Bayesian Uncertainty Inferencing for Fault Diagnosis of Intelligent Instruments in IoT Systems
Round 1
Reviewer 1 Report
1. Rearrange the article e.g keywords and intro in on line
2. Explain the integration of IoT with industrial machinery in graphical pattern
3. Rewrite the proposed methodology and write algorithms in proper way
4. In Table 1, 165, 166...? justify?
5. authors need to compare your proposed work with existing work and show the result in tabular form.
Author Response
Please see the attachment
Author Response File: 
Author Response.docx
Reviewer 2 Report
- This paper addresses a relevant topic that concerns fault diagnosis in IoT systems and smart instruments in industrial machines and most often requires the use and manipulation of real-time sensor data and expert knowledge. Remarkably, IoT sensors cannot collect data for diagnosing all types of faults in a specific instrument, and long-distance data transfer introduces additional uncertainties. Because industrial equipment has different causes of failure and complex performance, it is not obvious to obtain accurate data on the source of observed failures. It is in this context that this research work proposes a failure detection and diagnosis model for intelligent instruments obtained using a Bayesian network.
- The aim of this paper is the proposal of a Baysian model as the basis of the method proposed in this paper which focuses on dealing with the uncertainties of expert knowledge and uncertainties of IoT monitoring information in fault diagnosis. In addition, the entropy method based on trapezoidal intuitionistic fuzzy numbers (TrIFN) was applied to aggregate expert knowledge to generate priority probabilities, and the Leaky-OR gate was used on the one hand to calculate CPT on the other hand. The method was then demonstrated using GeNIe software. The results show that the proposed strategy is effective when using an example such as an intelligent pressure transmitter (IPT).
- The authors worked in this research to validate their proposed model for establishing relevant diagnostics. In this framework, they presented a BN-based fault diagnosis approach for industrial instruments in an IoT system. The proposed method deals mainly with the treatment of uncertainties in the construction of the BN model. As a result the entropy method based on TrIFN was applied to aggregate the priority probability, and the leaky-OR gate was used to compute the CPT to handle the uncertainties in determining the priority probability.
- The results of this work are relevant because they have allowed the use of an intelligent pressure transmitter to demonstrate the validity of the proposed model through a sensitivity analysis that has been performed. The results obtained prove that the proposed approach can successfully manage the uncertainties related to the diagnosis of failures and contribute to a more accurate diagnosis and detection of failures of BN models.
- The references are rich and adapted to the requirements imposed by the pertinence of the subject. The conclusions are relevant and consistent with the issues cited in the introduction.
Author Response
A lot of thanks to the reviewer's work.
Reviewer 3 Report
The manuscript entitled "Bayesian Uncertainty Inferencing for Fault Diagnosis of Intelligent Instrument in IoT System " has been prepared by the authors. It needs improvement. Note the following;
1- Writing and grammar need to be corrected.
2- The reviewer isn't sure about innovation. it needs more description.
3- It is nectary to explain the IoT-based networks such as smart grids. You can add the references as follows.
-Tuballa ML, Abundo ML. A review of the development of Smart Grid technologies. Renewable and Sustainable Energy Reviews. 2016 Jun 1;59:710-25.
-Tightiz L, Yang H. A comprehensive review on IoT protocols’ features in smart grid communication. Energies. 2020 Jun 1;13(11):2762.
-Dileep G. A survey on smart grid technologies and applications. Renewable energy. 2020 Feb 1;146:2589-625.
-Saadatmand M, Gharehpetian GB, Siano P, Alhelou HH. PMU-based FOPID controller of large-scale wind-PV farms for LFO damping in smart grid. IEEE Access. 2021 Jul 2;9:94953-69.
-Al-Turjman F, Abujubbeh M. IoT-enabled smart grid via SM: An overview. Future Generation Computer Systems. 2019 Jul 1;96:579-90.
4- Figure 5 must be updated. Use the 5G infrastructure.
5- The quality of the figures is very low.
Author Response
Please see the attachment
Reviewer 4 Report
In general, the paper is well organized and well structured. It gives a detailed discussion and simulation of the proposed methods. The paper reflects the high status of your work by your fellow professionals in the field. However, some major issues are addressed for clarification and enhancement of the work.
1. The research gap and the motivation for the proposed method should be clearly described.
2. The author’s key contributions must be highlighted in the introduction part.
3. Some recent references should be included to justify the novelty of the claims as compared to the pre-existing methods.
4. Whether the authors designed a fault knowledge repository based on experts’ opinions? How it can be validated and how it can able to handle uncertain machine failures?
5. The proposed method seems to be computationally intensive for real-time fault diagnosis. A clarification is required to justify the performance of the claims.
6. The conclusion of the work should be clearly stated by mapping the experimental outcomes and key indications in the Abstract.
7. The analysis is done over small-scale sample fault knowledge. The authors should clarify the fault knowledge elicitation details they used in the paper.
8. The result and discussion section does not lead to any potential outcomes to signify the notable contributions of the authors. Major applicability enhancement is required.
Author Response
Please see the attachment
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
incorporated all the changes
authors check spell and grammatical errors
for e.g
. Rewrite the proposed methodology and write algorithms in proper way
Answer: The proposed methodology part has been rewrited and the algorithm has been rewrited in proper way.
Author Response
The manuscript has been linguistically polished using MDPI's services
Author Response File: 
Author Response.pdf
Reviewer 3 Report
The reviewer's concerns remain.
Author Response
The references have been improved, and the manuscript has been linguistically polished using MDPI's services
Author Response File: Author Response.docx
Reviewer 4 Report
The paper reflects the high status of your work by your fellow professionals in the field.
Proofreading is required to resolve some technical writing issues.
Author Response
The manuscript has been linguistically polished using MDPI's services
Author Response File: Author Response.pdf
Round 3
Reviewer 3 Report
I agree with the acceptance.
Note that, the comments of the reviewers are for the manuscript enhancement and it is recommended that the authors follow the comments and correct all the items.
