Attitude UAV Stability Control Using Linear Quadratic Regulator-Neural Network (LQR-NN)

Oktaf Agni Dhewa; Fatchul Arifin; Ardy Seto Priyambodo; Anggun Winursito; Yasir Mohd. Mustafa

doi:10.31436/iiumej.v25i2.3119

Authors

Oktaf Agni Dhewa Yogyakarta State University https://orcid.org/0000-0002-5652-3922
Fatchul Arifin Yogyakarta State University https://orcid.org/0000-0002-5182-1269
Ardy Seto Priyambodo Yogyakarta State University
Anggun Winursito Yogyakarta State University
Yasir Mohd. Mustafa International Islamic University Malaysia https://orcid.org/0000-0003-4846-7104

DOI:

https://doi.org/10.31436/iiumej.v25i2.3119

Keywords:

UAV, Flying Wing, Optimal Control, Adaptive

Abstract

The stability of an Unmanned Aerial Vehicle (UAV) attitude is crucial in aviation to mitigate the risk of accidents and ensure mission success. This study aims to optimize and adaptively control the flight attitude stability of a flying wing-type UAV amidst environmental variations. This is achieved through the utilization of Linear Quadratic Regulator-Neural Network (LQR-NN) control, wherein the Neural Network predicts the optimal K gain value by fine-tuning Q and R parameters to minimize system errors. An online learning neural network adjusts the K value based on real-time error feedback, enhancing system performance. Experimental results demonstrate improved stability metrics: for roll angle stability, a rise time of 0.4682 seconds, settling time of 1.3819 seconds, overshoot of 0.298%, and Steady State Error (SSE) of 0.133 degrees; for pitch angle stability, a rise time of 0.2309 seconds, settling time of 0.7091 seconds, overshoot of 0.1224%, and Steady State Error (SSE) of 0.0239 degrees. The LQR-NN approach effectively reduces overshoot compared to traditional Linear Quadratic Regulator (LQR) control, thereby minimizing oscillations. Furthermore, LQR-NN can minimize the Steady State Error (SSE) to 0.074 degrees for roll rotation motion and 0.035 degrees for pitch rotation motion.

ABSTRAK: Kestabilan perubahan Pesawat Tanpa Pemandu (UAV) adalah penting dalam penerbangan bagi mengurangkan risiko kemalangan dan memastikan kejayaan misi. Kajian ini bertujuan mengoptimum dan menstabilkan perubahan kawalan adaptif penerbangan UAV jenis sayap terbang di tengah-tengah variasi persekitaran. Ini dicapai melalui penggunaan kawalan Rangkaian Linear Kuadratik Pengatur-Neural (LQR-NN), di mana Rangkaian Neural meramal nilai perolehan K optimum dengan meneliti parameter Q dan R bagi mengurangkan ralat sistem. Rangkaian neural pembelajaran dalam talian melaraskan nilai K berdasarkan maklum balas ralat masa nyata, ini meningkatkan prestasi sistem. Dapatan kajian eksperimen menunjukkan metrik kestabilan lebih baik: bagi kestabilan sudut gulungan, masa kenaikan sebanyak 0.4682 saat, masa kestabilan 1.3819 saat, lajakan 0.298% dan Ralat Keadaan Mantap (SSE) 0.133 darjah; bagi kestabilan sudut pic, masa kenaikan 0.2309 saat, masa penetapan 0.7091 saat, lajakan 0.1224%, dan Ralat Keadaan Mantap (SSE) 0.0239 darjah. Pendekatan LQR-NN berkesan mengurangkan lajakan berbanding kawalan tradisi Pengatur Kuadratik Linear (LQR), dengan itu mengurangkan ayunan. Tambahan, LQR-NN dapat mengurangkan Ralat Keadaan Mantap (SSE), sebanyak 0.074 darjah bagi gerakan putaran guling dan 0.035 darjah bagi gerakan putaran anggul.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

References

Mátyás P, Nagy M. (2019). Brief history of uav development. Repüléstudományi Közlemények, 31(1): 155-6. https://doi.org/10.32560/rk.2019.1.13 DOI: https://doi.org/10.32560/rk.2019.1.13

Andres AM, Yilei H, Yuhan J. (2023). A review of unmanned aerial vehicle applications in construction management: 2016–2021. Standards. 3(2): 95–109. https://doi.org/10.3390/standards3020009 DOI: https://doi.org/10.3390/standards3020009

Tri KP, Oktaf AD, Tri S. (2020). Model of linear quadratic regulator (lqr) control system in waypoint flight mission of flying wing uav. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 12(4): 43–49. https://jtec.utem.edu.my/jtec/article/view/5696

