Proactive Mission Planning of Unmanned Aerial Vehicle Fleets Used in Offshore Wind Farm Maintenance

Round 1

Reviewer 1 Report

The ideas in this paper are good. However, this article still has some deficiencies as follows:

1. The Introduction and Literatures review also need to be enhanced, especially on UAV or drone application, routing problem and mission planning. These articles may be helpful for improving this paper: the fourth-party logistics routing problem using ant colony system-improved grey wolf optimization, 4PL routing problem using hybrid beetle swarm optimization.

2. The explanation in the legend is missing, and the meaning of all the symbols should be indicated. See figure 2, 5, and so on.

3. The ship cooperates with UAV in this paper, which need a deeper discussion. The process can refer on, research on drones and riders joint take-out delivery routing problem.

4. The simulation results in the experimental part are very good, but there, a summary lacked, such as the comparison between the two programs. How can the model designed in this paper be better with the traditional one?

5. The conclusion needs to be enhanced by adding the purpose and significance of this paper, and give an analysis of the experimental results

6. In section 4.2, the three stages of UAV mission plan does not match the figure

Moderate editing of English language required

Author Response

The authors thank the reviewers for very helpful comments and suggestions. The authors have incorporated the reviewers’ comments in the revised manuscript.

Responses to the reviewers’ comments

Reviewer #1: The ideas in this paper are good. However, this article still has some deficiencies as follows.

Remark 1: The Introduction and Literatures review also need to be enhanced, especially on UAV or drone application, routing problem and mission planning. These articles may be helpful for improving this paper: the fourth-party logistics routing problem using ant colony system-improved grey wolf optimization, 4PL routing problem using hybrid beetle swarm optimization.

 Response: Thank you for your comment. Your suggestions have been included in the following additions introduced to the text on page 4.

Page 4. “The algorithms implemented in these, build on previous experience gained in solving problems arising in a variety of UAV applications. These range from precision farming [26] to disaster management [27] and infrastructure inspection [28], as well as in various fields, including the defense, civilian and commercial sectors.”

[26]Panagiotis Radoglou-Grammatikis, Panagiotis Sarigiannidis, Thomas Lagkas, Ioannis Moscholios, A compilation of UAV applications for precision agriculture, Computer Networks, Volume 172, 2020, 107148, https://doi.org/10.1016/j.comnet.2020.107148.

[27]N. Nikhil, S. M. Shreyas, G. Vyshnavi and S. Yadav, "Unmanned Aerial Vehicles (UAV) in Disaster Management Applications," 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India, 2020, pp. 140-148, doi: 10.1109/ICSSIT48917.2020.9214241.

[28]A. Savva et al., "ICARUS: Automatic Autonomous Power Infrastructure Inspection with UAVs," 2021 International Conference on Unmanned Aircraft Systems (ICUAS), Athens, Greece, 2021, pp. 918-926, doi: 10.1109/ICUAS51884.2021.9476742.

Page 4. “(using, e.g., population algorithms such as ant colony [29], beetle swarm [30], system-improved grey wolf optimization [31] etc. as well as fuzzy logic algorithms such as fuzzy reinforcement learning [32], fuzzy particle swarm optimization [33], [34],  fuzzy C-means [35], etc. and so on).”

[29]Fuqiang Lu, Wenjing Feng, Mengying Gao, Hualing Bi, Suxin Wang, Corrigendum to The Fourth-Party Logistics Routing Problem Using Ant Colony System-Improved Grey Wolf Optimization, Journal of Advanced Transportation, vol. 2022, Article ID 9864064, 17 pages, 2022. https://doi.org/10.1155/2022/9864064

[30]Jian Ni, Jing Tang and Rui Wang, Hybrid Algorithm of Improved Beetle Antenna Search and Artificial Fish Swarm, Appl. Sci. 2022, 12(24), 13044; https://doi.org/10.3390/app122413044

[31]Hou, Y.; Gao, H.; Wang, Z.; Du, C. Improved Grey Wolf Optimization Algorithm and Application. Sensors 2022, 22, 3810. https://doi.org/10.3390/s22103810

