Sevil Ahmed

Sliding mode incremental learning algorithm for interval type-2 Takagi–Sugeno–Kang fuzzy neural networks

Type-2 fuzzy logic systems are an area of growing interest over the last years. The ability to model uncertainties and to perform under noisy conditions in a better way than type-1 fuzzy logic systems increases their applicability. A new stable on-line learning algorithm for interval type-2 Takagi–Sugeno–Kang (TSK) fuzzy neural networks is proposed in this paper. Differently from the other recently proposed variable structure system theory-based on-line learning approaches for the type-2 TSK fuzzy neural nets, where the adopted consequent part of the fuzzy rules consists solely of a constant, the developed algorithm applies the complete structure of the Takagi–Sugeno type fuzzy if–then rule base (i.e. first order instead of zero order output function is implemented). In addition it is able to adapt the existing relation between the lower and the upper membership functions of the type-2 fuzzy systems. This allows managing of non-uniform uncertainties. Simulation results from the identification of a nonlinear system with uncertainties and a non-bounded-input bounded-output nonlinear plant with added output noise have demonstrated the better performance of the proposed algorithm in comparison with the previously reported in the literature sliding mode on-line learning algorithms for both type-1 and type-2 fuzzy neural structures.

Neural net tracking control of a mobile platform in robotized wireless sensor networks

In the recent years sensor networks have emerged as an effective tool for monitoring environments that are large in size and have complex topology. They have been successfully applied to solve various problems such as monitoring of different environmental indicators, detection of floods and fires, temperature control in office buildings, to collect information about the health status of hospitalized patients, to monitor the activity of some species and many others. Based-on the wireless communications the unification of the sensor modules can be implemented as a wireless sensor network (WSN). A newly observed trend is the inclusion of mobile robots into the WSN structure. The present paper describes a work-in-progress aiming to build laboratory prototype of a robotized hybrid WSN. The latter can be used for various distributed control experiments over the network structure and its efficiency. A robotized wireless sensor node has been designed and its functionality has been experimentally tested using an advanced trajectory tracking control algorithm. The proposed robotic node consists itself of a mobile robot platform integrated with a wireless sensor node. The latter has been implemented with a Tiva C Series TM4C1294NCPDT LaunchPad evaluation board equipped with TI Sensor Hub and WiFi Booster Pack. The mobile robot platform is based on the iRobot Create additionally upgraded with an on-board control system built in with gumstix verdex pro XL6P embedded microprocessor.

Implementations of a Hammerstein fuzzy-neural model for predictive control of a lyophilization plant

This paper describes two methodologies for implementation of Hammerstein model by using different input-output representations into model predictive control schemes. The model nonlinearity is easily approximated using a simple Takagi-Sugeno inference, while the linear parts are flexibly introduced. As optimization procedures for predictive control are used a standard gradient optimization method and an implementation of Hildreth Quadratic Programming. A comparison between the proposed control strategies is made by simulation experiments for control of nonlinear lyophilization plant.

Trajectory control of manipulators using type-2 fuzzy neural friction and disturbance compensator

An incrementally tuned interval type-2 Takagi-Sugeno-Kang (TSK) fuzzy neural network implementing fuzzy if-then rule base with first order output functions is proposed for compensation of friction and disturbance effects during the trajectory tracking control of rigid robot manipulators. Friction and disturbances have an important influence on the robot manipulator dynamics. They are highly nonlinear terms that cannot be easily modeled. The proposed intelligent compensator makes use of a newly developed stable Variable Structure Systems theory-based on-line learning algorithm that is also able to adapt the existing relation between the lower and the upper membership functions of the type-2 fuzzy system. This allows managing of non-uniform uncertainties. Simulation results from the trajectory tracking control of two degrees of freedom RR planar robot manipulator using feedback linearization techniques and the proposed adaptive interval type-2 fuzzy neural compensator have shown that the joint positions are well controlled under wide variation of operation conditions and existing uncertainties.

