Hybrid Turbo-Shaft Engine Digital Twinning for Autonomous Aircraft via AI and Synthetic Data Generation

Round 1

Reviewer 1 Report

The article provides an interesting perspective on using Digital Twins (DT) and synthetic data generation for developing autonomous aircraft and urban services. However, there are a few critical comments to consider:

1. The article mentions that autonomous aircraft are key enablers of future urban services, but it does not provide a comprehensive explanation or contextualization of this statement. It would be helpful to elaborate on the specific applications and benefits of autonomous aircraft in urban environments.

2. While the article introduces Digital Twins (DT) as a promising technology for transforming the transport ecosystem, it lacks a detailed discussion on the concept of DT and its significance. Additionally, the article briefly mentions the importance of data management for implementing DT as a Service (DTaaS). Still, it fails to delve deeper into the challenges and considerations associated with this aspect.

3. The article acknowledges the challenge of data availability for training algorithms and verifying the functionality of DT. However, it does not explore potential solutions or alternative approaches to address this issue. Providing insights into strategies for acquiring real-life data or discussing potential collaborations with industry stakeholders would enhance the article's practicality.

4. The article primarily uses synthetic data generation for Hybrid turbo-shaft engines in drones/helicopters. While this specific focus allows for a detailed analysis, it restricts the generalizability of the findings. Including a broader discussion on the applicability of synthetic data generation in the UAV domain or addressing potential limitations would strengthen the article's impact.

5. The article mentions that the corresponding DT model shows high efficiency in noise filtration and predicts engine parameters with a lower error rate, except for engine torque. However, it does not provide a comparative analysis of existing methods or approaches. A comparative evaluation would enable readers to understand the relative strengths and weaknesses of the proposed approach.

6. Given the critical role of autonomous aircraft in urban environments, addressing ethical and safety implications is essential. The article does not touch upon potential concerns, such as privacy, security, or the impact of autonomous systems on society. Discussing these aspects would contribute to a more comprehensive analysis.

All the best

Minor editing of the English language required

Author Response

Title: Hybrid Turbo-shaft Engine Digital Twining for Autonomous Air-crafts via AI and Synthetic Data Generation

Manuscript number: aerospace-2455029

Revision Version: 1

 

Dear Editor,

 

We appreciate you and the reviewers for your precious time in reviewing our paper and providing valuable comments. It was your valuable and insightful comments that led to possible improvements in the current version.

 

Since the comments were all fine and constructive points, the authors have carefully considered all comments and tried our best to address every one of them. We hope the manuscript after careful revisions meets your high standards.

 

Below we provide the point-by-point responses. All modifications in the manuscript have

been highlighted in red.

 

 

Author's Responses

Reviewer 1

Reviewer Comments:

The article provides an interesting perspective on using Digital Twins (DT) and synthetic data generation for developing autonomous aircraft and urban services. However, there are a few critical comments to consider:

Behalf of the authors team: Thank you very much for the fine and constructive points. We have accordingly revised the manuscript regarding the following points.

1. The article mentions that autonomous aircraft are key enablers of future urban services, but it does not provide a comprehensive explanation or contextualization of this statement. It would be helpful to elaborate on the specific applications and benefits of autonomous aircraft in urban environments.

Author Response: Thank you for the nice reminder. We have added the following monograph to the literature review to address the comment.

A recent systematic review by Butila et al 2022 shows UAVs play a vital role in shaping the future of urban services [1]. They offer numerous benefits to urban environments, such as transforming transportation and delivery services by circumventing congestion [1]. Moreover, drones contribute to emergency response, infrastructure inspection, and urban surveillance, thereby enhancing safety and efficiency [2][3][4]. With the advancement of regulations and technology, autonomous aircraft will further unlock their potential, leading to improved efficiency and safety in urban areas [1][2].

On the other side, UAVs can play a crucial role in further advancing the future of urban transportation. UAM vehicles, including electric vertical takeoff and landing (eVTOL) aircraft, share similarities with UAVs in terms of autonomous flight, electric propulsion, and advanced sensing and navigation systems [5]. Background literature from UAV operations studies, such as autonomous flight control algorithms, obstacle detection and avoidance systems, and communication protocols, can be used to improve the safety, efficiency, and reliability of UAM vehicles [6]. Therefore, UAV technology research and development efforts play a key role in forming the foundation for the successful implementation of UAM systems, bringing us closer to a future where air transportation is seamlessly integrated into urban environments.

2. While the article introduces Digital Twins (DT) as a promising technology for transforming the transport ecosystem, it lacks a detailed discussion on the concept of DT and its significance. Additionally, the article briefly mentions the importance of data management for implementing DT as a Service (DTaaS). Still, it fails to delve deeper into the challenges and considerations associated with this aspect.

