Науковий вісник НГУ

Improvement of the method for optimization of predicting the efficiency of a robotic platform

• 
• 

User Rating:  / 0

PoorBest 

Details

Category: Content №3 2024

Last Updated on 28 June 2024

Published on 30 November -0001

Hits: 70

Authors:

O.Laktionov*, orcid.org/0000-0002-5230-524X, National University “Yuri Kondratyuk Poltava Polytechnic”, Poltava, Ukraine, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

I.Laktionova, orcid.org/0009-0005-6340-8761, National University “Yuri Kondratyuk Poltava Polytechnic”, Poltava, Ukraine, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

* Corresponding author e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

повний текст / full article

Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu. 2024, (3): 135 - 141

https://doi.org/10.33271/nvngu/2024-3/135

Abstract:

Purpose. Improving the optimization method for predicting the efficiency of a robotic platform (using the gradient boosting method as an example).

Methodology. The process of refining the optimization method for predicting efficiency has been investigated using robotic platforms as complex systems comprising hardware components, data exchange technology, security systems, and navigation, along with user interaction methods. The optimization method relies on a linear equation, whose mathematical model, through the triple interaction of factors, consolidates assessments of subsystem elements into an efficiency index for the robotic platform. The outcomes of the proposed optimization algorithm result in regression models from machine learning. These acquired models are employed for predicting the efficiency of a specific configuration of a robotic platform designed to perform particular practical tasks.

Findings. The optimization method for predicting the efficiency of a robotic platform has been enhanced by utilizing evaluations of the robotic platform efficiency index as input data. In comparison to existing methods, the proposed index demonstrates minimal values of root mean square deviation at 0.1794, 0.14 and 0.1245, respectively. This particular characteristic has enabled the development of a more accurate optimization method for predicting the efficiency of robotic platforms. This assertion is supported both theoretically and empirically through criteria such as Root Mean Square Error, Mean Absolute Error, and Maximum Absolute Error on experimental datasets.

Originality. The optimization method for predicting the efficiency of a robotic platform differs from existing approaches through its model-building process, which consists of two iterations and incorporates different sets of input evaluations. The first iteration involves primary and index-based evaluations of the robotic platform’s efficiency, while the second iteration incorporates primary, index-based evaluations, and predicted index-based evaluations.

Practical value. Selection of the optimal configuration of a robotic platform for addressing tasks in the energy sector. Cost reduction through a finely tuned combination of robotic platforms. The proposed solutions will contribute to the Development Concept of Artificial Intelligence in Ukraine.

Keywords: robotic platform, linear equation, dual interaction, triple interaction, efficiency index, optimization method

References.

1. Zhou, T., Wang, Y., Zhu, Q., & Du, J. (2022). Human hand motion prediction based on feature grouping and deep learning: Pipe skid maintenance example. Automation in Construction, 138, 104232. https://doi.org/10.1016/j.autcon.2022.104232.

2. Yang, F., & Hein, J. E. (2023). Training a robotic arm to estimate the weight of a suspended object. Device, 100011. https://doi.org/10.1016/j.device.2023.100011.

3. Chen, H., & Cheng, H. (2021). Online performance optimization for complex robotic assembly processes. Journal of Manufacturing Processes, 72, 544-552. https://doi.org/10.1016/j.jmapro.2021.10.047.

4. Zafar, M. N., & Mohanta, J. C. (2018). Methodology for Path Planning and Optimization of Mobile Robots: A Review. Procedia Computer Science, 133, 141-152. https://doi.org/10.1016/j.procs.2018.07.018.

5. Hong, W.-C., Li, M.-W., Geng, J., & Zhang, Y. (2019). Novel chaotic bat algorithm for forecasting complex motion of floating platforms. Applied Mathematical Modelling, 72, 425-443. https://doi.org/10.1016/j.apm.2019.03.031.

6. Binchi, J., Mangeruca, L., Rucco, M., Ferrante, O., Minissale, A., & Abbà, F. F. (2021). Online Prediction for Safe Human-Robot Collaboration: A Model of the Human Arm. Procedia CIRP, 97, 533-538. https://doi.org/10.1016/j.procir.2022.05.204.

7. Seker, M. Y., Tekden, A. E., & Ugur, E. (2019). Deep effect trajectory prediction in robot manipulation. Robotics and Autonomous Systems, 119, 173-184. https://doi.org/10.1016/j.robot.2019.07.003.

8. Ye, C., Yang, J., & Ding, H. (2022). High-accuracy prediction and compensation of industrial robot stiffness deformation. International Journal of Mechanical Sciences, 233, 107638. https://doi.org/10.1016/j.ijmecsci.2022.107638.

9. Gitardi, D., Sabbadini, S., & Valente, A. (2022). UMA Universal Maintenance Automata – an adaptable robotic platform designed to run maintenance operations in harsh environment. Procedia CIRP, 107, 1473-1478. https://doi.org/10.1016/j.procir.2022.05.177.

10. Tkáčik, M., Březina, A., & Jadlovská, S. (2019b). Design of a Prototype for a Modular Mobile Robotic Platform. IFAC-PapersOnLine, 52(27), 192-197. https://doi.org/10.1016/j.ifacol.2019.12.755.

11. Ahmadianfar, I., Heidari, A. A., Gandomi, A. H., Chu, X., & Chen, H. (2021). RUN beyond the metaphor: An efficient optimization algorithm based on Runge Kutta method. Expert Systems with Applications, 181, 115079. https://doi.org/10.1016/j.eswa.2021.115079.

12. Onyshchenko, S., Yanko, A., & Hlushko, A. (2023). Improving the efficiency of diagnosing errors in computer devices for processing economic data functioning in the class of residuals. Eastern-European Journal of Enterprise Technologies, 5(4(125)), 63-73. https://doi.org/10.15587/1729-4061.2023.289185.

13. Laktionov, A. (2021). Improving the methods for determining the index of quality of subsystem element interaction. Eastern-European Journal of Enterprise Technologies, 6(3(114)), 72-82. https://doi.org/10.15587/1729-4061.2021.244929.

14. Korets^,ka, I., & Zinchenko, T. (2018). Evaluation of research samples by nonlinear quality criteria. Vsesvitnya nauka u 2018 rotsi, 22-26.

• < Prev
• Next >