لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
هشتمین کنفرانس بین المللی کنترل ، ابزار دقیق و اتوماسیون
Using Deep Learning Network for Fault Detection in UAV
نویسندگان :
Armin Mahdi Erfanian
1
Amin Ramezani
2
1- دانشگاه تربیت مدرس
2- دانشگاه تربیت مدرس
کلمات کلیدی :
UAV, Quadrotor, Fault detection, BLSTM, Deep learning.
چکیده :
Unmanned aerial vehicles (UAV), especially quadrotors, have received much attention in recent years. The most important challenge in a drone system is fault detection. therefore, in this article, we used the Long short-term memory algorithm (LSTM) to detect faults. in other words we were able to detect the actuator fault of quadrotor using LSTM algorithm, used in the field of deep learning. In this research, we first simulated the quadrotor model using PID controller and then extracted the data and through this we were able to train the network and eventually detect the fault by collecting data from various state variables and inputs at different frequencies and amplitudes. The simulation results show this method can be effective in detecting faults in quadrotor and its accuracy reaches 99%.
لیست مقالات
لیست مقالات بایگانی شده
Adaptive Optimal Control of Chaotic System Using Backstepping Neural Network Concept
Mohammad Sarbaz - MohammadReza Soltanian - Mohammad Manthouri - Iman Zamani
Enhancing Fault Detection in Induction Motors using LSTM-Attention Neural Networks
Mohammad Ali Labbaf Khaniki - Marzieh Mirzaeibonehkhater - Mohammad Manthouri
Artificial Potential Field-Based Obstacle Avoidance Integrated with a Dual-Loop GA-Optimized PID Feedback Control of a Mobile Robot
Mohammad Bagher Sajjadi - Ali Anisi - Moosa Ayati
کنترل مقاوم سیستمهای سوئیچشونده خطی نامعین با کلیدزنی غیرهمزمان جامع در حضور اغتشاش
علی نصراللهی - علی اکبر افضلیان
Robust Data-Driven QFT Synthesis in the Presence of High Uncertainty
Mahdi Sadigh Dallali - Ali Khaki Sedigh
A New SDP-Based Estimation Framework for Predicting Chaotic Time Series
Abbas-Ali Zamani
Identification of Solar Panel Conditions Using Fully Decentralized Federated Learning
Keyvan Kazemi
Continuous Wavelet Transformation and VGG16 Deep Neural Network for Stress Classification in PPG Signals
Yasin Hasanpoor - Bahram Tarvirdizadeh - Khalil Alipour - Mohammad Ghamari
Multi-Derivative Portfolio Management with Data-Driven Nonlinear Stochastic Control Policies in Retail Energy Markets
Mahdi Rezaei Bahrmand - Hamid Khaloozadeh
Selection of Least Error Wavelet Function for Typical Fault Diagnosis in HVDC Transmission System
Reza Tarighi - Mohammad Hosein Kazemi - Esmail Zarezadeh
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.9.5