In this paper deep neural networks are proposed to diagnose inter-turn short-circuits of induction motor stator windings operating under the Direct Field Oriented Control method. A convolutional neural network (CNN), trained with a Stochastic Gradient Descent with Momentum method is used. This kind of deep-trained neural network allows to significantly accelerate the diagnostic process compared to the traditional methods based on the Fast Fourier Transform as well as it does not require stationary operating conditions. To assess the effectiveness of the applied CNN-based detectors, the tests were carried out for variable load conditions and different values of the supply voltage frequency. Experimental results of the proposed induction motor fault detection system are presented and discussed.
Conventional field-orientated Induction motor drives operate at rated flux even at low load. To improve the efficiency of the existing motor it is important to regulate the flux of the motor in the desired operating range. In this paper a loss model controller (LMC) based on the real coded genetic algorithm is proposed, it has the straightforward goal of maximizing the efficiency for each given load torque. In order to give more accuracy to the motor model and the LMC a series model of the motor which consider the iron losses as a resistance connected in series with the mutual inductance is considered. Digital computer simulation demonstrates the effectiveness of the proposed algorithm and also simulation results have confirmed that this algorithm yields the optimal efficiency.
The paper presents the mathematical model of an autonomous induction generator with the AC load circuit and the converter control system of the voltage magnitude at the terminals of stator generator. The control algorithm and the structure of the control system are described. The simulation results of the control system are presented and discussed.
The mathematical model of the five-phase squirrel-cage induction motor and the system of the dual five-phase voltage source inverter have been presented. The control methods and control systems of the field-oriented control of the five-phase induction motor with an open-end stator winding are described. The structures of the direct fieldoriented control system (DFOC) and the Indirect Field-oriented control system (IFOC) with PI controllers in outer and inner control loops are analyzed. A method of space vector modulation used to control the system of the dual five-phase voltage source inverter has been discussed. The results of simulation studies of the field-oriented control methods are presented. Comparative analysis of the simulation results was carried out.
The paper presents a solution for sensorless field oriented control (FOC) system for five-phase induction motors with improved rotor flux pattern. In order to obtain the advantages of a third harmonic injection with a quasi-trapezoidal flux shape, two vector models, α1–β1 and α3–β3, were transformed into d1–q1, d3–q3 rotating frames, which correlate to the 1st and 3rd harmonic plane respectively. A linearization approach of the dual machine model in d–q coordinate frames is proposed by introducing a new additional variable “x” which is proportional to the electromagnetic torque. By applying the static feedback control law, a dual mathematical model of the five-phase induction motor was linearized to synthesize a control system in which the electromagnetic torque and the rotor flux can be independently controlled. The results shows the air gap flux shape in steady as well transient states under various load conditions. Moreover, the implemented control structure acquires fault tolerant properties and leads to possible emergency running with limited operation capabilities. The fault-tolerant capability of the analyzed machine was guaranteed by a special implemented control system with a dedicated speed observer, which is insensitive to open-phase fault situation. The experimental tests have been performed with single and double-open stator phase fault. A torque measurement was implemented to present the mechanical characteristics under healthy and faulty conditions of the drive system.
The paper presents the analysis of different fault states in drive systems with multiphase induction motors. The mathematical models of a five-phase and six-phase induction motor and the MRASCC estimator have been presented and the description of the Space Vector Modulation has been shown. The Direct Field-Oriented Control (DFOC) system is analyzed. Results of the simulation and experimental studies of the Direct Field-Oriented Control systems in the fault conditions are presented. The author’s original contribution includes analysis and studies of the DFOC control method of a five-phase induction motor resistant to the motor speed sensor fault with the use of the MRASCC estimator.