Mechatronic Device Control by Artificial Intelligence
Abstract
:1. Introduction
2. Materials and Methods
- Designing and building a mechatronic device with a parallel kinematic structure.
- Obtaining enough values to control the motors using inverse kinematics (CREO).
- Building a structure where a millimeter graph paper was placed on which the motions of the device could be studied.
- Writing the necessary programs.
- Processing the results.
2.1. Agile Eye
2.2. Neural Network Model
3. Results
3.1. Agile Eye Design
- Servomotor cooling;
- Effector designed so that it can be used to mount both camera and laser;
- Created T-slots for precise attachment of the second device, in the case of stereo imaging testing;
- Mounting holes that allow mounting of the device to the wall.
3.1.1. Main Components of Construction
3.1.2. Electric Components
- 3× MG996R Servo (RPishop.cz, Roudné, Czech Republic, the device was purchased through their eshop)—servo motors which are used to create torque on the device hoop and then move the effector;
- 1× RaspberryPi 4B (RPishop.cz, Roudné, Czech Republic, the device was purchased through their eshop)—the control unit in which the scripts were created to control this mechanism, including training the neural networks;
- 1× Servo Driver—a device that allows control of up to 16 servo motors.
3.2. Kinematics
- ψ = 20 deg;
- θ = 20 deg;
- ϕ = 40 deg.
3.2.1. Creo Parametric
3.2.2. Simscape Multibody Model
3.3. Collection of Data from Created Device Movements
3.3.1. Tracker
3.3.2. Calculation of Achieved Points
3.4. Using Prediction for Motor Control
3.4.1. Processing the Results by Moving along the Circle R20
3.4.2. Processing the Results by Moving along the Circle R10
3.4.3. Processing the Results by Moving on the Line X30
3.4.4. Processing the Results by Moving on the Y50 Line
3.4.5. Processing the Results by Moving on the Line X10Y30
3.4.6. Fourier Transform
4. Discussions
5. Conclusions
References
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Appendix A
Circle R20 | xcenter [mm] | ycenter [mm] | Dimension of the Annular Area [mm] | Radius Inner [mm] | Radius Outer [mm] |
---|---|---|---|---|---|
CREO | 1.4529 | 0.45085 | 5.221 | 13.827 | 19.0481 |
Prediction | 2.584 | 0.64836 | 11.7513 | 9.2923 | 21.0436 |
Calibration according to the mean circle | 0.61807 | −0.38082 | 9.6603 | 15.0923 | 24.7526 |
Calibration according to the average point curve | −3.9477 | −5.135 | 14.2048 | 10.9642 | 25.169 |
Circle R10 | xcenter [mm] | ycenter [mm] | Dimension of the Annular Area [mm] | Radius Inner [mm] | Radius Outer [mm] |
---|---|---|---|---|---|
CREO | 0.52421 | −0.57734 | 7.5812 | 2.2057 | 9.7869 |
Prediction | −0.45999 | 0.19545 | 6.6117 | 3.3813 | 9.9929 |
Calibration according to the mean circle | 0.71054 | −1.3825 | 7.623 | 4.9045 | 12.5276 |
Line X30 | Mean A [X;Y] | Circle A [X;Y] | Circle Radius [A;B] | Mean B [X;Y] | Circle B [X;Y] |
---|---|---|---|---|---|
CREO | −22.6290; −0.7716 | −22.8759; −0.9357 | 1.8368; 3.1305 | 17.7390; −1.6877 | 17.9179; −1.5837 |
Prediction | −24.9526; 1.1181 | −22.7572; 0.1707 | 3.3431; 0.9870 | 18.8197; −2.1449 | 18.9206; −1.6785 |
Calibration according to the mean circle | −30.3119; 4.6014 | −29.8509; 5.7452 | 1.96; 2.4627 | 25.2273; 5.2472 | 24.0485; 4.8840 |
Line Y50 | Mean A [X;Y] | Circle A [X;Y] | Circle Radius [A;B] | Mean B [X;Y] | Circle B [X;Y] |
---|---|---|---|---|---|
CREO | −47.2469; −1.0282 | −49.2846; −4.6818 | 5.9688; 1.4017 | 42.4793; 0.1806 | 42.1856; 0.3747 |
Prediction | −47.9879; −1.6494 | −47.9684; −1.5761 | 0.8949; 1.0737 | 42.8011; 0.5451 | 42.5573; 0.9177 |
Line X10Y30 | Mean A [X;Y] | Circle A [X;Y] | Circle Radius [A;B] | Mean B [X;Y] | Circle B [X;Y] |
---|---|---|---|---|---|
CREO | −7.1995; 21.8294 | −7.1865; 21.8432 | 0.3023; 0.6011 | 5.5410; −19.5651 | 5.6359; −19.4667 |
Prediction | −6.4536; 19.7469 | −6.6761; 19.5895 | 0.6207; 1.1513 | 6.11; −21.8049 | 5.8308; −21.4966 |
References
- Zhipeng, Z.; Yin, D.; Ding, J.; Luo, Y.; Yuan, M.; Zhu, C. Collaborative tracking method in multi-camera system. J. Shanghai Jiaotong Univ. 2020, 25, 802–810. [Google Scholar]
- Bilal, A.; Wang, J.; Zain, A.A. Role of machine learning and data mining in internet security: Standing state with future directions. J. Comput. Netw. Commun. 2018, 2018, 6383145. [Google Scholar]
- Javaid, M.; Haleem, A.; Singh, R.P.; Rab, S.; Suman, R. Exploring impact and features of machine vision for progressive industry 4.0 culture. Sens. Int. 2022, 3, 100132. [Google Scholar] [CrossRef]
- Machine Learning in Python Pandas Documentation. Available online: https://scikit-learn.org/stable/ (accessed on 15 June 2023).
