Next Article in Journal
Design and Processing Method for Doppler-Tolerant Stepped-Frequency Waveform Using Staggered PRF
Next Article in Special Issue
Deep Learning for the Industrial Internet of Things (IIoT): A Comprehensive Survey of Techniques, Implementation Frameworks, Potential Applications, and Future Directions
Previous Article in Journal
Uncertainty-Aware Knowledge Distillation for Collision Identification of Collaborative Robots
Previous Article in Special Issue
Recent Technologies, Security Countermeasure and Ongoing Challenges of Industrial Internet of Things (IIoT): A Survey
 
 
Article
Peer-Review Record

Cost-Effective Vibration Analysis through Data-Backed Pipeline Optimisation

Sensors 2021, 21(19), 6678; https://doi.org/10.3390/s21196678
by Artur Sokolovsky 1,*, David Hare 2 and Jorn Mehnen 1
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Sensors 2021, 21(19), 6678; https://doi.org/10.3390/s21196678
Submission received: 18 August 2021 / Revised: 4 October 2021 / Accepted: 6 October 2021 / Published: 8 October 2021
(This article belongs to the Special Issue Smart Sensors in the Industrial Internet of Things (IIoT))

Round 1

Reviewer 1 Report

The article presents an effective vibration analysis and fault diagnosis scheme for IoT systems. I read the article with much interest, and founded interesting. However, I have a comment that need to be addressed. Resonance band demodulation (also called envelope analysis) is a very effective technique for extracting bearing failure features. Generally, the resonance frequency band is higher than 1kHz. This situation also needs to be discussed.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

This paper introduces a Cost-effective vibration analysis through data-backed pipeline optimisation. The proposed optimisation approach, as well as statistically supported 15 findings of the study, allow for an efficient design of IoT vibration analysis systems, both in terms 16 of complexity and costs, bringing us one step closer to the widely accessible IoT/Edge-based 17 vibration analysis.

As above, the manuscript presents interesting and novel approach for IoT vibration analysis. It can be accepted after major revision.

 

  1. The manuscript presents the results of the proposed approach. However, the comparison with other machine learning or deep learning method is absent. The coresponding comparison should be presented to demonstrate the efficiency and performance.
  2. The statement in Introduction for the industrial problem for solving should be introduced more detailly, such as, the computing capacity required for actual operation in industrial scenarios.
  3. The actual calculation delay and the signal processing and inference speed of each method; although the paper does a complete hypothesis, inference and simulation verification, but lack of actual implementation results, may still result unpredictable (failure) in applications.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The manuscript can be accepted for publication.

Back to TopTop