[32]Zheng Hao, Haowei Zhang andYipu Zhang, Stock Portfolio Management by Using Fuzzy Ensemble Deep Reinforcement Learning Algorithm,  J. Risk Financial Manag. 2023, 16(3), 201; https://doi.org/10.3390/jrfm16030201

[33]Praseeda, C.K., Shivakumar, B.L. Fuzzy particle swarm optimization (FPSO) based feature selection and hybrid kernel distance based possibilistic fuzzy local information C-means (HKD-PFLICM) clustering for churn prediction in telecom industry. SN Appl. Sci. 3, 613 (2021). https://doi.org/10.1007/s42452-021-04576-7

[34]Tian, Dongping & Li, Nai-qian. (2009). Fuzzy Particle Swarm Optimization Algorithm. IJCAI International Joint Conference on Artificial Intelligence. 263-267. 10.1109/JCAI.2009.50.

[35]Salar Askari, Fuzzy C-Means clustering algorithm for data with unequal cluster sizes and contaminated with noise and outliers: Review and development, Expert Systems with Applications, Volume 165, 2021, 113856, https://doi.org/10.1016/j.eswa.2020.113856.

 Remark 2: The explanation in the legend is missing, and the meaning of all the symbols should be indicated. See figure 2, 5, and so on.?

 Response: Thank you for your comment. The legends relating to figures have been completed.

Remark 3: The ship cooperates with UAV in this paper, which need a deeper discussion. The process can refer on, research on drones and riders joint take-out delivery routing problem.

Response: Thank you for your comment. The following paragraph has been added to the section "Related works" (section 2).

Page 3. “The considered problem, of planning service missions involving the routing/scheduling of a vessel transporting service groups and UAVs delivering spare parts to serviced WTs, is a special case of Ground-Vehicle and Unmanned-Aerial-Vehicle routing problems GV-UAV [20], assuming that the base of the UAVs is an object moving on land. In literature, there are numerous contributions dealing with this subject [21]-[25]. However, they do not address the issues of planning missions in the maritime environment, where weather conditions are of great importance for the implementation of the mission. In this perspective, the proposed declarative model for planning WTs service missions fills the gap in research on the use of UAVs in the maritime environment.”

[20]Hongqi Li, Jun Chen, Feilong Wang, Ming Bai, Ground-vehicle and unmanned-aerial-vehicle routing problems from two-echelon scheme perspective: A review, European Journal of Operational Research, Volume 294, Issue 3, 2021,1078-1095, https://doi.org/10.1016/j.ejor.2021.02.022.

[21]Boysen, N., Briskorn, D. , Fedtke, S. , & Schwerdfeger, S. (2018b). Drone delivery from trucks: Drone scheduling for given truck routes. Networks, 72 (4), 506–527 .

[22]Campbell, J. F. , Sweeney, D. , & Zhang, J. (2017). Strategic design for delivery with trucks and drones. Supply Chain Analytics Report SCMA 04 2017 .

[23]Chang, Y. S. , & Lee, H. J. (2018). Optimal delivery routing with wider drone-delivery areas along a shorter truck-route. Expert Systems with Applications, 104 , 307–317

[24]Das, D. N., Sewani, R., Wang, J., & Tiwari, M. K. (2020). Synchronized truck and drone routing in package delivery logistics. IEEE Transactions on Intelligent Transportation Systems . https://doi.org/10.1109/TITS.2020.2992549

[25] Bocewicz G., Nielsen P., Banaszak Z., Thibbotuwawa A. A Declarative Modelling Framework for Routing of Multiple UAVs in a System with Mobile Battery Swapping Stations Intelligent Systems in Production Engineering and Maintenance, A. Burduk, E. Chlebus, (Eds) ISPEM 2018, AISC 835, Springer Nature Switzerland AG 2019, 2019, 429-441, doi: 10.1007/978-3-319-97490-3_42

Remark 4: The simulation results in the experimental part are very good, but there, a summary lacked, such as the comparison between the two programs. How can the model designed in this paper be better with the traditional one?.

 Response: Thank you for your comment. The following paragraph has been added to Section 4.