- Pandas Documentation. Available online: https://pandas.pydata.org/ (accessed on 13 June 2023).
- NumPy Documentation. Available online: https://numpy.org/doc/stable/ (accessed on 16 June 2023).
- Krenicky, T.; Nikitin, Y.; Božek, P. Model-Based Design of Induction Motor Control System in MATLAB. Appl. Sci. 2022, 12, 11957. [Google Scholar] [CrossRef]
- Li, S.; Zhang, Y.; Jin, L. Kinematic control of redundant manipulators using neural networks. IEEE Trans. Neural Netw. Learn. Syst. 2016, 28, 2243–2254. [Google Scholar] [CrossRef]
- Daun-Gruhn, S.; Büschges, A. From neuron to behavior: Dynamic equation-based prediction of biological processes in motor control. Biol. Cybern. 2011, 105, 71–88. [Google Scholar] [CrossRef]
- Yang, C.; Li, Z.; Cui, R.; Xu, B. Neural network-based motion control of an underactuated wheeled inverted pendulum model. IEEE Trans. Neural Netw. Learn. Syst. 2014, 25, 2004–2016. [Google Scholar] [CrossRef]
- Gosselin, C.M.; Hamel, J.-F. The agile eye: A high-performance three-degree-of-freedom camera-orienting device. In Proceedings of the 1994 IEEE International Conference on Robotics and Automation, San Diego, CA, USA, 8–13 May 1994; pp. 781–786. [Google Scholar]
- Bonev, I.A.; Chablat, D.; Wenger, P. Working and assembly modes of the Agile Eye. In Proceedings of the 2006 IEEE International Conference on Robotics and Automation 2006, ICRA, Orlando, FL, USA, 15–19 May 2006; pp. 2317–2322. [Google Scholar]
- Kuric, I.; Klačková, I.; Domnina, K.; Stenchlák, V.; Saga, M., Jr. Implementation of predictive models in industrial machines with proposed automatic adaptation algorithm. Appl. Sci. 2022, 12, 1853. [Google Scholar] [CrossRef]
- Du, K.-L.; Swamy, M.N.S. Perceptrons. In Neural Networks and Statistical Learning; Springer: Berlin, Germany, 2019; pp. 81–95. [Google Scholar]
- Brownlee, J. A Gentle Introduction to the Rectified Linear Unit (ReLU). Mach. Learn. Mastery 2020, 6, 10–13. [Google Scholar]
- Agarap, A.F. Deep learning using rectified linear units (relu). arXiv 2018, arXiv:1803.08375. [Google Scholar]
- Chang, Z.; Zhang, Y.; Chen, W. Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform. Energy 2019, 187, 115804. [Google Scholar] [CrossRef]
- Alibakhshi, R.; Mohammadi Daniali, H.R. Trajectory Optimization of Spherical Parallel Robots using Artificial Neural Network. Int. J. Adv. Des. Manuf. Technol. 2014, 7, 91–98. [Google Scholar]
- Gosselin, C.M.; Gange, M. A closed-form solution for the direct kinematics of a special class of spherical three-degree- of-freedom parallel manipulators. In Workshop on Computational Kinematics 1995; Springer: Berlin, Germany, 1995; pp. 231–240. [Google Scholar]
- Liu, X.-J.; Guan, L.; Wang, J. Kinematics and closed optimal design of a kind of PRRRP parallel manipulator. J. Mech. Des. 2007, 129, 558–563. [Google Scholar] [CrossRef]
- Zhou, S.; Gao, H.; Xu, C.; Jia, Z.; Lin, J.; Han, Q.; Luo, Z. Kinematic Modeling and Stiffness Analysis of a 3-DOF 3SPS+ 3PRS Parallel Manipulator. Mathematics 2022, 10, 4465. [Google Scholar] [CrossRef]
- Schappler, M. Structural and Dimensional Synthesis of Overconstraint Symmetric 3T2R Parallel Robots Using Tait-Bryan-Angle Kinematic Constraints. In Advances in Robot Kinematics 2022; Springer International Publishing: Cham, Switzerland, 2022; pp. 188–197. [Google Scholar]
- Craig, J. Introduction to Robotics, Global Edition, 4th ed.; Pearson Education Limited: London, UK, 2021; ISBN 978-12-921-6493-9. [Google Scholar]
- Ondočko, Š.; Svetlík, J.; Šašala, M.; Bobovský, Z.; Stejskal, T.; Dobránsky, J.; Demeč, P.; Hrivniak, L. Inverse kinematics data adaptation to non-standard modular robotic arm consisting of unique rotational modules. Appl. Sci. 2021, 11, 1203. [Google Scholar] [CrossRef]
- Tobaja, L.M.; Gil, J. Tracking Parabolic Trajectories with a Mobile Phone. Phys. Teach. 2023, 61, 268–270. [Google Scholar] [CrossRef]
- Christian, W.; Belloni, M.; Sokolowska, D.; Cox, A.; Dancy, M. Teaching with Physlets. Phys. Educ. 2020, 55, 045008. [Google Scholar] [CrossRef]
- Timan, A.F. Theory of Approximation of Functions of a Real Variable; Elsevier: Amsterdam, The Netherlands, 2014. [Google Scholar]
- Görög, A. Number of Points for Roundness Measurement-Measured Results Comparison. Res. Pap. Fac. Mater. Sci. Technol. Slovak Univ. Technol. 2011, 19, 19–24. [Google Scholar] [CrossRef]
- Kaťuch, P.; Kováč, J.; Dovica, M. Metrológia v Strojárstve. Laboratórne Úlohy—Teoretická Čast’; Strojnícka fakulta, Centrum Informatiky: Košice, Slovakia; ISBN 978-80-553-0543-1.
- Fritsch, F.N.; Carlson, R.E. Monotone Piecewise Cubic Interpolation. SIAM J. Numer. Anal. 1980, 17, 238–246. [Google Scholar] [CrossRef]
- Kahaner, D.; Cleve Moler, S.N. Numerical Methods and Software; Prentice Hall: Upper Saddle River, NJ, USA, 1988. [Google Scholar]
- Kuric, I.; Tlach, V.; Sága, M.; Císar, M.; Zajačko, I. Industrial robot positioning performance measured on inclined and parallel planes by double ballbar. Appl. Sci. 2021, 11, 1777. [Google Scholar] [CrossRef]
- Görög, A.; Görögová, I. Application of Fourier Series for Evaluation of Roundness Profiles in Metrology. Adv. Sci. Technol. Res. J. 2019, 13, 30–38. [Google Scholar] [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Bohušík, M.; Stenchlák, V.; Císar, M.; Bulej, V.; Kuric, I.; Dodok, T.; Bencel, A. Mechatronic Device Control by Artificial Intelligence. Sensors 2023, 23, 5872. https://doi.org/10.3390/s23135872
Bohušík M, Stenchlák V, Císar M, Bulej V, Kuric I, Dodok T, Bencel A. Mechatronic Device Control by Artificial Intelligence. Sensors. 2023; 23(13):5872. https://doi.org/10.3390/s23135872
Chicago/Turabian StyleBohušík, Martin, Vladimír Stenchlák, Miroslav Císar, Vladimír Bulej, Ivan Kuric, Tomáš Dodok, and Andrej Bencel. 2023. "Mechatronic Device Control by Artificial Intelligence" Sensors 23, no. 13: 5872. https://doi.org/10.3390/s23135872
APA StyleBohušík, M., Stenchlák, V., Císar, M., Bulej, V., Kuric, I., Dodok, T., & Bencel, A. (2023). Mechatronic Device Control by Artificial Intelligence. Sensors, 23(13), 5872. https://doi.org/10.3390/s23135872