Next Article in Journal
Robots in Partially Known and Unknown Environments: A Simulated Annealing Approach for Re-Planning
Next Article in Special Issue
Multi-Agent System for Smart Roll-on/Roll-off Terminal Management: Orchestration and Communication Strategies for AI-Driven Optimization
Previous Article in Journal
Flame Combustion State Detection Method of Cement Rotary Furnace Based on Improved RE-DDPM and DAF-FasterNet
 
 
Article
Peer-Review Record

Digitalization and Dynamic Criticality Analysis for Railway Asset Management

Appl. Sci. 2024, 14(22), 10642; https://doi.org/10.3390/app142210642
by Mauricio Rodríguez Hernández 1, Antonio Sánchez-Herguedas 1, Vicente González-Prida 1,*, Sebastián Soto Contreras 2 and Adolfo Crespo Márquez 1
Reviewer 1:
Reviewer 2:
Appl. Sci. 2024, 14(22), 10642; https://doi.org/10.3390/app142210642
Submission received: 12 October 2024 / Revised: 5 November 2024 / Accepted: 15 November 2024 / Published: 18 November 2024
(This article belongs to the Special Issue Big-Data-Driven Advances in Smart Maintenance and Industry 4.0)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This study explores the critical analysis of railway assets using digital technology, which holds significant practical implications for railway operations and resource management. However, there is still room for improvement in the article:

 

1. The keywords are too numerous; it would be advisable to remove a few less important ones.

2. The organizational logic of the first paragraph of the introduction could be improved: first discuss the importance of railway systems and current challenges, followed by the new advantages brought by digital technologies. Specifically, it would be more appropriate to move lines 34-39 to line 60.

3. The full names of the abbreviations in Table 2 should be provided (FMEA, FTA, RBCA).

4. The conclusion of the introduction should briefly state the research objectives and main content of this study, along with an overview of the organizational structure of the remaining sections of the paper.

5. In Section 3.2, a table could be provided with generic or reference original data types and their transformed data.

6. In 3.3.2, is there a standardization criterion or method for determining the weight wj?

7. In 3.3.3, how are α and β determined? What is the rationale for using a linear regression model to predict FF? Are there alternative models or methods?

8. How are the consequences (C) in 3.3.3 and 3.3.5 obtained? What evaluation metrics or methods are used?

9. What is the source of the data in Section 4.1?

10. Since the case study data in Section 4 is historical, how will the system be applied in a real-time environment?

11. Both Table 4 and Table 5 describe the Detailed Steps for the Creation and Population of the Master Board and should be merged into a single table.

12. The content of lines 653-657 and the content in Figure 4 should be replaced with English.

13. Explain SE, MA, and C.S. in Figure 4.

14. How are the reduced downtime and cost savings calculated?

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The authors address the issue of railway assets management, a subject that is within the wide domain of CMMS - Computerized Maintenance Management System. The paper outlines a methodology, i.e. an architectural model of a system.

Given the heterogeneous data sources of railway equipment and devices, ranging from IOT to sensors to business data bases, authors adopt an ETL (Extraction Transformation Loading) approach by which they normalize data and create a vector of characteristics, including dynamic attributes such as failure frequency. The resulting data warehouse enables the integration of dynamic asset data with business information systems such as the CMMS. The paper is very well structured, with a clear review of critical issues in railways and a well explained literature review, which both make the reader comfortable with the approach and the problem area. Also, the discussions and conclusions are well structured.

Let us address the possible improvements. Figures 1, 2, and 4, are conceptually clear but too small – they should either be divided in two pieces or made vertical. Since the paper focuses the Spanish case and  nit the overall CMMS  issue  in railways, I suggest pointing out that limit in the title. The authors consider failure risk as a function of failure frequency (alias MTBF) and impact, but the interdependence of failures is not considered. Is a factorial analysis of failure interdependence out scope? I think this limit should be declared. Also, there is no discussion of the potential role of AI in forecasting failures and supporting simulation and continuous improvement. I suggest adding some paragraphs on it, in discussion and literature review.  Finally, I would appreciate a report on the actual implementation of the system: how does it work? How long was the project?

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

It is clear that the current version of the manuscript represents a significant improvement in both clarity and methodological rigor based on the extensive revisions.

The revised manuscript has thoroughly considered and incorporated prior suggestions, with enhancements such as a refined keyword selection, restructured introduction for better readability, and clarified research objectives. Key tables and figures have been revised to improve comprehension, including added explanations and standardized terms to address any ambiguities. Specific sections now include detailed methodology clarifications, such as the weight assignment process and the justification for model choice.

Overall, these comprehensive updates have enhanced the manuscript's quality, addressing earlier concerns and providing a clearer, more rigorous presentation of their research.

Back to TopTop