Journal Article10.1016/j.ast.2023.108228
Deep reinforcement learning method for turbofan engine acceleration optimization problem within full flight envelope
13
TL;DR: In this paper , a design method of aeroengine full-envelope acceleration controller based on deep reinforcement learning is proposed, where the flight envelope is divided into regions by clustering to reduce the span of data changes.
read more
About: This article is published in Aerospace Science and Technology. The article was published on 01 Mar 2023. The article focuses on the topics: Acceleration & Envelope (radar).
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Multi-variable anti-disturbance controller with state-dependent switching law for adaptive cycle engine
Xingyun Jia,Dengji Zhou +1 more
TL;DR: This paper proposes a multi-variable anti-disturbance controller with state-dependent switching law for adaptive cycle engines, improving robustness and thrust linearity by 20.02% and 0.096%, respectively, and reducing adjust time and overshoot by 11.91% and 9.98%.
6
Self-evolution direct thrust control for turbofan engine individuals based on reinforcement learning methods
Yiyang Zhu,Muxuan Pan,Wenxiang Zhou,Jinquan Huang +3 more
TL;DR: This paper proposes a self-evolution direct thrust control (SDTC) architecture for turbofan engines using reinforcement learning methods, addressing individual differences and performance degeneration through uncertainty-aware state prediction and online policy evolution.
6
A novel aeroengine real-time model for active stability control: compressor instabilities integration
Xinglong Zhang,Hanlin Sheng +1 more
TL;DR: A novel real-time aeroengine model integrates compressor instability into a classical component-level model, enabling effective active stability control, with simulation results showing accurate dynamic characteristics and real-time capabilities, suitable for instability detection and feedback control algorithms.
5
Development of a Predictive Tool for the Parametric Analysis of a Turbofan Engine
Z. Ahmed,Muhammad Sohail,Ali Javed,Raees Fida Swati +3 more
TL;DR: Parametric analysis of a turbofan engine using machine learning and deep learning models for performance prediction. A dataset was created using GasTurb 14 software, and various models were trained to predict performance metrics based on input parameters. The best model was selected based on root mean square error, and the results showed that machine learning and deep learning models offer an efficient alternative to intensive computational simulations.
2
Robust acceleration schedule design for gas turbine engine using multilayer perceptron network with adaptive sample class weighting
Kang Wang,Zengbu Liao,Maojun Xu,Ming Li,Bowen Duan,Jinxin Liu,Song Zhi-ping +6 more
1
References
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
67K
Technical Note : \cal Q -Learning
Chris Watkins,Peter Dayan +1 more
TL;DR: This paper presents and proves in detail a convergence theorem forQ-learning based on that outlined in Watkins (1989), showing that Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action- values are represented discretely.
Reinforcement learning: a survey
TL;DR: Central issues of reinforcement learning are discussed, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state.
•Proceedings Article
Continuous control with deep reinforcement learning
Timothy P. Lillicrap,Jonathan J. Hunt,Alexander Pritzel,Nicolas Heess,Tom Erez,Yuval Tassa,David Silver,Daan Wierstra +7 more
- 22 Jul 2016
TL;DR: In this paper, an actor-critic, model-free algorithm based on the deterministic policy gradient is proposed to operate over continuous action spaces, which is able to find policies whose performance is competitive with those found by a planning algorithm with full access to the dynamics of the domain.
6.5K
An Introduction to Deep Reinforcement Learning
TL;DR: This manuscript provides an introduction to deep reinforcement learning models, algorithms and techniques and particular focus is on the aspects related to generalization and how deep RL can be used for practical applications.