Browsing by Author "Lewis, D. J. G."

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    The application of neural networks to spacecraft control
    (1994-08) Cooper, A.; Lewis, D. J. G.
    This thesis investigates how two neural network-based control techniques can be applied to a specific spacecraft control problem. The neural networks used are simple backpropagation networks, consisting of one or more tansigmoidal neurons (neurons with tanh transfer functions) in a hidden layer, and a linear neuron in the output layer. The neural network control techniques investigated here are Direct Model Inversion and Indirect Model Inversion. The spacecraft control problem is that of reducing the vibrations of a spacecraft payload. The source of the vibrations is a mass imbalance in one of the reaction wheels of the spacecraft. Four components are represented in the spacecraft model. These are rigid body inertia, solar array flexure, fuel slosh and payload vibration. A simple sinusoidal signal is used to model the disturbance torque produced by the reaction wheel mass imbalance. The complete model is broadly based on the Solar Heliospheric Observatory (SOHO) that is due for launch in 1995. Each of the neural network control techniques used is shown to be successful in reducing the effects of the disturbance torques on the spacecraft payload. However, in each case, a simple positional feedback gain term provides more effective and reliable control.
  • No Thumbnail Available
    ItemOpen Access
    The design of a fuzzy logic system for control of an unmanned aircraft
    (Cranfield University, 1996-05) Assuncao, J. M. V.; Lewis, D. J. G.
    Many control problems are based on control objectives easily quantified and consequently realisable by standard control synthesis methods. When an unmanned aircraft navigates, it moves inside a complex environment due to interactions with its surrounding and time varying environmental conditions. Several causes of perturbations have been identified as for example gusts and corrupted information of position. The characteristics of possible missions carried out by the un manned aircraft leads to the desire to construct navigation control systems which when operated in perturbed environments combine the advantages of smooth control with accurate navigation. Rule based, and adaptive controllers have favourable properties for such systems. This thesis investigates the use of a rule based navigation controller for a particular unmanned aircraft, the XRAEl aircraft. To achieve this objective several different types of fuzzy logic controllers are analysed as for example conventional and direct and indirect adaptive fuzzy controllers. They are designed by employing simple control engineering knowledge and subsequently validated using a stability method. For this purpose diverse stability methods are described and a new technique presented, the fuzzy root locus method, which is also based on the introduction of a new concept for fuzzy logic controllers, the fuzzy cell. The realisation of this work has been achieved by a series of simulation tests employing different processes and a simulation model of the XRAEl aircraft. The conclusions drawn from the results of the experiments consider in general that a rule based controller can improve the quality of navigation when compared to conventional controllers.