Stavros K, Chris B, Pavlos K, Pericles P, Kyros Y. (2023). Parametric investigation of canards on a flying wing uav using the taguchi method. Aerospace, 10(3): 264. https://doi.org/10.3390/aerospace10030264 DOI: https://doi.org/10.3390/aerospace10030264

Seyhun D. (2023). Aerodynamic performance comparison of airfoils in flying wing uav. International Journal of Innovative Engineering Applications, 7(1): 123–127. https://doi.org/10.46460/ijiea.1169652 DOI: https://doi.org/10.46460/ijiea.1169652

Panjani D, Indira P, Chandu A. (2022). Design of folded wing mechanism for unmanned aerial vehicle (uav). Materials Today: Proceedings, 62: 4117–4125. https://doi.org/10.1016/j.matpr.2022.04.660 DOI: https://doi.org/10.1016/j.matpr.2022.04.660

Yankui W, Xiangxi T, Tao L. (2020). Lateral stability and control of a flying wing configuration aircraft. Journal of Physics: Conference Series, 1509(1): 012022. https://doi.org/10.1088/1742-6596/1509/1/012022 DOI: https://doi.org/10.1088/1742-6596/1509/1/012022

Jose DH, Camilo E, Juan PA, Gustavo S, Juliana AN, Jorge IG. (2023). Two-way coupled aero-structural optimization of stable flying wings, Aerospace. 10(4): 346. https://doi.org/10.3390/aerospace10040346 DOI: https://doi.org/10.3390/aerospace10040346

Oktaf AD, Andi D, Tri KP. (2017). Model of linear quadratic regulator (lqr) control method in hovering state of quadrotor. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(3): 135–143. https://jtec.utem.edu.my/jtec/article/view/1589

Oktaf AD, Faisal FR. (2022). Peningkatan kestabilan quadrotor menggunakan kendali linear quadratic regulator dengan kompensasi integrator dalam mempertahankan posisi. Buletin Ilmiah Sarjana Teknik Elektro. 4(2): 62–75. https://doi.org/10.12928/biste.v4i2.6808 DOI: https://doi.org/10.12928/biste.v4i2.6808

Riccardo D, Piero T, Salvatore FG, Alessandro M. (2021). Recent advances in unmanned aerial vehicle forest remote sensing - a systematic review, part i: a general framework. Forests. 12(3): 327. https://doi.org/10.3390/f12030327 DOI: https://doi.org/10.3390/f12030327

Jingjing B, Afshin M, Maryam F, Mehran M. (2019). Lqr through the lens of first order methods: discrete-time case. https://doi.org/10.48550/ARXIV.1907.08921

Aisha SE, Seref NE. (2022). Robust lqr and lqr-pi control strategies based on adaptive weighting matrix selection for a uav position and attitude tracking control. Alexandria Engineering Journal, 61(8): 6275–6292. https://doi.org/10.1016/j.aej.2021.11.057 DOI: https://doi.org/10.1016/j.aej.2021.11.057

Jinsong Z, Yan L, Lin L. (2023). LQR-based adaptive optimal control for aircraft engine. Proceedings of 2023 Chinese Intelligent Systems Conference. CISC 2023. Lecture Notes in Electrical Engineering, vol 1090. Springer, Singapore. https://doi.org/10.1007/978-981-99-6882-4_28 DOI: https://doi.org/10.1007/978-981-99-6882-4_28

Faisal FR, Tri KP. (2019). Penalaan mandiri full state feedback lqr dengan jst tiruan pada kendali quadrotor. Indonesian Journal of Electronics and Instrumentation Systems (IJEIS). 9(1): 21-32. https://doi.org/10.22146/ijeis.37212

Chenxi S, Tao L, Kui Y. (2013). Balance control of two-wheeled self-balancing robot based on Linear Quadratic Regulator and Neural Network. 2013 Fourth Int. Conf. Intell. Control Inf. Process. 1: 862–867. https://doi.org/10.1109/ICICIP.2013.6568193 DOI: https://doi.org/10.1109/ICICIP.2013.6568193

Huynh VN, Dinh PN, Nguyen TMN, Nguyen TD, Nguyen PL, Phung ST, Le THL, Dang XB. (2021). A lqr-based neural-network controller for fast stabilizing rotary inverted pendulum. 2021 International Conference on System Science and Engineering (ICSSE), 19–22. https://doi.org/10.1109/ICSSE52999.2021.9537940 DOI: https://doi.org/10.1109/ICSSE52999.2021.9537940

John BH. (2007). Modelling Simulation and Control of Fixed-wing UAV: CyberSwan. Institutt for teknisk kybernetikk.

