ISBN
979-13-87631-27-7
Fecha de publicación
27-12-2024
Licencia
D. R. © copyright 2024. Alan David Ramírez Noriega, Ivan Noel Alvarez Sánchez y Herman Geovany Ayala Zúñiga
José de Jesús Valenzuela Hernández
Colegio Nacional de Educación Profesional Técnica
0009-0009-6152-4186
Giovanni Mora Castro
Colegio Nacional de Educación Profesional Técnica
0009-0004-6108-9122
Gilberto Bojórquez Delgado
Instituto Tecnológico Superior de Guasave
0009-0000-7829-6540
Acerca de
El presente artículo, explora el uso de redes neuronales convolucionales (CNN) para modelar la dinámica no lineal de cuadricópteros utilizando datos de vuelo registrados en la “caja negra”. Este enfoque es crucial debido a la complejidad y la naturaleza no lineal de los cuadricópteros, que demandan métodos avanzados de modelización. La investigación se centra en seleccionar las variables más significativas para el entrenamiento de la CNN, con el objetivo de mejorar la adaptabilidad y eficiencia de los drones en entornos dinámicos y no estructurados.
El artículo inicia con una revisión de trabajos relacionados y el marco teórico, destacando la importancia y los desafíos del modelado preciso de cuadricópteros. Posteriormente, se describe la metodología para…
… extraer y analizar datos de la caja negra, incluyendo parámetros como la aceleración, la orientación y los comandos de la radioemisora. Se construye una matriz de correlación para identificar las relaciones entre estas variables y se presentan los resultados del análisis, destacando la alta correlación entre los motores y los sensores IMU (acelerómetro y giroscopio).
Finalmente, se discuten las implicaciones de las correlaciones observadas y se concluye que las variables seleccionadas serán utilizadas para entrenar la CNN. Se menciona la intención de realizar investigaciones futuras para comparar otras técnicas de selección de variables y mejorar el modelo propuesto, con el objetivo de desarrollar sistemas de control más sofisticados y adaptativos para cuadricópteros.
Referencias
Abdelmaksoud, S. I., Mailah, M., & Abdallah, A. M. (2021). Practical Real-Time Implementation of a Disturbance Rejection Control Scheme for a Twin-Rotor Helicopter System Using Intelligent Active Force Control. IEEE Access, 9, 4886–4901. https://doi.org/10.1109/ACCESS.2020.3046728
Abdulkareem, A., Oguntosin, V., Popoola, O. M., & Idowu, A. A. (2022). Modeling and Nonlinear Control of a Quadcopter for Stabilization and Trajectory Tracking. Journal of Engineering (United Kingdom), 2022. https://doi.org/10.1155/2022/2449901
Ahn, S., Kim, J., Park, S. Y., & Cho, S. (2021). Explaining Deep Learning-Based Traffic Classification Using a Genetic Algorithm. IEEE Access, 9, 4738–4751. https://doi.org/10.1109/ACCESS.2020.3048348
Ali, K. M., & Jaber, A. A. (2022). Comparing dynamic model and flight control of plus and cross quadcopter configurations. FME Transactions, 50(4), 683–692. https://doi.org/10.5937/FME2204683M
Ayyad, A., Chehadeh, M., Awad, M. I., & Zweiri, Y. (2020). Real-Time System Identification Using Deep Learning for Linear Processes with Application to Unmanned Aerial Vehicles. IEEE Access, 8, 122539–122553. https://doi.org/10.1109/ACCESS.2020.3006277
Betaflight – Pushing the Limits of UAV Performance | Betaflight. (n.d.). Retrieved May 28, 2024, from https://betaflight.com/
