Bir Quadcopter İHA'nın Tutum Kontrolü için PID ve NARX Sinir Ağının Performans Karşılaştırması

Öz

ÖZET: Bu çalışmada, parametrik belirsizlik ve bozulmaların etkisi altında kontrol performansını karşılaştırmak için otonom bir dört kanatlı helikopterin yükseklik ve hareket kontrolü için iki farklı tipte kontrolör tasarlanmış ve test edilmiştir. İlk kontrolör, geleneksel bir doğrusal kontrolör olan orantısal-integral-türev (PID) bir kontrolördür. Kapalı çevrim PID algoritmaları, kapalı çevrim geri besleme yöntemi ile ölçülen sensör değerleri ile referans girişleri arasındaki farktan oluşan hata değerlerini kullanarak sistemin sonuçlarını hesaplar. Kullanılan ikinci yöntem, PID'de kullanılan kapalı döngü geri besleme yöntemi ile doğrusal sistemlerin ve doğrusal olmayan sistemlerin tanımlanmasında ve kontrol edilmesinde hem avantaj hem de kolaylık sağlayan yapay sinir ağı (YSA) algoritmalarıdır. YSA algoritmalarının en önemli özelliği, farklı girdi değerleri ile eğitim sonucunda yüksek performans göstermeleridir. Bu nedenle YSA kontrol sistemi Gauss gürültüsü ile kullanılan giriş verileri ve istenen hedef veriler ile eğitilmiştir. Eksojen girdili doğrusal olmayan otoregresif dinamik zaman serisi yapay sinir ağı, zaman gecikmeli geri yayılım öğrenme performansı nedeniyle bir YSA denetleyicisi olarak seçilmiştir. Bu çalışmada dört kanatlı helikopter, Matlab Simulink üzerinde modellenmiştir. Model üzerinde PID ve NARX kontrolörlerin hareket kontrol performansları test edilmiştir. Tasarım, bir milisaniyelik sabit adım boyutuyla gerçek zamanlı bir simülasyon ortamında test edildi.

Anahtar Kelimeler

• Davranış ve yükseklik kontrolü
• dört kanatlı helikopter
• gaus gürültüsü
• orantısal-integral-türev
• dış (eksojen) girdili doğrusal olmayan otoregresif yapay sinir ağları

Performance Comparison of PID and NARX Neural Network for Attitude Control of a Quadcopter UAV

Abstract

ABSTRACT: In this study, two different types of controllers have been designed and tested for altitude and motion control of an autonomous quadrotor to compare the control performance under the influence of parametric uncertainty and disturbances. The first controller is a proportional-integral-derivative (PID) controller which is a conventional linear controller. The closed-loop PID algorithms calculate the results of the system by using the error values that consist of the difference between the sensor values measured by the closed-loop feedback method and the reference inputs. The second method that has been used is artificial neural network (ANN) algorithms, which provide both advantages and convenience in defining and controlling linear systems and non-linear systems with the closed-loop feedback method used in PID. The most important feature of the ANN algorithms is their high performance as a result of training with different input values. Therefore, the ANN control system has been trained with the input data used with Gaussian noise and the desired target data. A dynamic time series non-linear autoregressive with Exogenous input (NARX) neural network has been chosen as an ANN controller because of the time-delayed backpropagation learning performance. In this study, PID, and NARX NN control algorithms to control the maneuvers and altitude of the quadcopter and the mathematical model have been designed on Matlab Simulink. Motion control performances of the PID and NARX controllers are tested on the model. The design was tested on a real-time simulation environment with a one-millisecond fixed-step size. This paper proposes an alternative approach to control attitude and altitude on a quadcopter with the NARX NN algorithm.

Keywords

• Attitude and altitude control
• quadcopter
• proportional-integrator-derivative
• non-linear autoregressive with external (Exogenous) input artificial neural networks
• gaussian noise

References

1. Akın M., Gören A., Rachid A., Implementation of Sensor Filters and Altitude Estimation of Unmanned Aerial Vehicle using Kalman Filter. Journal of Mechatronics and Robotics 5, 8-17, 2021.
2. Anonymous, 2021, Mathworks Documentation, https://www.mathworks.com/help/.
3. Buitrago J., Asfour S., Short-Term Forecasting of Electric Loads Using Nonlinear Autoregressive Artificial Neural Networks with Exogenous Vector Inputs. Energies 10(1):40, 1-25, 2017.
4. Cedro L., Wieczorkowski K., Optimizing PID controller gains to model the performance of a quadcopter. Transportation Research Procedia 40, 156-169, 2019.
5. El Dakrory A. M., Tawfik M., Identifying the Attitude of Dynamic Systems using NeuralNetwork, 2016 International Workshop on Recent Advances in Robotics and Sensor Technology for Humanitarian Demining and Counter-IEDs (RST), 1-4, 2016.
6. Hagan M., Menhaj M., Training Feedforward Networks with the Marquardt Algorithm, IEEE Transactions on neural networks 5(6), 989-993, 1994.
7. Hagiwara K., Hayasaka T., Toda N., Usui S., Kuno K., Upper bound of the expected training error of neural network regression for a Gaussian noise sequence. Neural Networks 14(10), 1419-1429, 2001.
8. Hamidi K. E., Mjahed M., Kari A. E., Ayad H., Adaptive Control Using Neural Networks and Approximate Models for Nonlinear Dynamic Systems. Modelling and Simulation in Engineering 2020:8642915, 1-13, 2020.

9. Hamidi K. E., Mjadeh M., Kari A. E., Ayad H., Neural Network and Fuzzy-logic-based Self-tuning PID Control for Quadcopter Path Tracking. Studies in Informatics and Control 28(4), 401-412, 2019.
10. Krivec T., Papa G., Kocijan J., Simulation of variational Gaussian process NARX models with GPGPU. ISA Transactions 109, 141-151, 2021.
11. Luukkonen T., Modelling and control of quadcopter, Independent research project in applied mathematics Espoo, 1-26, 2011.
12. Muliadi J., Kusumoputro B., Neural Network Control System of UAV Altitude Dynamics and Its Comparison with the PID Control System. Journal of Advanced Transportation 2018: 3823201, 1-18, 2018.
13. Nguyen N.P., Mung N.X., Thanh H.L.N.N., Huynh T.T., Lam N.T., Hong S.K., Adaptive Sliding Mode Control for Attitude and Altitude System of a Quadcopter UAV via Neural Network, IEEE Access Volume: 9, 40076-40085, 2021.
14. Paiva E., Soto J., Salinas J., Ipanaqué W., Modeling, Simulation and Implementation of a modified PID Controller for stabilizing a Quadcopter, 2016 IEEE International Conference on Automatica (ICA-ACCA), 1-6, 2016.
15. Praveen V., Pillai A. S., Modeling and Simulation of Quadcopter using PID Controller, IJCTA 9(15), 7151-7158, 2016.
16. Razmi H., Afshinfar S., Neural network-based adaptive sliding mode control design for position and attitude control of a quadrotor UAV. Aerospace Science and Technology 91, 12-27, 2019.
17. Wang P., Man Z., Cao Z., Zheng J., Dynamics Modelling and Linear Control of Quadcopter, International Conference on Advanced Mechatronic Systems 2016, 498-503, 2016.
18. Yoon G.Y., Yamamoto A., Lim H.O., Mechanism and Neural Network Based on PID Control of Quadcopter, 16th International Conference on Control, Automation and Systems (ICCAS 2016), 19-24, 2016.
19. Zulu A., John S., A review of control algorithms for autonomous quadrotors. Open Journal of Applied Sciences 4, 547-556, 2014.