Pose Estimation and Damage Characterization of Turbine Blades during Inspection Cycles and Component-Protective Disassembly Processes
, Richard Blümel 2,*, Lennart Hinz 1, Annika Raatz 2, Markus Kästner 1 and Eduard Reithmeier 1
Round 1
Reviewer 1 Report
Review Comments
Manuscript ID: Sensors-1777857
“Condition assessment and damage characterization of turbine blades during inspection cycles and component-protective disassembly process”
I have reviewed the above mentioned article by Middendorf et al., where the authors have demonstrated bore-scope inspection of turbine blades and have used of computerized programs to assess the severity.
The manuscript is well presented and I am happy to recommend it for publication after a thorough review with respect to the following minor points.
1) In the last paragraph of Section 1, Chapter 3 and Chapter 4 shall be replaced with Section 3 and Section 4, respectively.
2) Before proceeding with the discussion on borescopic inspection, a few other conventional techniques for turbine blades may be briefly mentioned in Section 1, for the sake of completeness, which may be followed by a sentence on the advantages of borescopic inspection under industrial settings.
3) Please consider including a table for abbreviations.
4) Also, it will be useful, if the authors can summarize the various components, along with the manufacturers, in a tabular form. Too many components are mentioned in the text, which becomes confusing.
5) Throughout the text, please change “chapter” to “section”.
6) The conclusion section, at present, summarizes the manuscript. It will be better if it is enriched along with a few details on the lowest sensitivity and accuracy achieved using the automated process.
Author Response
Please see the attachment.
In addition, you will find a PDF in which the revisions are color-coded under this link: https://cloud.imr.uni-hannover.de/s/2o7FLcJNRW9N9jZ
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The paper is well written and includes interesting findings for the engineers. The authors proposed a borescopic 3D sensor based on the fringe projection profilometry. The overall quality of the paper is OK to be accepted in this journal and the below recommendation can enhance its quality.
1. In the introduction of the paper, it's recommended to cite more recent works in the domain of artificial intelligence and deep learning which have a correlation with your work.
Author Response
Please see the attachment.
In addition, you will find a PDF in which the revisions are color-coded under this link: https://cloud.imr.uni-hannover.de/s/2o7FLcJNRW9N9jZ
Author Response File: Author Response.pdf
Reviewer 3 Report
The article present an experimental study on a technique for condition assessment of a turbine blades through borescopic inspection and fringe projection. The article presents also experimental tests with the aim to establish linear elastic limit capacity of the blade root.
The article is generally well written. However, some areas should be improved or commented in more detail before possible publication.
1. In my opinion the proposed title is to general as the main aspect is to present novel technique for an alignment of measured geometry of the turbine blade with the reference computer model.
2. Some aspects of the proposed technique should be described in more detail, such as how denoising was performed (Fig 5).
3. What is the accuracy of the proposed technique? i.e. in Fig. 11c deviation from reference geometry and regenerated blade is shown, it is not 1:1 the same geometry however. What would be deviation if we compare reference and measured geometry of the same blade?
4. Have the authors considered comparing experimentally obtained elastic limit capacity of the blade root with numerical models?
Additionally for the sake of readability some kind of additional designation could be introduced in the workflows (e.g. 1), 2) etc.) and in text which will make easier to follow description of the technique.
Author Response
Please see the attachment.
In addition, you will find a PDF in which the revisions are color-coded under this link: https://cloud.imr.uni-hannover.de/s/2o7FLcJNRW9N9jZ
Author Response File: Author Response.pdf
Round 2
Reviewer 3 Report
The authors improved the paper which can now be considered for publication.
If possible, Figs 6-8 could be additionally corrected as due to 3d projection it appears that there are two different vertical axes which can be misleading.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