Ccari, L. F. C., & Yanyachi, P. R. (2023). A Novel Neural Network-Based Robust Adaptive Formation Control for Cooperative Transport of a Payload Using Two Underactuated Quadcopters. IEEE Access, 11, 36015–36028. https://doi.org/10.1109/ACCESS.2023.3265957
Cooper, Y. N., Ganesh Ram, R. K., Kalaichelvi, V., & Bhatia, V. (2014). Stabilization and Control of an Autonomous Quadcopter. Applied Mechanics and Materials, 666, 161–165. https://doi.org/10.4028/WWW.SCIENTIFIC.NET/AMM.666.161
Duan, J., Zhou, C. G., Zhao, L. C., Jia, Y. Y., & Liu, Z. X. (2023). Finite-time control based on RBF neural network for quadrotor UAVs with varied mass load. Journal of Physics: Conference Series, 2612(1), 012008. https://doi.org/10.1088/1742-6596/2612/1/012008
Eltayeb, A., Rahmat, M. F., Basri, M. A. M., Mohammed Eltoum, M. A., & Mahmoud, M. S. (2022). Integral Adaptive Sliding Mode Control for Quadcopter UAV Under Variable Payload and Disturbance. IEEE Access. https://doi.org/10.1109/ACCESS.2022.3203058
Esfandiari, M. J., Haghighi, H., & Urgessa, G. (2023). Machine Learning-based Optimum Reinforced Concrete Design for Progressive Collapse. Electronic Journal of Structural Engineering, 23(2), 1–8. https://doi.org/10.56748/ejse.233642
Esmail, M. S., Merzban, M. H., Khalaf, A. A. M., Hamed, H. F. A., & Hussein, A. I. (2022). Attitude and Altitude Nonlinear Control Regulation of a Quadcopter Using Quaternion Representation. IEEE Access, 10, 5884–5894. https://doi.org/10.1109/ACCESS.2022.3141544
Froud, R., Hansen, S. H., Ruud, H. K., Foss, J., Ferguson, L., & Fredriksen, P. M. (2021). Relative performance of machine learning and linear regression in predicting quality of life and academic performance of school children in Norway: Data analysis of a quasi-experimental study. Journal of Medical Internet Research, 23(7), e22021. https://doi.org/10.2196/22021
GitHub – betaflight/blackbox-log-viewer: Interactive log viewer for flight logs recorded with blackbox. (n.d.). Retrieved May 28, 2024, from https://github.com/betaflight/blackbox-log-viewer
González-Hernández, I., Salazar, S., Lozano, R., & Ramírez-Ayala, O. (2022). Real-Time Improvement of a Trajectory-Tracking Control Based on Super-Twisting Algorithm for a Quadrotor Aircraft. Drones 2022, Vol. 6, Page 36, 6(2), 36. https://doi.org/10.3390/DRONES6020036
Gotov, B.-E., Tserendondog, T., Choimaa, L., & Amar, B. (2022). Quadcopter Stabilization using Neural Network Model from Collected Data of PID Controller. ICT Focus, 1(1), 10–21. https://doi.org/10.58873/SICT.V1I1.28
Gusev, V. N., Blishchenko, A. A., & Sannikova, A. P. (2022). Study of a set of factors influencing the error of surveying mine facilities using a geodesic quadcopter. Journal of Mining Institute, 254, 173–179. https://doi.org/10.31897/PMI.2022.35
Heidari, H., & Saska, M. (2021). Trajectory Planning of Quadrotor Systems for Various Objective Functions. Robotica, 39(1), 137–152. https://doi.org/10.1017/S0263574720000247
Ho, D., Linder, J., Hendeby, G., & Enqvist, M. (2017). Mass estimation of a quadcopter using IMU data. 2017 International Conference on Unmanned Aircraft Systems, ICUAS 2017, 1260–1266. https://doi.org/10.1109/ICUAS.2017.7991417
Huang, X., Kroening, D., Ruan, W., Sharp, J., Sun, Y., Thamo, E., Wu, M., & Yi, X. (2020). A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability. Computer Science Review, 37, 100270. https://doi.org/10.1016/J.COSREV.2020.100270
