Reviewer: Extensive editing of English language and style required
Answer: English of this article was corrected by Native English carrier (USA)
in the process of preparing to NATO conference.
Reviewer: I think that the paper is very general
Answer: It is a new CONCEPT of DECS.
Reviewer: the paper does not clearly explain what is meant by DECS system, what
types of engines are incorporated, what is meant by an engine.
Answer: this paper was oriented to real professionals working in the area
DECS that know what is meant by DECS system. The topic of article included
information regarding types of engines. It will be engines of future air
Reviewer: Some terms are very strange like firefighting network.
Answer: firefighting network it is the network for firefighting or fire
Reviewer: It is not quite clear on what types of engines does the paper aim as it
cannot be aimed at all engines at once (there very big differences between land,
aircraft, naval engines, requirements and so on).
Answer: The structure and principle of proposed DECS are independent on
types of engines and will be the same for land, aircraft, naval engines etc. It is
the principal position of author. The different will be only on the level of
sensors adapters and effectors (actuators).
Reviewer: Distributed engine control system is not defined nor does the paper
define what are its advantages and how is it related for example to full authority
digital engine control systems and how it can be implemented for different vehicles
(air, ground, naval, unmanned, etc.) as each of the domains is very specific and
requires a specific approach.
Answer: The general definition of DECS is known from previous publications.
On the other hand, the text of my article said:” The distributed engine control
system (DECS) of future air vehicle should be built on the base of networking
principle as the part of an integrated, hierarchical, multidimensional and
multiple networks system on the air vehicle board”. The paper defined what
is its advantages and how is it related for example to full authority digital
engine control systems and how it can be implemented for different vehicles
(air, ground, naval, unmanned, etc.). Regarding implementation proposed
architecture, SOSA equipment, fiber optics communication, AI and AR
technologies. For all domains (air, ground, naval, unmanned, etc.) should be
used the same architecture of DECS.
Reviewer: The article is mixing neural networks, predictive maintenance and
augmented reality and the parts are not clearly interconnected, nor they are
logically bound with a certain scientific aim
Answer: neural networks, predictive maintenance and augmented reality are
parts of proposed DECS concept.
Reviewer: Advanced approach to description of Neural Network model is a
chapter, which is absolutely not clear to me as a specialist in the area of artificial
intelligence. Neural networks are very well formalized and explored, it is not clear
how and why is this chapter connected to distributed engine control systems.
Formalization and modeling of neural networks should be in my opinion a special
paper for a journal dealing with neural networks.
Answer: I do not agree that neural networks are very well formalized and
studied. This science will develop for a long time. The proof of this point of
view is my tensor-matrix theory of Artificial Intelligence and Neural networks
that very important for Edge computing inside DECS. Any DECS without
neural networks would be archaic and ineffective.
Reviewer: It is not clear how the augmented reality systems would help with
control tasks in engine systems (how would augmented reality help with fuel flow
control, aggregates control, etc.?). Augmented reality can of course be beneficial in
maintenance or predictive maintenance, but that would again in my opinion require
a standalone paper dealing with these issues.
Answer: Augmented Reality is the communication bridge and feedback
mechanism from AI to a Human (pilot, engineer etc.) for the support of
decisions making. Augmented Reality help with fuel flow control, aggregates
Reviewer: the paper is very general and does not contain any quantifiable results, it
does not contain any new scientific methodologies or contributions that can be
Answer: New ideas:
To collect Big Data from sensors and the pre-processing of this data before a
machine learning (ML) procedure it is proposed to form data sets with the
help of the face-splitting matrix product.
To decrease the time of reaction of Neural Networks it has been suggested the
implementation of advanced tensor-matrix theory on the basis of penetrating
face product of matrices.
Other important results of the paper are a possible version of the AR data
format for DECS and a proposal about the use of non-orthogonal frequency
discrete multiplexing (N-OFDM) signals to data transfer via fibre optics.