An extended sliding mode learning algorithm for type-2 fuzzy neural networks

Type-2 fuzzy logic systems are an area of growing interest over the last years. The ability to model uncertainties in a better way than type-1 fuzzy logic systems increases their applicability. A new stable on-line learning algorithm for type-2 fuzzy neural networks is proposed in this paper. It can be considered as an extended version of the recently developed on-line learning approaches for type-2 fuzzy neural networks based on the Variable Structure System theory concepts. Simulation results from the identification of a nonlinear system with uncertainties have demonstrated the better performance of the proposed extended algorithm in comparison with the previously reported in the literature sliding mode learning algorithms for both type-1 and type-2 fuzzy neural structures.

Industrial implementation of a fuzzy logic controller for brushless DC motor drives using the PicoMotion control framework

Modern industry requires an improved motor performance and the permanent magnet brushless DC (BLDC) motors are especially appropriate for applications that require a high level of accuracy and performance. The advanced control strategies when applied into BLDC motor drive systems may further enhance their performance. However, these methods are relatively complex and computationally intensive, which may hamper the implementation. Fuzzy logic control algorithm has been developed in this investigation and embedded into a commercially available motion control system for the position control of BLDC motors. BLDC motor drives offered by PicoMotion Inc. and Motion Control Framework software platform have been selected for the experiments due to their compactness, flexibility and the open hardware and software concept they have been created upon. The obtained comparative results with respect to the built in PI control law have confirmed that the implementation of more advanced control strategies on inexpensive hardware and software platforms, nowadays available on the market for the control of BLDC motors, can be practically feasible and can enhance their performance.

Fuzzy-neural predictive control using Levenberg-Marquardt optimization approach

It is proposed in this paper a study on the influence of the Levenberg-Marquardt optimization approach for computation of the control actions in Nonlinear Model Predictive Controller. To predict the future plant behavior, a classical Takagi-Sugeno inference is used. A comparison by applying the Gradient descent and the Newton-Raphson optimization approaches is made. The efficiency of the proposed optimization strategies is demonstrated by experiments in MATLAB environment to control a Continuous Stirred Tank Reactor.

Parallel distributed neuro-fuzzy model predictive controller applied to a hydro turbine generator

Model predictive control (MPC) has been considered as the most important development in the area of process control in the last two decades. This paper addresses the issue of controlling a nonlinear plant by the use of the nonlinear model predictive control formulation. To handle the nonlinearities, a Takagi-Sugeno neuro-fuzzy model is suggested as a means to model the plant with nonlinearities depending on the operating region. The developed model is used as a predictive model for a parallel distributed model predictive control algorithm. In this paper, the parallel distributed neuro-fuzzy model predictive controller has been proposed to control a non-linear control system of a hydro turbine generator. The proposed technique has been tested and evaluated using this simulated industrial plant.

A robotized wireless sensor network based on MQTT cloud computing

The possibility to use the Message Queue Telemetry Transport (MQTT) protocol-based cloud platform for collecting information from and transmitting remote control commands to the laboratory prototype of a robotized wireless sensor network has been investigated. The obtained experimental results with the designed communication have demonstrated the data transmission performance of the network sensor nodes. The proposed concept of a cloud-based wireless sensor network permits to deploy it to any required place with a single requirement that the system should be able to connect to the internet.

Control of the flight of a small quadrotor using gestural interface

A new approach using gestures and visual computing techniques to control unmanned aerial vehicles is presented. The goal is to control automatically and in semi-autonomous mode the flight of a quad-rotor rotorcraft in indoor environments characterized with the absence of possibility to receive GPS data. Human operator can control the implementation of various maneuvers during the flight of the rotorcraft via specific gestures and body postures. In this way a more-effective interface with the controlled aerial robot is created. For its practical implementation a Parrot AR. Drone quadrotor and a Microsoft Kinect sensor have been used.