Jazar, R. N. (2022). Robot Dynamics. Theory of Applied Robotics, 609–684. https://doi.org/10.1007/978-3-030-93220-6_11
Khaki, S., Wang, L., & Archontoulis, S. V. (2020). A CNN-RNN Framework for Crop Yield Prediction. Frontiers in Plant Science, 10, 492736. https://doi.org/10.3389/FPLS.2019.01750/BIBTEX
Kremer, P., Sanchez-Lopez, J. L., & Voos, H. (2022). A Hybrid Modelling Approach for Aerial Manipulators. Journal of Intelligent and Robotic Systems: Theory and Applications, 105(4), 1–21. https://doi.org/10.1007/S10846-022-01640-1/METRICS
Lee, M. Y., Chen, B. Sen, Tsai, C. Y., & Hwang, C. L. (2021). Stochastic H∞Robust Decentralized Tracking Control of Large-Scale Team Formation UAV Network System with Time-Varying Delay and Packet Dropout under Interconnected Couplings and Wiener Fluctuations. IEEE Access, 9, 41976–41997. https://doi.org/10.1109/ACCESS.2021.3065127
Li, H., He, B., Yin, Q., Mu, X., Zhang, J., Wan, J., Wang, D., & Shen, Y. (2019). Fuzzy Optimized MFAC Based on ADRC in AUV Heading Control. Electronics 2019, Vol. 8, Page 608, 8(6), 608. https://doi.org/10.3390/ELECTRONICS8060608
Li, X., Tupayachi, J., Sharmin, A., & Martinez Ferguson, M. (2023). Drone-Aided Delivery Methods, Challenge, and the Future: A Methodological Review. Drones 2023, Vol. 7, Page 191, 7(3), 191. https://doi.org/10.3390/DRONES7030191
Lopez-Pacheco, M., & Yu, W. (2022). Complex Valued Deep Neural Networks for Nonlinear System Modeling. Neural Processing Letters, 54(1), 559–580. https://doi.org/10.1007/S11063-021-10644-1/TABLES/14
Ma, G., Wu, H., Zhao, Z., Zou, T., & Hong, K. S. (2023). Adaptive neural network control of a non-linear two-degree-of-freedom helicopter system with prescribed performance. IET Control Theory & Applications, 17(13), 1789–1799. https://doi.org/10.1049/CTH2.12379
Ma, H., Xu, C. F., Shen, Z., Yu, C. H., & Li, Y. M. (2018). Application of Machine Learning Techniques for Clinical Predictive Modeling: A Cross-Sectional Study on Nonalcoholic Fatty Liver Disease in China. BioMed Research International, 2018. https://doi.org/10.1155/2018/4304376
Martinez, W. M., Borges, J. A., Rodriguez, N. J., & Hunt, S. (1995). Natural language processor with neural networks. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 4, 3156–3161. https://doi.org/10.1109/ICSMC.1995.538268
Martini, S., Sonmez, S., Rizzo, A., Stefanovic, M., Rutherford, M. J., & Valavanis, K. P. (2022). Euler-Lagrange Modeling and Control of Quadrotor UAV with Aerodynamic Compensation. 2022 International Conference on Unmanned Aircraft Systems, ICUAS 2022, 369–377. https://doi.org/10.1109/ICUAS54217.2022.9836215
Merkert, R., & Bushell, J. (2020). Managing the drone revolution: A systematic literature review into the current use of airborne drones and future strategic directions for their effective control. Journal of Air Transport Management, 89, 101929. https://doi.org/10.1016/J.JAIRTRAMAN.2020.101929
Mizouri, W., Najar, S., Bouabdallah, L., & Aoun, M. (2020). Dynamic Modeling of a Quadrotor UAV Prototype. Studies in Systems, Decision and Control, 270, 281–299. https://doi.org/10.1007/978-981-15-1819-5_14/COVER
Narendra, K. S., & Parthasarathy, K. (1990). Identification and Control of Dynamical Systems Using Neural Networks. IEEE Transactions on Neural Networks, 1(1), 4–27. https://doi.org/10.1109/72.80202
