model
Previous Article in Journal
Radical Concept Generation Inspired by Cross-Domain Knowledge
Previous Article in Special Issue
Genetic Programming-Based Feature Construction for System Setting Recognition and Component-Level Prognostics
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 12
Issue 10
10.3390/app12104931
Review Report
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

Novelty Detection with Autoencoders for System Health Monitoring in Industrial Environments

Appl. Sci. 2022, 12(10), 4931; https://doi.org/10.3390/app12104931
by Francesco Del Buono 1, Francesca Calabrese 2, Andrea Baraldi 1, Matteo Paganelli 1 and Francesco Guerra 1,*
Reviewer 1:
Gopinath Rajendiran
Reviewer 2: Anonymous
Appl. Sci. 2022, 12(10), 4931; https://doi.org/10.3390/app12104931
Submission received: 11 April 2022 / Revised: 6 May 2022 / Accepted: 11 May 2022 / Published: 13 May 2022
(This article belongs to the Special Issue Complex Systems Reliability and Maintenance Optimal Management Using the PHM Approach and Artificial Intelligence)

Round 1

Reviewer 1 Report

The authors have presented Novelty Detection with Autoencoders for System Health Monitoring in Industrial Environments. Its an interesting work. The paper has been written well. The reviewer has the following comments for improving the paper further. 

1) It is essential to include the pictorial representations of experimental facility/machines/sensors in the paper. 

2) What is meant by c1, c2, c3, c4 conditions. Include the description.

3) Need to include some fundamental discussions on novelty detection concept before using it in the experiments. 

4) Need more clarity on the results, tables, and discussions. 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

The paper aims to support the development of predictive maintenance needed in industrial contexts to predict the occurrence of a failure to minimise unexpected downtimes and maximise the useful life of components.
The needs analysis to support the research is broadly explained concerning the shortcomings that many maintenance sector employees face and the various benefits the new strategy for maintenance management could provide. However, it is not entirely clear how the proposed autoencoder-based architecture will address all the various levels at which changes in maintenance management are dealt with. 
In terms of innovation, it is positive that a study on methods for determining the operating condition in which a machinery works is conducted, as the paper enables to consider several points of view and interpretations. Applicants' claim for innovation is plausible, even if this statement is not highly specific. Particularly, the paper does not present enough evidence of how the authors' research outputs will be distinguished from other offerings as more details are omitted.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The paper could be published as it is.

Back to TopTop