By Nazlı Gülüm Mutlu https://orcid.org/0000-0003-0210-5175

Review Details

---

Reviewer has chosen not to be Anonymous

Summary of paper in a few sentences:

The study presents an unsupervised predictive maintenance analysis that leverages data collected from reciprocating compressor systems and time series data to identify critical behaviors through Renormalization Group (RG) analysis and models their effects on the time series using the Log Periodic Power Law (LPPL) function to predict failures in advance. However, it has been understood that further effort is required in some points. The points open for improvement in the article are summarized below.

Reasons to accept:

The mathematical foundation and adaptation of the analysis framework to the data have been explained sufficiently. They have shown that the proposed method performs well.

Reasons to reject:

In the Introduction section, the problem presented in the study should be referenced more clearly. (page number 1, line numbers 28-44, and page number, line numbers 1-4). For example, 'This would suggest that unsupervised approaches may prove to be a better-suited tool for building PM processes' – according to whom?

What are the characteristics of the data collected through this process? Why are unsupervised approaches suitable for predictive maintenance? Although this is somewhat explained in the Related Works section, it is not sufficiently clear. It should be elaborated further with more examples linked to previous studies.

A citation should be provided (p.2, lines 24-28).

'It is sufficient to determine whether it can be determined whether a given point in the time series is the initial (initiating) moment of IB or not.' A citation should be provided.

However, there is insufficient information on other studies conducting predictive maintenance analysis and the methods used. The need for such a framework has not been adequately discussed based on previous works. For instance, what does the proposed method achieve that the Statistical Process Control method does not? A methodological framework has been presented without sufficiently considering the advantages and disadvantages of existing methods.

Nanopublication comments:

Further comments:

Reviewer has chosen to be Anonymous

Summary of paper in a few sentences:

The paper proposes an unsupervised method for predictive maintenance on industrial systems using an algorithm based on Log Periodic Power Laws (LPPL) that analyzes univariate time series and detects critical points.
The proposed approach was tested using data collected from a reciprocating compressor system to predict and classify failures in advance, as well as determine its root cause.

Reasons to accept:

The paper treats an important problem in the context of maintenance management of industrial systems, proposing an approach that uses an existing methodology with application in another area.
The exhaustive description of the methodology and the results obtained with a specific industrial system show its potential effectiveness.

Reasons to reject:

The novelty, impact and effectiveness of the approach are not clear and the generalization of the methodology for different industrial systems may be limited.
The assumptions considered and the use of a univariate approach do not guarantee that the methodology can be successfully applied to different industrial systems.

Nanopublication comments:

Further comments:

The article can be enhanced, improving the analysis of the state of the art in section 2 and comparing the results obtained with the proposed methodology and with other existing approaches.
To clarify the meaning of failure, a definition of failure should be included, distinguishing failure from fault.
The 1st member of Equation (6) is not correct.
In equation (25), C_1 must be replaced by C.
The text should be verified because there are some typos.
Some sentences needed to be reviewed in terms of writing in English.