Nguyen, N. P., Mung, N. X., Thanh, H. L. N. N., Huynh, T. T., Lam, N. T., & Hong, S. K. (2021). Adaptive Sliding Mode Control for Attitude and Altitude System of a Quadcopter UAV via Neural Network. IEEE Access, 9, 40076–40085. https://doi.org/10.1109/ACCESS.2021.3064883
Rajendra, P., & Brahmajirao, V. (2020). Modeling of dynamical systems through deep learning. Biophysical Reviews, 12(6), 1311. https://doi.org/10.1007/S12551-020-00776-4
Rashdi, R., Ali, Z., Larik, J. R., Jamro, L. A., & Baig, U. (2019). Controller Design for the Rotational Dynamics of a Quadcopter. Mehran University Research Journal of Engineering and Technology, 38(2), 269–274. https://doi.org/10.22581/MUET1982.1902.03
Rejeb, A., Abdollahi, A., Rejeb, K., & Treiblmaier, H. (2022). Drones in agriculture: A review and bibliometric analysis. Computers and Electronics in Agriculture, 198, 107017. https://doi.org/10.1016/J.COMPAG.2022.107017
Shauqee, M. N., Rajendran, P., & Suhadis, N. M. (2021). An effective proportional-double derivative-linear quadratic regulator controller for quadcopter attitude and altitude control. Automatika, 62(3–4), 415–433. https://doi.org/10.1080/00051144.2021.1981527
Springer, T., Eiroa‐lledo, E., Stevens, E., & Linstead, E. (2021). On-Device Deep Learning Inference for System-on-Chip (SoC) Architectures. Electronics 2021, Vol. 10, Page 689, 10(6), 689. https://doi.org/10.3390/ELECTRONICS10060689
Ullah Khan, R., & Kumar, R. (2018). Optimizing a Deep Learning Model in Order to Have a Robust Neural Network Topology. International Journal of Modeling and Optimization, 8(3), 145–149. https://doi.org/10.7763/IJMO.2018.V8.639
Wenhui, Z., Hongsheng, L., Xiaoping, Y., Jiacai, H., & Mingying, H. (2018). Adaptive robust control for free-floating space robot with unknown uncertainty based on neural network. International Journal of Advanced Robotic Systems, 15(6). https://doi.org/10.1177/1729881418811518/ASSET/IMAGES/LARGE/10.1177_1729881418811518-FIG11.JPEG
Ye, J., Wang, J., Song, T., Wu, Z., & Tang, P. (2021). Nonlinear modeling the quadcopter considering the aerodynamic interaction. IEEE Access, 9, 134716–134732. https://doi.org/10.1109/ACCESS.2021.3116676
Zhan, T. (2022). DL 101: Basic introduction to deep learning with its application in biomedical related fields. Statistics in Medicine, 41(26), 5365–5378. https://doi.org/10.1002/SIM.9564
Zhang, X., Zhao, Z., Wang, Z., & Wang, X. (2021). Fault Detection and Identification Method for Quadcopter Based on Airframe Vibration Signals. Sensors 2021, Vol. 21, Page 581, 21(2), 581. https://doi.org/10.3390/S21020581
Zhenhuan, C. A. I., Zhang, S., & Jing, X. (2021). Model predictive controller for quadcopter trajectory tracking based on feedback linearization. IEEE Access, 9, 162909–162918. https://doi.org/10.1109/ACCESS.2021.3134009
Zhilenkova, E., Cvetkov, P., & Epifantsev, I. (2021). Approaches to assessing the characteristics of a vehicle body based on a virtual test bench. E3S Web of Conferences, 258, 09077. https://doi.org/10.1051/E3SCONF/202125809077
Zhou, Y., Tian, Z., & Lin, H. (2023). UAV based adaptive trajectory tracking control with input saturation and unknown time-varying disturbances. IET Intelligent Transport Systems, 17(4), 780–793. https://doi.org/10.1049/ITR2.12303