• The Transactions of the Korea Information Processing Society
• /
• v.4 no.9
• /
• pp.2299-2308
• /
• 1997

While most machine learning research has been primarily concerned with the development of systems that implement one type of learning strategy, we use a multistrategy approach which integrates rule induction learning and instance-based learning, and show how this marriage allows for overall better performance. In the rule induction learning phase, we derive an entropy function, based on Hellinger divergence, which can measure the amount of information each inductive rule contains, and show how well the Hellinger divergence measures the importance of each rule. We also propose some heuristics to reduce the computational complexity by analyzing the characteristics of the Hellinger measure. In the instance-based learning phase, we improve the current instance-based learning method in a number of ways. The system has been implemented and tested on a number of well-known machine learning data sets. The performance of the system has been compared with that of other classification learning technique.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.1
• /
• pp.271-279
• /
• 2015

Induction cooking application with multiple loads need high power inverters and appropriate control techniques. This paper proposes an inverter configuration with buck-boost converter for multiple load induction cooking application with independent control of each load. It uses one half-bridge for each load. For a given dc supply of $V_{DC}$, one more $V_{DC}$ is derived using buck-boost converter giving $2V_{DC}$ as the input to each half-bridge inverter. Series resonant loads are connected between the centre point of $2V_{DC}$ and each half-bridge. The output voltage across each load is like that of a full-bridge inverter. In the proposed configuration, half of the output power is supplied to each load directly from the source and remaining half of the output power is supplied to each load through buck-boost converter. With buck-boost converter, each half-bridge inverter output power is increased to a full-bridge inverter output power level. Each half-bridge is operated with constant and same switching frequency with asymmetrical duty cycle (ADC) control technique. By ADC, output power of each load is independently controlled. This configuration also offers reduced component count. The proposed inverter configuration is simulated and experimentally verified with two loads. Simulation and experimental results are in good agreement. This configuration can be extended to multiple loads.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2007.11a
• /
• pp.307-312
• /
• 2007

The paper is proposed artificial neural network(ANN) sensorless control of induction motor drive with fuzzy learning control-fuzzy neural network(FLC-FNN) controller. The hybrid combination of neural network and fuzzy control will produce a powerful representation flexibility and numerical processing capability. Also, this paper is proposed speed control of induction motor using FLC-FNN and estimation of speed using ANN controller The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The error between the desired state variable and the actual one is back-propagated to adjust the rotor speed, so that the actual state variable will coincide with the desired one. The proposed control algorithm is applied to induction motor drive system controlled FLC-FNN and ANN controller, Also, this paper is proposed the analysis results to verify the effectiveness of the FLC-FNN and ANN controller.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.25 no.4
• /
• pp.45-56
• /
• 2011

This paper is proposed artificial neural network(ANN) rotor resistance estimation of induction motor drive controlled by multi-adaptive fuzzy learning controller(AFLC). A simple double layer feedforward ANN trained by the back-propagation technique is employed in the rotor resistance identification. In this estimator, double models of the state variable estimations are used; one provides the actual induction motor output states and the other gives the ANN model output states. The total error between the desired and actual state variables is then back propagated to adjust the weights of the ANN model, so that the output of this model tracks the actual output. When the training is completed, the weights of the ANN correspond to the parameters in the actual motor. The estimation and control performance of ANN and multi-AFLC is evaluated by analysis for various operating conditions. Also, this paper is proposed the analysis results to verify the effectiveness of this controller.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2005.05a
• /
• pp.47-50
• /
• 2005

In this paper, we investigate a filtering technique to reduce the adverse effect of long motor leads on H-bridge cascaded 7-level inverter fed ac motor drive. The switching surge voltage becomes the major cause to occur the insulation failure by serious voltage stress in the stator winding of high voltage induction motor. However, the effect of switching surge appears un seriousin high voltage induction motor than low voltage induction motor. Consequently, we demonstrated that the filter connected to the motor terminals greatly reduces the transient voltage stress and ringing, moreover we show lowers the dv/dt of the inverter switching pulse. The results of simulation show the suppression of dv/dt and the reduced peak voltage at the motor end of a long cable.