Author Response: Thank you very much for pointing this out. This is the first phase of a bigger research project. Therefore, as we already mentioned in the introduction and last section of the background review, to create a DT first we need to train the ML algorithms and then in the implementation phase we probe the challenges of bringing DTaaS into action. So the first step is generating real-life similar data. To some, this is the first challenge that without surpassing, it is impossible to speak about other challenges; and we clearly mentioned it in the gap that we found in the background review.

On the other side, the next step is studying the different noise generation algorithms on the final results, and after that, elaborating on the practical challenges in real-life cases is the project's third phase. Therefore, we added this monograph to the manuscript:

 

3. The article acknowledges the challenge of data availability for training algorithms and verifying the functionality of DT. However, it does not explore potential solutions or alternative approaches to address this issue. Providing insights into strategies for acquiring real-life data or discussing potential collaborations with industry stakeholders would enhance the article's practicality.

Author Response: The comment is absolutely fine, but the reviewer missed a piece of important information. Regrettably, there is no openly accessible data for Hybrid-turbo shaft engines in this domain, mainly due to its status as a cutting-edge technology in the realm of UAM (Urban Air Mobility). Companies involved in this field prefer to maintain confidentiality regarding their data because of the competitive engineering market. Despite our attempts to reach out to authors of previously published and highly referenced articles, who claimed to have conducted experiments on a real-life test-bench, they declined to provide any experimental data. In our introduction, we have already acknowledged the absence of data and the challenges encountered in collaborating with private technology owners.

4. The article primarily uses synthetic data generation for Hybrid turbo-shaft engines in drones/helicopters. While this specific focus allows for a detailed analysis, it restricts the generalizability of the findings. Including a broader discussion on the applicability of synthetic data generation in the UAV domain or addressing potential limitations would strengthen the article's impact.

Author Response: thank you for reminder. We revised abstract, discussion, and conclusion sections to emphasize the fact that the process is reusable in other contexts, and we mentioned the main limits.

The unavailability of costly infrastructures, such as wind tunnels or physical entities, poses a significant challenge in academia. In this regard, data generation plays a crucial role in assisting academics with their research. In the case of UAVs, data generation allows researchers and developers to simulate and create synthetic data to train and test algorithms[7], improving the performance of autonomous flight systems, collision avoidance mechanisms[8], and object detection algorithms[9]. By generating diverse data scenarios, such as different weather conditions, terrains, and obstacle configurations, engineers can evaluate the robustness and effectiveness of their UAV systems in a controlled and scalable environment[8]. This approach assists engineers in assessing the behavior and performance of designs without the need for physical prototyping or costly experiments, saving time and resources while facilitating iterative design improvements. Overall, data generation plays a vital role in enabling effective development, testing, and optimization of UAVs and engineering systems when real data is scarce or inaccessible.[7][8][9] Therefore Data generation techniques can be used in different contexts considering an efficient PCA to find the most efficient parameters of the problem under study.

5. The article mentions that the corresponding DT model shows high efficiency in noise filtration and predicts engine parameters with a lower error rate, except for engine torque. However, it does not provide a comparative analysis of existing methods or approaches. A comparative evaluation would enable readers to understand the relative strengths and weaknesses of the proposed approach.

Author Response: Unfortunately we are in cutting-edge and there is no alternative approach in this domain yet. However, as we mentioned in response to comment 2, we are probing the effect of various noise generation algorithms on the results. To address these comments we underlined the future research lines to probe an alternative approach.

6. Given the critical role of autonomous aircraft in urban environments, addressing ethical and safety implications is essential. The article does not touch upon potential concerns, such as privacy, security, or the impact of autonomous systems on society. Discussing these aspects would contribute to a more comprehensive analysis.

Author Response: Thank you very much for pointing this out. We added a monograph to the introduction to address this comment.

The rapid development and integration of autonomous systems, including autonomous aircraft, in urban environments raise significant ethical, safety, and social concerns. The collection and processing of large amounts of data by autonomous systems have made privacy-related concerns that potentially violate people's privacy rights [10]. Security is also an important aspect, as autonomous systems are vulnerable to cyber-attacks and unauthorized access and require strong security measures to protect against potential threats [11]. In addition, the social impacts of autonomous systems, including unemployment and economic impacts, require careful consideration to ensure equitable distribution of benefits and mitigation of adverse impacts [12]. Addressing these ethics, privacy, security, and social implications is critical to supporting the responsible development and deployment of autonomous aircraft in urban environments.

