Kendali Adaptif Neuro Fuzzy PID untuk Kestabilan Terbang Fixed Wing UAV (Adaptive Control of Neuro Fuzzy PID for Fixed Wing UAV Flight Stability)

Irmawan, Erwhin; Prasetiyo, Erwan Eko

doi:10.22146/jnteti.v9i1.142

Cited by 8 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Metode kendali yang diterapkan berhasil mengendalikan sudut roll dan membuat pesawat mencapai kestabilan sikap, namun masih menghasilkan overshoot yang besar serta waktu penyelesaian yang relative lama. Erwhin Irmawan [10] menggabungan metode adaptif neuro fuzzy dan PID untuk mengendaikan kestabilan sikap longitudinal pesawat tanpa awak, penggabungan kedua metode tersebut berhasil membuat respon sistem dan waktu penyelesaiannya menjadi lebih cepat, tetapi overshoot yang dihasilkan cukup besar. Pengendalian sudut roll sangat penting karena berpengaruh terhadap kestabilan sikap longitudinal pesawat, oleh karena itu sistem kendali yang yang kuat dan cepat sangat dibutuhkan untuk pesawat dalam rangka menuju titik kestabilan.…”

Section: Pendahuluanunclassified

Implementasi Kendali LQR Untuk Pengendalian Sikap Longitudinal Pesawat Flying Wing

Susanto¹,

Riskiono

Rikendry

et al. 2020

jelekn

View full text Add to dashboard Cite

Perkembangan pesawat tanpa awak dalam beberapa tahun terakhir menjadi perhatian banyak pihak dan menarik banyak peminat. Pesawat tanpa awak telah banyak digunakan untuk berbagai misi, diantaranya adalah untuk pemetaan wilayah dan militer. Bentuk pesawat tanpa awak yang relative kecil, menjadikan sensitive terhadap gangguan lingkungan terutama angin, hal tersebut dapat menyebabkan pesawat kehilangan kestabilan dan mengalami stall, sehingga menggagalkan misi penerbangan. Oleh karena itu diperlukan sistem kendali yang yang kuat dan cepat untuk mengatur konfigurasi gerak agar tidak terjadi stall. Pada penelitian ini metode kendali LQR diterapkan untuk mengendalikan sudut roll pada pesawat agar mampu mempertahankan kestabilan sikap longitudinal. Berdasarkan hasil pengujian yang telah dilakukan, metode kendali LQR mampu mengendalikan sudut roll pesawat sehingga pesawat mampu mempertahankan kestabilan sikap longitudinal, terbukti ketika sudut roll diberikan gangguan, terjadi overshoot sebesar 4,28º , namun pesawat dengan cepat mampu kembali ke keadaan semula dengan rise time 0,7 detik, setling time 1,3 detik dan kecendrungan steady state error sebesar 1,37º

show abstract

Section: Pendahuluanunclassified

Implementasi Kendali LQR Untuk Pengendalian Sikap Longitudinal Pesawat Flying Wing

Susanto¹,

Riskiono

Rikendry

et al. 2020

jelekn

View full text Add to dashboard Cite

show abstract

“…Beberapa kondisi yang dihindari oleh pesawat ketika terbang menjalankan misinya agar tidak terjadi crash, salah satunya adalah stall. Stall adalah kondisi sudut serang (angle of attack) pesawat meningkat melebihi titik tertentu yang menyebabkan gaya angkat menjadi berkurang [5]. Sudut kritis yang dapat menyebabkan stall pada pesawat adalah 25 derajat.…”

Section: Pendahuluanunclassified

“…Proses pengendalin pesawat tidak menjadi masalah ketika terbang secara manual oleh pilot, namun ketika terbang secara autopilot pesawat dituntut untuk mampu menjaga kestabilansikap sehingga mampu terbang menjalankan misinya dengan baik [5]. Salah satu faktor penting dalam mengendalikan kestabilan terbang adalah pengendalian sikap lateral.…”

Section: Pendahuluanunclassified

Pengendalian Sikap Lateral Pesawat Flying wing Menggunakan Metode LQR

Susanto

Ahdan

2020

protk

View full text Add to dashboard Cite

Unnamed Aerial Vehicle (UAV) technology of drone is widely used to carry out various mission such as photography, disaster monitoring, and area mapping. However, crash can be caused by environmental disturbances that hinders the completion of the mission. Moreover, an automatic control system is needed to handle this. In this study, the LQR control method is used to control the eleven and pitch angle so that the drone is able to maintain a stable lateral attitude. This control method has a fast and strong response in reaching a point of balance. Based on the test results, it show that the LQR control method applied is able to control the pitch angle and is able to make the drone maintain a lateral attitude, as evidenced by the disturbance at a pitch 20 ∘ the drone is able to maintain a lateral attitude with overshoot of 4.23 ∘ , risetime of 0,7 second, settling time of 1,2 second with a steady state error trend of 0,78 ∘

show abstract

“…The use of flight control strategies with disturbance resistance and higher efficiency has also received attention. At present, the flight control methods for drones mainly include linear control methods [8][9][10], nonlinear control methods [11][12][13], and intelligent control methods [14][15][16][17]. The learning-based robot control method has received widespread attention in the field of automatic control [18][19][20], as it ignores the dynamic model of the robot and learns control methods through a large amount of motion data.…”

Section: Introductionmentioning

confidence: 99%

A Supervised Reinforcement Learning Algorithm for Controlling Drone Hovering

Wu,

Yang,

Zhuo

et al. 2024

Drones

View full text Add to dashboard Cite

The application of drones carrying different devices for aerial hovering operations is becoming increasingly widespread, but currently there is very little research relying on reinforcement learning methods for hovering control, and it has not been implemented on physical machines. Drone’s behavior space regarding hover control is continuous and large-scale, making it difficult for basic algorithms and value-based reinforcement learning (RL) algorithms to have good results. In response to this issue, this article applies a watcher-actor-critic (WAC) algorithm to the drone’s hover control, which can quickly lock the exploration direction and achieve high robustness of the drone’s hover control while improving learning efficiency and reducing learning costs. This article first utilizes the actor-critic algorithm based on behavioral value Q (QAC) and the deep deterministic policy gradient algorithm (DDPG) for drone hover control learning. Subsequently, an actor-critic algorithm with an added watcher is proposed, in which the watcher uses a PID controller with parameters provided by a neural network as the dynamic monitor, transforming the learning process into supervised learning. Finally, this article uses a classic reinforcement learning environment library, Gym, and a current mainstream reinforcement learning framework, PARL, for simulation, and deploys the algorithm to a practical environment. A multi-sensor fusion strategy-based autonomous localization method for unmanned aerial vehicles is used for practical exercises. The simulation and experimental results show that the training episodes of WAC are reduced by 20% compared to the DDPG and 55% compared to the QAC, and the proposed algorithm has a higher learning efficiency, faster convergence speed, and smoother hovering effect compared to the QAC and DDPG.

show abstract

Kendali Adaptif Neuro Fuzzy PID untuk Kestabilan Terbang Fixed Wing UAV (Adaptive Control of Neuro Fuzzy PID for Fixed Wing UAV Flight Stability)

Cited by 8 publications

References 6 publications

Implementasi Kendali LQR Untuk Pengendalian Sikap Longitudinal Pesawat Flying Wing

Implementasi Kendali LQR Untuk Pengendalian Sikap Longitudinal Pesawat Flying Wing

Pengendalian Sikap Lateral Pesawat Flying wing Menggunakan Metode LQR

A Supervised Reinforcement Learning Algorithm for Controlling Drone Hovering

Contact Info

Product

Resources

About