Intelligent landing control system for civil aviation aircraft with dual fuzzy neural network

Xu, Kaijun; Zhang, Guangming; Xu, Yang

doi:10.1109/fskd.2011.6019520

Cited by 5 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The linear observer estimates the state vector e providing ê (estimation of the vector e ); the observer uses only the input vector:

z_{c} = \overset{y}{true} = {[\begin{matrix} center \\ center {\overset{y}{true}}_{1} & center {\overset{y}{true}}_{2} \end{matrix}]}^{T} = {[\begin{array}{c} center & c_{1} e_{1} & c_{2} \end{array} {bold-italice}_{2}]}^{T} = ([], \begin{array}{c} center & c_{1} & 0 \\ center & 0 & c_{2} \end{array}) bold-italice = \overset{C}{true} bold-italice

, with

C = ([], \begin{array}{c} center & c_{1} & 0_{1 \times 3} \\ center & 0_{1 \times 2} & c_{2} \end{array}), c_{1} = ([], \begin{array}{c} center & 1 & 0 & 0 \end{array})

c_{2} = ([], \begin{array}{c} center & 1 & 0 \end{array})

. The observer is modeled by the equations :

\overset{\overset{true^}{bold-italice}}{true} = \overset{A}{true} \overset{e}{true} + L ((), z_{c} - {\overset{true^}{z}}_{c}), z_{c} = C bold-italice, {\overset{true^}{z}}_{c} = C \overset{e}{true}

, or by the following equivalent one:

\overset{\overset{true^}{bold-italice}}{true} = \overset{A}{true} \overset{e}{true} + L z_{c}, \overset{A}{true}

…”

Section: The Design Of the Two Alssmentioning

confidence: 99%

“…To calculate the relative degrees r 1 and r 2 , we derive the first five differential scalar equations that result from model (8) and we eliminate _ δ p and _ δ T between the resulting equations and the two equations (7); then, choosing the output variables y 1 and y 2 , we remove all the states, other than y 1 and y 2 ; the highest degrees for the derivatives of y 1 and y 2 are r 1 and r 2 . For both structures in Fig.…”

Section: The Design Of the Two Alssmentioning

confidence: 99%

“…To study the functionality of the new ALSs, we consider a light aircraft (Charlie type) having dynamics (8) with coefficients [4]: a 11 ¼ À0:021; a 12 ¼ 0:122; a 13 ¼ 0; a 14 ¼ À9:69; a 21 ¼ À0:003; a 22 ¼ À0:7535; a 23 ¼ 1; a 24 ¼ 0; a 31 ¼ 0:000052; a 32 ¼ À0:24569; a 33 ¼ À0:213; a 34 ¼ 0;…”

Section: Numerical Simulation Setupmentioning

confidence: 99%

“…; also, for the aircraft trajectory's control during landing, the use of optimal control laws ( H 2 , H ∞ , H 2 / H ∞ ), together with full‐ or reduced‐order observers, provides good results . Unfortunately, in the presence of unknown or partially known nonlinearities associated with aircraft or compensators’ dynamics, the use of different adaptive control architectures such as those based on the dynamic inversion technique and neural networks (NNs), with or without Pseudo Control Hedging (PCH) blocks is needed. The adapting and the train of the NNs are based on the signals provided by the observers which receive information relative to the errors of the automatic control system (ACS).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Landing Auto‐Pilots for Aircraft Motion in Longitudinal Plane using Adaptive Control Laws Based on Neural Networks and Dynamic Inversion

Lungu

2016

Asian Journal of Control

View full text Add to dashboard Cite

This paper presents two new automatic landing systems (ALSs) for aircraft motion in longitudinal plane; the model of the landing geometry determines the flight trajectory and the aircraft calculated altitude; the flight trajectory during landing consists of two parts: the glide slope and the flare. Both designed ALSs have an adaptive system (ACS) for the aircraft output's control; for the first ALS, the output vector consists of the flying altitude and the longitudinal velocity, while, for the second ALS, the output variables are the pitch angle and the longitudinal velocity of aircraft. The second variant of ALS also contains an altitude controller providing the calculated pitch angle. The calculated altitude (for the first ALS), the calculated pitch angle (for the second ALS), and the desired flight velocity are provided to the ACS by means of a block consisting of two reference models. ACS is based on the dynamic inversion concept and contains an adaptive controller which includes a linear dynamic compensator, a state observer, a neural network, and a Pseudo Control Hedging block. The paper is focused both on the design of the two ALSs and on their complex software implementation and validation.

show abstract

“…The linear observer estimates the state vector e providing ê (estimation of the vector e ); the observer uses only the input vector: