In this paper, we derive and prove the stability bounds of the momentum coefficient µ and the learning rate ? of the back propagation updating rule in Artificial Neural Networks .The theoretical upper bound of learning rate ? is derived and its practical approximation is obtained

Artificial Neural Networks (ANN) is one of the important statistical methods that are widely used in a range of applications in various fields, which simulates the work of the human brain in terms of receiving a signal, processing data in a human cell and sending to the next cell. It is a system consisting of a number of modules (layers) linked together (input, hidden, output). A comparison was made between three types of neural networks (Feed Forward Neural Network (FFNN), Back propagation network (BPL), Recurrent Neural Network (RNN). he study found that the lowest false prediction rate was for the recurrentt network architecture and using the Data on graduate students at the College of Administration and Economics, Univer

The physical substance at high energy level with specific circumstances; tend to behave harsh and complicated, meanwhile, sustaining equilibrium or non-equilibrium thermodynamic of the system. Measurement of the temperature by ordinary techniques in these cases is not applicable at all. Likewise, there is a need to apply mathematical models in numerous critical applications to measure the temperature accurately at an atomic level of the matter. Those mathematical models follow statistical rules with different distribution approaches of quantities energy of the system. However, these approaches have functional effects at microscopic and macroscopic levels of that system. Therefore, this research study represents an innovative of a wi

Lowering the emission, fuel economy and torque management are the essential
requirements in the recent development in the automobile industry. The main engine control
input that satisfies the above requirements is the throttling angle which adjusts the air mass
flow rate to the engine port. Due to the uncertainty and the presence of the nonlinear
components in its dynamical model, the sliding mode control theory is utilized in this work
for the throttle valve angle control system to design a robust controller for this system in the
presence of a nonlinear spring and Coulomb friction. A continuous sliding mode control law
which consists of a saturation function, instead of a signum function, and the integral of
ano

This paper proposes a new structure for a Fractional Order Sliding Mode Controller (FOSMC) to control a Twin Rotor Aerodynamic System (TRAS). The new structure is composed by defining two 3-dimensional sliding mode surfaces for the TRAS model and introducing fractional order derivative integral in the state variables as well as in the control action. The parameters of the controller are determined so as to minimize the Integral of Time multiplied by Absolute Error (ITAE) performance index. Through comparison, this controller outperforms its integer counterpart in many specifications, such as reducing the delay time, rise time, percentage overshoot, settling time, time to reach the sliding surface, and amplitude of chattering in control inpu

In this paper, first and second order sliding mode controllers are designed for a single link robotic arm actuated by two Pneumatic Artificial Muscles (PAMs). A new mathematical model for the arm has been developed based on the model of large scale pneumatic muscle actuator model. Uncertainty in parameters has been presented and tested for the two controllers. The simulation results of the second-order sliding mode controller proves to have a low tracking error and chattering effect as compared to the first order one. The verification has been done by using MATLAB and Simulink software.

The aim of this paper is to approximate multidimensional functions by using the type of Feedforward neural networks (FFNNs) which is called Greedy radial basis function neural networks (GRBFNNs). Also, we introduce a modification to the greedy algorithm which is used to train the greedy radial basis function neural networks. An error bound are introduced in Sobolev space. Finally, a comparison was made between the three algorithms (modified greedy algorithm, Backpropagation algorithm and the result is published in [16]).

The objective of an Optimal Power Flow (OPF) algorithm is to find steady state operation point which minimizes generation cost, loss etc. while maintaining an acceptable system performance in terms of limits on generators real and reactive powers, line flow limits etc. The OPF solution includes an objective function. A common objective function concerns the active power generation cost. A Linear programming method is proposed to solve the OPF problem. The Linear Programming (LP) approach transforms the nonlinear optimization problem into an iterative algorithm that in each iteration solves a linear optimization problem resulting from linearization both the objective function and constrains. A computer program, written in MATLAB environme

L1 adaptive controller has proven to provide fast adaptation with guaranteed transients in a large variety of systems. It is commonly used for controlling systems with uncertain time-varying unknown parameters. The effectiveness of  L1 adaptive controller for position control of single axis has been examined and compared with Model Reference Adaptive Controller (MRAC). The Linear servo motor is one of the main constituting elements of the x-y table which is mostly used in automation application. It is characterized by time-varying friction and disturbance.

    The tracking and steady state performances of both controllers have been assessed fo