• Journal of Electrical Engineering and Technology
• /
• v.3 no.1
• /
• pp.79-87
• /
• 2008

This paper proposes the design and implementation of a direct torque controlled induction motor drive system. The method is based on control of decoupling between amplitude and angle of reference stator flux for determining reference stator voltage vector in generating PWM output voltage for induction motors. The objective is to reduce electromagnetic torque ripple and stator flux droop which result in a decrease in current distortion in steady state condition. In addition, the proposed technique provides simplicity of a control system. The direct torque control is based on the relationship between instantaneous slip angular frequency and rotor angular frequency in adjustment of the reference stator flux angle. The amplitude of the reference stator flux is always kept constant at rated value. Experimental results are illustrated in this paper confirming the capability of the proposed system in regards to such issues as torque and stator flux response, stator phase current distortion both in dynamic and steady state with load variation, and low speed operation.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.1
• /
• pp.57-64
• /
• 2006

This paper is proposed for a artificial neural network(ANN) sensorless control based on the vector controlled induction motor drive, or proposes a adaptive fuzzy teaming control(AFLC). The fuzzy logic principle is first utilized for the control rotor speed. AFLC scheme is then proposed in which the adaptation mechanism is executed using fuzzy logic. Also, this paper is proposed for a method of the estimation of speed of induction motor using ANN Controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The error between the desired state variable and the actual one is back-propagated to adjust the rotor speed, so that the actual state variable coincide with the desired one. The back propagation mechanism is easy to derive and the estimated speed tracks precisely the actual motor speed. This paper is proposed the analysis results to verify the effectiveness of the new method.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.3
• /
• pp.27-34
• /
• 2007

The rotor faults of induction motors may cause bad effects on the performance of the induction motor. This paper proposes the detecting technique of these faults by analyzing the waveform of the induced current and voltage of search coil using numerical analysis and the experiment. Several defective rotor bars are simulated to analyze the fault conditions-broken bars and high resistance of rotor bars. In order to prove the usefulness of the proposed method, we made an prototype experimental apparatus. The waveform of the induced voltages in search coil has the obvious characteristics and it is easy to differentiate the normal rotor from the abnormal one. The experimental results show that the proposed method is useful to detect the rotor fault conditions.

• Journal of Power Electronics
• /
• v.9 no.3
• /
• pp.343-353
• /
• 2009

In this paper, a nonlinear controller is proposed for Doubly-Fed Induction Machine (DFIM) drives. The nonlinear controller is designed based on an adaptive backstepping control technique, using a fifth order model of an induction machine in the synchronous d & q axis rotating reference frame, whose d axis coincides with the space voltage vector of the main AC supply, and using the rotor current and stator flux components as state variables. The nonlinear controller can perfectly track the torque reference signal measured in the stator terminals under the condition of unity power factor regulation, in spite of the stator and rotor resistance variations. In order to make the drive system capable of operating in the motoring and generating modes below and above the synchronous speed, two level Space-Vector PWM (SV-PWM) back-to-back voltage source inverters are employed in the rotor circuit. It is confirmed through computer simulation results that the proposed control approach is effective and valid.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.54 no.3
• /
• pp.154-161
• /
• 2005

This paper proposes a speed-sensorless induction motor control system using a rotor speed compensation. To explain the proposed system, this paper describes an induction motor model in the synchronous reference frame for the vector control. The rotor flux is estimated by the rotor flux observer using the reduced-dimensional state estimator technique. The estimated rotor speed is directly obtained from the electrical frequency, the slip frequency, and the rotor speed compensation with the estimated q-axis rotor flux. The error of the rotor time constant is indirectly reflected in the rotor speed compensation using the compensation of the flux error angle. To precisely estimate the rotor flux, the actual value of the stator resistance, whose actual variation is reflected, is derived. An implementation of pulse-width modulation (PWM) pulses using an effective space vector modulation (SVM) is briefly mentioned. For fast calculation and improved performance of the proposed algorithm, all control functions are implemented in software using a digital signal processor (DSP) with its environmental circuits. Also, it is shown through experimental results that the proposed system gives good performance for the speed-sensorless induction motor control.