Tri KP, Abdul MF. (2021). Modeling and Simulation of The UX-6 Fixed-Wing Unmanned Aerial Vehicle. J Control Autom Electr Syst 32, 1344–1355. https://doi.org/10.1007/s40313-021-00754-5 DOI: https://doi.org/10.1007/s40313-021-00754-5

Burak E. (2019). Fault tolerant flight control applications for a fixed wing uav using linear and nonlinear approaches. https://doi.org/10.13140/RG.2.2.25180.03205

Jie C, Jianxin L. (2021). Mathematical modeling and fault tolerant control of uav with wing layout. Journal of Physics: Conference Series, 1846(1): 012045. https://doi.org/10.1088/1742-6596/1846/1/012045 DOI: https://doi.org/10.1088/1742-6596/1846/1/012045

Ruijie S, Zhou Z, Xiaoping Z. (2022). Stability control of a fixed full-wing layout uav under manipulation constraints. Aerospace Science and Technology, 120: 107263. https://doi.org/10.1016/j.ast.2021.107263 DOI: https://doi.org/10.1016/j.ast.2021.107263

Aman S, Gabriel FL, Jan S. (2023). Identifying aerodynamics of small fixed-wing drones using inertial measurements for model-based navigation. NAVIGATION: Journal of the Institute of Navigation, 70(4): navi.611. https://doi.org/10.33012/navi.611 DOI: https://doi.org/10.33012/navi.611

Yuqiong S, Song W, Anastasiia K, Yujing H. (2019). Attitude control of flying wing uav based on advanced adrc. IOP Conference Series: Materials Science and Engineering, 677(5): 052075. https://doi.org/10.1088/1757-899X/677/5/052075 DOI: https://doi.org/10.1088/1757-899X/677/5/052075

Shi Q, Cui H, Li F, Liu Y, Ju W, Sun Y. (2017). A hybrid dynamic demand control strategy for power system frequency regulation. CSEE J Power Energy Syst, 3(2):176–185. https://doi.org/10.17775/CSEEJPES.2017.0022 DOI: https://doi.org/10.17775/CSEEJPES.2017.0022

Jianglin L, Dezong Z. (2023). Finding the lqr weights to ensure the associated riccati equations admit a common solution. IEEE Transactions on Automatic Control, 68(10): 6393–6400. https://doi.org/10.1109/TAC.2023.3234237 DOI: https://doi.org/10.1109/TAC.2023.3234237

Gembong ES, Wijaya K, Amroy CLG. (2019). Linear quadratic regulator controller (lqr) for ar. drone’s safe landing. 2019 International Conference on Sustainable Information Engineering and Technology (SIET), 228–233. https://doi.org/10.1109/SIET48054.2019.8986078 DOI: https://doi.org/10.1109/SIET48054.2019.8986078

Mahmud S. (2021). Modelling and simulation of small scale fixedwing autonomous aerial vehicles. PhD Thesis. Sheffield Hallan University, Business, Technology and Engineering.

Faisal FR, Tri KP. (2019). Penalaan mandiri full state feedback dengan lqr dan jst pada kendali quadrotor. IJEIS (Indonesian Journal of Electronics and Instrumentation Systems), 9(1): 21. https://doi.org/10.22146/ijeis.37212 DOI: https://doi.org/10.22146/ijeis.37212

Bailun J, Boyang L, Weifeng Z, Li-Yu L, Chih-Keng C, Chih-Yung C. (2022). Neural network based model predictive control for a quadrotor uav. Aerospace, 9(8): 460. https://doi.org/10.3390/aerospace9080460 DOI: https://doi.org/10.3390/aerospace9080460

Yunlong G, Guixin Z, Tong Z. (2022). Based on backpropagation neural network and adaptive linear active disturbance rejection control for attitude of a quadrotor carrying a load. Applied Sciences, 12(24): 12698. https://doi.org/10.3390/app122412698 DOI: https://doi.org/10.3390/app122412698

Aris T, Suroto M, Munadi M, Joga DS. (2023). Application of driving behavior control system using artificial neural network to improve driving comfort by adjusting air-to-fuel Ratio. IIUM Engineering Journal, 24(2): 337–353. https://doi.org/10.31436/iiumej.v24i2.2781 DOI: https://doi.org/10.31436/iiumej.v24i2.2781

Oktaf AD, Tri KP, Aris N, Yasir MM. (2022). Enhancement of stability on autonomous waypoint mission of quadrotor using lqr integrator control. IIUM Engineering Journal, 23(1): 129–158. https://doi.org/10.31436/iiumej.v23i1.1803 DOI: https://doi.org/10.31436/iiumej.v23i1.1803