Page 20. The conducted experiments show that the developed model can be used in the process of planning one-day service missions online (mission planning time < 10 min, mission execution time up to 8 h). In all experiments it was assumed that only one transport vessel is used - which corresponds to situations encountered in practice. This does not mean, however, that in future research it will not be possible to consider more complex situations in which the delivery and collection of service teams is carried out by a fleet of ships. The proposed reference model makes it possible to plan the service in such situations, however, ensuring the possibility of making decisions online requires the development of a new, more computationally efficient method for assessing acceptable scenarios.

It once again is worth emphasizing that the greatest advantage of the developed model is its open structure. This allows for taking into account additional constraints, that describe the individual characteristics of the considered WT. The use of the concept of declarative programming means that taking into account additional constraints does not affect the time to obtain solutions. This is especially important for practical applications that are characterized by a large variety.

Remark 5: The conclusion needs to be enhanced by adding the purpose and significance of this paper, and give an analysis of the experimental results

 Response: Thank you for your comment. The Conclusions section (see page 20) has been supplemented with the following paragraph.

Page 20. “ With these assumptions, the famous goal of the research was to develop a reference model enabling the implementation of methods of computer-aided online service mission planning for problems of a scale encountered in practice (i.e., 6-8 WTs serviced during the day). The solutions known so far, are mostly limited to land conditions and do not take into account the impact of the environment, in particular sea state and weather, on the feasibility of missions. The declarative nature of the model allows its implementation in commercially available constraint programming environments, e.g, ILOG, ECLiPSe, Gurobi.

The results of the conducted experiments confirm the possibility of using the developed approach in situations where the number of serviced WTs , and number of service groups .”

 

All new elements have been highlighted in yellow (see corrected paper version).

Once again, thank you very much for your considered comments.

Yours sincerely,

Banaszak Z., Radzki G., Nielsen I., Frederiksen R. and Bocewicz G.

 

Author Response File: Author Response.pdf

Reviewer 2 Report

Overall, a nicely written paper. However, I had one fundamental doubt. It is not clear why the UAVs would be used for the delivery of repair equipment. As mentioned, the payload capacity of the UAV is 12 kg. With onboard sensors such as ultrasonic, visual, thermographic, and hyperspectral cameras, there is probably not much equipment carrying capacity left.

Perhaps, the operations need to be reassessed. How about planning an initial UAV inspection operation, where it detects faults by inspecting each wind turbine?  Subsequently, a vessel loaded with the required equipment and personnel sets off from the port with an optimal sequence of turbine repairs. The UAV could be onboard as well, to validate towards the end that the repair work has been completed satisfactorily.  

English looks fine overall, please proofread carefully for any typographical or grammatical errors. 

Author Response

The authors thank the reviewers for very helpful comments and suggestions. The authors have incorporated the reviewers’ comments in the revised manuscript.

Responses to the reviewers’ comments

Reviewer #2:

Remark 1: Overall, a nicely written paper. However, I had one fundamental doubt. It is not clear why the UAVs would be used for the delivery of repair equipment. As mentioned, the payload capacity of the UAV is 12 kg. With onboard sensors such as ultrasonic, visual, thermographic, and hyperspectral cameras, there is probably not much equipment carrying capacity left.

Perhaps, the operations need to be reassessed. How about planning an initial UAV inspection operation, where it detects faults by inspecting each wind turbine?  Subsequently, a vessel loaded with the required equipment and personnel sets off from the port with an optimal sequence of turbine repairs. The UAV could be onboard as well, to validate towards the end that the repair work has been completed satisfactorily.

Response: Thank you for your comment. You are right. Instead of the payload capacity of the UAV of 12 kg given in the text, it should be 120 kg. The class of drones considered in this type of operation includes UAVs with a lifting capacity of up to 200kg.

In the planned mission scenarios, it is assumed that the service teams delivered to the WTs identify the defects noticed there and, depending on their scale, place orders for appropriate spare parts supplemented with UAVs.

 All new elements have been highlighted in yellow (see corrected paper version).

Once again, thank you very much for your considered comments.

Yours sincerely,

Banaszak Z., Radzki G., Nielsen I., Frederiksen R. and Bocewicz G.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

All the questions have been addressed. I recommend the acceptance of the paper.

Minor editing of English language required