Contribution to the Artifical Neural Network Speed Estimator in a Degraded Mode for Sensor-Less Fuzzy Direct Control of Torque Application Using Dual Stars Induction Machine

Abstract

Recently one of the major topic of research is the involvement of the intelligence artificial in the control system. This paper deals with application of a new combination between two-control strategy known as fuzzy direct control of torque and then an adaptive Neuronal Speed estimator utilizing dual starts induction motor. The research discussed consist to replace the switching table used in the conventional direct control method and adaptive mechanism of the classic MRAS estimator with fuzzy controller and new neural network accordingly, both strategies can manage the degraded and normal modes. The neural networks used are the back-propagation, to reduce the training patterns and increase the execution speed of the training process. As results we achieved can be summarised as follows: 1) <em>high degree</em> of reliability of speed estimation even with using only one start voltages and currents and parameters; 2) Minimization of the torque and flux ripples; and 3) Minimization of the current total harmonic distortion.

A Novel Neuroglial Architecture for Modelling Singular Perturbation System

“…This method is used for multi-time scale systems that can be reduced to the standard form of equation (3) by the determination of the parasitic term ε. Consider the state model of a linear system of dimension n:…”

“…This renders them useful for solving a variety of problems in pattern recognition, prediction, optimization and associative memory [1], [2]. Additionally, they are also being employed in system modeling and control [3], [4].…”

Low Speed Estimation of Sensorless DTC Induction Motor Drive Using MRAS with Neuro Fuzzy Adaptive Controller

“…In NFC, fuzzy system is trained by the neural network learning algorithm having expert human knowledge and learning ability. The hybrid learning algorithm of unsupervised and supervised methods is used to reduce the training time [16], [17], [19], [20]. The unsupervised learning generates the number of fuzzy sets, fuzzy rules, rules themselves and the centers and widths of the membership sets.…”