Search

To remove the funitional payload variation, the attitude oscillation and trajectory tracking error of civil UAV in complex environment, a combined inner and outer control strategy for the civil UAV is designed based on the interval system control theory and dynamic tracking error minimization principle, which can guarantee the attitude stabilization in inner loop and the heading tracking in outer loop, thus solving the control effect deterioration and trajectory error drawback of the existing UAV with large scale model variation. The simulation results show that, the proposed combined control strategy can keep flight state's stabilization and effective trajectory tracking with good closed-loop robustness. This study is useful to develop effective and automatic civil UAV system's flight control strategy.

Fuzzy logic, neural networks are two popular artificial intelligence techniques that are widely used in many applications. Due to their distinct properties and advantages, they are currently being investigated and integrated to form new models or strategies in the areas of system control. This paper presents an adjustment strategy for a dynamic tracking neuro-fuzzy controller (DTNC) for steady-state control in complex system. In this method, DTNC consists of two neural network composed of the same structure, one for control, one for learning. Strategies to adjust the DTNC in accordance with the environment dynamics are automatically generated in off-line manner in learning neural network. The generated strategies are stored in a neural network and with the changes of the external environment parameters, the learning part used for adjusting the DTNC in on-line. The other neural network has to be regarded as controller, and now tuned into a learning part. Therefore, the DTNC is automatically adjusted in accordance with the dynamics of complex environment using the generated strategies which are stored in two neural networks.

A novel dual fuzzy neural network to civil aviation aircraft disturbance landing control is presented in this paper. Conventional automatic landing system (ALS) can provide a smooth landing, which is essential to the comfort of passengers. However, these systems work only within a specified operational safety envelope. When the conditions are beyond the envelope, such as turbulence or wind shear, they often cannot be used. The objective of this paper is to investigate the use of dual fuzzy neural network in ALS and to make that system more intelligent. Firstly the dual fuzzy neural network is trained from available flight data and then that trained neural network controls the landing, roll, pitch and altitude hold of the airplane. Current flight control law is adopted in the intelligent controller design. Tracking performance and robustness are demonstrated through software simulations. The neural network control has been implemented in MATLAB and the data for training have been taken from Flight Gear Simulator. Simulated results show that control for different flight phases is successful and the dual fuzzy neural network controllers provide the robustness to system parameter variation.

This paper presents the aircraft intelligent landing system with dynamic neuro-fuzzy controller that enhances the fault tolerant capabilities of a high performance civil aviation aircraft during the landing phase when subjected to severe winds and failures such as stuck control surfaces. The controller proposed in this paper is comprised of a fuzzy logic controller (FLC) in the feedback configuration and two dynamic neural networks in the forward path. A dynamic control network (DCN) is used to control the intelligent landing system, and a dynamic learning network (DLN) is employed to learn the weighting factor of the fuzzy logic. It is envisaged that the integration of fuzzy logic and neural network based-controller will encompass the merits of both technologies, and thus provide a robust controller for the intelligent landing system. The fuzzy logic controller, based on fuzzy set theory, provides a means for converting a linguistic control strategy into control action and offering a high level of computation. This design is carried out for no failure conditions but with the aircraft being subjected to winds. Simulation studies indicate that the designed conventional controller has only a limited failure handling ability. However, neural controller augmentation considerably improves the ability to handle large faults and meet the strict touchdown dispersion requirements, thus enlarging the fault-tolerance envelope.

This paper presents the intelligent landing control system that overcome wind disturbance problem of a civil aviation aircraft during the landing phase when subjected to severe winds and failures such as stuck control surfaces. The controller architecture uses a dual fuzzy neural network (DFNN) controller, which is capable of implementing fuzzy inference in general and neural network mechanism in particular. A systematic method for mapping an existing rule base into a set of dual fuzzy neural network weights has also been presented. However, in order to utilize this method to initialize the dual fuzzy neural network weights, such a rule base obtained from domain experts or from experimental data through systematic, knowledge acquisition methods has been proposed. It uses one neural network as on-line learning and does not need a priori training. Simulations show that it improved the performance of conventional automatic landing system (ALS) and guide the aircraft to a safe landing.