Author Response File: Author Response.pdf

Reviewer 2 Report

Please review the highlighted notes in the attached document.

Comments for author File: Comments.pdf

Author Response

Title: Hybrid Turbo-shaft Engine Digital Twining for Autonomous Air-crafts via AI and Synthetic Data Generation

Manuscript number: aerospace-2455029

Revision Version: 1

 

Dear Editor,

 

We appreciate you and the reviewers for your precious time in reviewing our paper and providing valuable comments. It was your valuable and insightful comments that led to possible improvements in the current version.

 

Since the comments were all fine and constructive points, the authors have carefully considered all comments and tried our best to address every one of them. We hope the manuscript after careful revisions meets your high standards.

 

Below we provide the point-by-point responses. All modifications in the manuscript have

been highlighted in red.

 

 

Author's Responses

Reviewer 2

Reviewer Comments:

Please review the highlighted notes in the attached document.

Behalf of the authors team:: Thank you for raising all of the important points in the pdf file. We agree with these comments and improve the manuscript according to your valuable comments.

1. Text should be in black along the document.

Author Response: Thank you for the comment; the manuscript is modified.

2. Write: Where the explanation of each parameter is shown in Table 2. or any other similar wording. (line 177 )

Author Response: Thank you for the comment; the manuscript is modified

3. rewrite: in this study (or) in this process (line 214)

Author Response: Thank you for the comment; the manuscript is modified

4. add a table or a list defining all parameters mentioned here(eq12-13) and not described yet in your paper

Author Response: Thank you for the comment; the manuscript is modified

5. in your results section you need to shoow the data (or part of it) before adding and after adding the noise then you show the model analysis results from processing this data.

Author Response: Thank you for the comment; the result section is modified (please check response to comment no. 7)

6. add units to the y-axis title (Figure. 8)

Author Response: Thank you for the comment; The figure is modified.

y-axis signal is not clear. Explain it in the previous paragraph and explain the point you are trying to support with this chart.

Author Response: Thank you for the comment. The manuscript is slightly modified.

7. Not an accurate statement; The results section included only one paragraph which is just the titles of the included graphs. More explanatioon and walk throug of your approach and its effect on data need to be clearly discussed in the results. (Line 231)

 

Author Response: Thank you for the fin point. We extended the results section with the following paragraphs to fulfill the current constructive comment.

In this section, we present the results of the proposed method and provide a more detailed explanation of our approach and its effects on the data. As mentioned in the Methodology section, we configured the take-off condition and added noise to the data. Fig.7 illustrates the generation of noise on the shaft speed. It is important to note that the added noise followed the patterns of the original data. This means that the noise was not random or unrelated to the underlying data patterns. By aligning the noise with the data patterns, we ensured that it did not introduce any disruptive or misleading elements to the analysis

Furthermore, the analysis revealed that there were no outliers present in the dataset. Outliers are data points that deviate significantly from the overall pattern of the data. The absence of outliers indicates that the data was relatively consistent and reliable, allowing us to focus on the effects of the proposed methodology without any major aberrations.

Following the the addition of the noise, we applied the Linear Regression and the Kalman Filter algorithm. Fig.8 serves as an example, showcasing the results of rolling linear regression applied to the shaft speed data. In the figure, the blue line represents the referenced shaft speed (the original data), while the orange line represents the result of rolling linear regression (the prediction). Notably, Fig.8 demonstrates that our predictions exhibit accuracy even in the presence of noise, indicating the effectiveness of our approach.

Furthermore, in the subsequent section, we will discuss the performance of the DT model. The results reveal that the combined algorithms perform effectively across the majority of the parameters. Specifically, the results indicate that the combined algorithms yield a significantly lower mean squared error/mean value index. This demonstrates the improved performance achieved through the utilization of our proposed methodology.

8. Assuming that no real-life machine exists with the proposed design. A 3D design with simulated results can be used and compared with your model. Another approach is to use a none hybrid (regular) vertical lifting machine data and embed in your analysis as needed. (line 265)

Author Response: Thank you for your comment. In fact, the current article already utilizes a Matlab-based simulation model as the primary dataset for generating synthetic data. Therefore, the same physical rules employed by 3D modeling software such as CATIA, ANSYS, FLUENT, Nastran and Patran, SolidWorks, and cosmos motion library, etc., for generating dynamic simulations based on FEA, FDA, or CFD modeling, are already applied in this article. As there is no need to visualize the machine, 3D visualization is not required.

However, the suggestion of employing non-hybrid vertical lifting machine data can be an excellent approach, and we will certainly consider it for the next phase of the study. Consequently, we have included it in the future study section.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Accept