ExtruOnt: An Ontology for describing a type of manufacturing machine for Industry 4.0 systems

This manuscript was submitted as 'Ontology Description' and should be reviewed along the following dimensions: (1) Quality and relevance of the described ontology (convincing evidence must be provided). (2) Illustration, clarity and readability of the describing paper, which shall convey to the reader the key aspects of the described ontology.

This paper is about a proposed ontology called ExtruOnt for the description of extruder, a type of manufacturing machine that performs extrusion process. Five (5) modules are created to describe the various components of an extruder. The proposed ontology is to benefit three (3) different categories of stakeholders, namely: novice workers, product designers and domain experts. Evaluation of the paper is carried out using Oops!, an online ontology pitfall scanner, ontology metrics and domain experts to check for domain coverage and quality of the modelling. Interestingly, the ontology is documented and also publicly accessible online.

The paper is well written and clear to read as I was able to follow through and connect the dots. So to me, the authors have done justice in providing detail descriptions and illustrations for the modules of the proposed ontology and also justified why each module is needed.

What I observed.
For me, I will say from line 21 under related work section should have been under design methodology.

The evaluation errors from the pitfall scanner have been greatly reduced by the authors but there may still be need to eliminate all the errors though they are minor ones. This will make it more presentable and acceptable.

Due to lack of gold standard source for comparison, gold standard evaluation of the proposed ontology was not done, however, I will suggest that the authors should consider doing that in future work to see that the proposed ontology is widely adaptable and reusable.

For some sections, I had to read over and over to clearly understand the content. For instance, line 51 on page 14, section 4.4, was not clear even though the sentence is correct. So I will like to humbly suggest that overall proof reading be done before final submission.
And I believe that the paper can be accepted after.

The main contribution of this paper is ExtruOnt: an ontology designed to represent extruder machines in the manufacturing processes. The ontology is designed to represent specific features associated with the extruder machines, however, authors believe that their approach can be followed to represent a variety of machines in the Industry 4.0 scenarios. ExtruOnt covers all major components of an extruder machine, its features, spatial information, 3D modeling, and sensor-related data. Ontology is designed following the best practices and an extensive evaluation in terms of accuracy, completeness, consistency together with a few other aspects have been conducted.

Paper is very well-written and easy to follow. The proposed work is very aligned with the overall scope of the special issue and can be a good contribution to science. A few concerns/suggestions for the improvement of the work are as follows;

1. The focus of designed ontology is too narrow and representing only a specific type of machine. While the authors claim that the represented ontology can be further extended or adapted to represent a variety of the machines, it is not clear why the authors believe that there is a need to represent a specific ontology for these types of machines. The usual focus on the generic ontologies is to cover a broad range of use cases/equipment rather than very specific machines, for example, the practice followed for SSN/SOSA ontologies design are to cover a broad range of the sensors. Authors must think of either generalizing their work to cover a wide range of machines or give very solid reasons/motivations on the need for this specialize ontology for the extrusion process.

2. The ontology is accessible online, but authors must also consider providing the de-reference-ability of the URIs used in their ontology. Also, I recommend providing detailed documentation of the ontology via a weblink.

3. The examples that are given in the paper (i.e CQ1-CQ5) and their relevant example SPARQL queries appear to be too trivial at times. These kind of queries can be easily answered from information stored in any traditional database. It would be great to highlight the power of semantics, reasoning and RDF models while designing queries and clearly distinguish/demonstrate the added value and advantages of using ontologies and their underlying information models.

4. The presented use case and also the overall area of Industry 4.0 is mostly applied. Additional to the OOPS evaluation, It would be great to see a section in this paper, solely dedicated on the use of ontology in the practical scenarios with some reports on its performance and evaluation over real data and queries.

Overall, I commend authors efforts for this paper and I believe it is a good contribution to the science. While I recommend the paper for acceptance, I hope the authors will consider a few of the above points before preparing their final camera-ready version.