An intelligent landing system design using dual fuzzy neural network is proposed for research aircraft similar in configuration to civil aviation aircraft. The control law to track the pitch rate command is developed based on system theory. The controller architecture uses two fuzzy neural networks, which is capable of implementing fuzzy inference in general and neural network mechanism in particular. Neural network 1 with linear filters and back propagation through time learning algorithm is used to approximate the control law as system control part. The bounded signal requirement to develop the neural controller is circumvented using an off-line finite time training scheme in neural network 2 as system learning part, which provides the necessary stability and tracking performances. On-line learning scheme is implemented to compensate for uncertainties due to variation in aerodynamic coefficients, control surface failures and also variations in center of gravity position. The performance of the proposed control scheme is validated at different flight conditions. The disturbance rejection capability of the neural controller is analyzed in the presence of the realistic gust and sensor noises.

This paper presents the dynamic neuro-fuzzy control system for controlling the intelligent transportation system. The controller proposed in this paper is comprised two dynamic neural networks and a system identifier. The system identifier is used to identify the output of the adaptive cruise control system, and one of the dynamic neural networks is employed to learn the weighting factor of the fuzzy logic neural network, the other is control the vehicle system. When the control strategy is not suit for vehicle, identifier will select the best model to be the controller.

It is difficult to realize dynamic control for some complex nonlinear processes which are operated in different environments and when operation conditions are changed frequently. In this paper we propose an identifier-based control method in dynamic tracking neuro-fuzzy control system. The dynamic tracking neuro-fuzzy control (DTNFC) system is comprised of two neural networks and a system identification network. The system identification network is used to identify the output of the manipulator system, and one of the dynamic neural networks is employed to learn the weighting factor of the fuzzy logic neural network, the other is control the manipulator system. The identifier combines two parts: performance index and selector. A hysteresis switching algorithm is applied to select the best model.

This paper presents the dynamic neuro-fuzzy control system for controlling a gas-fired water heater. The controller proposed in this paper is comprised of a fuzzy logic controller (FLC) in the feedback configuration and two dynamic neural networks in the forward path. A dynamic identification network (DIN) is used to identify the output of the manipulator system, and a dynamic learning network (DLN) is employed to learn the weighting factor of the fuzzy logic. It is envisaged that the integration of fuzzy logic and neural network based-controller will encompass the merits of both technologies, and thus provide a robust controller for the gas-fired water heater system. The fuzzy logic controller, based on fuzzy set theory, provides a means for converting a linguistic control strategy into control action and offering a high level of computation. On the other hand, the ability of a dynamic network structure to model an arbitrary dynamic nonlinear system is incorporated to approximate the unknown nonlinear input-output relationship using a dynamic back propagation learning algorithm.

This paper presents a design method of adaptive fuzzy controllers using dual-fuzzy neural networks (DFNNs). For the convenience of adaptive control, the structure of the two-fuzzy neural-network controller is divided into two parts. Each part is a fuzzy neural-network (FNN). The adaptive controller uses two FNNs. One FNN is used to identify a fuzzy model of controlled object. The fuzzy control rule is designed with the linguistic rules of the fuzzy model and is incorporated into the other FNN. Simulations using a controlled object with an non-monotonic input-output characteristics are done to verify the proposed design method.

During the last decade, there has been increased use of neural networks (NNs), fuzzy logic (FL) and genetic algorithms (GAs) in artificial intelligence (AI). Since these three methods are complementary rather than competitive, a better performance model which has combined GAs, FL and NNs comes into being gradually. This paper presents genetic-fuzzy-neuro (GF-N) model to design the dual-fuzzy neural-networks (DFNNs) controller. For the convenience of adaptive control, the structure of the two-fuzzy neural-network controller is divided into two parts. Each part is a fuzzy neural-network (FNN). The adaptive controller uses two FNNs. One FNN is used to identify a fuzzy model of controlled object. The other is onlinetracking learning the suitable control policy.