• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1413-1415
• /
• 2004

This paper proposes a SVM(Support Vector Machine) training algorithm to control a service robot with voice command. The service robot with a stereo vision system and dual manipulators of four degrees of freedom implements a User-Dependent Voice Control System. The training of SVM algorithm that is one of the statistical learning theories leads to a QP(quadratic programming) problem. In this paper, we present an efficient SVM speech recognition scheme especially based on less learning data comparing with conventional approaches. SVM discriminator decides rejection or acceptance of user's extracted voice features by the MFCC(Mel Frequency Cepstrum Coefficient). Among several SVM kernels, the exponential RBF function gives the best classification and the accurate user recognition. The numerical simulation and the experiment verified the usefulness of the proposed algorithm.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.1 no.1
• /
• pp.27-37
• /
• 1996

This paper proposes the control algorithm for maximum efficiency drive of PWM inverter - induction motor system with high dynamic performance. If the induction motor is driven under light load with rated magnetizing current, the Iron loss is excessively large compared with the codder loss which results in doer motor efficiency. Maximum efficiency drive of an induction motor can be achieved by controlling the magnetizing current to satisfy the optimal ratio that leads the total motor loss to be a minimum value at a given speed. The proposed control algorithm essentially uses vector control technique and adopts voltage decoupling control strategy to prevent the degradation of dynamic performance due to reduced magnetizing current. To verify the proposed method, digital simulations and experiments are carried out for a squirrel-cage induction motor with the rating of 2.2[kW].

• The Transactions of the Korean Institute of Power Electronics
• /
• v.27 no.1
• /
• pp.18-25
• /
• 2022

The cold staring issue of permanent magnet synchronous motors (PMSM) is a chronic problem in the field of PMSM sensorless drives. A traditional starting method, called the I-F method, is widely adopted because of its simple structure. However, when using this method, the pre-defined magnitude and frequency of the starting current should be changed according to the condition of the load and machine inertia. In this paper, a smart and simple algorithm for the cold starting of PMSM is proposed. In the proposed method, an integrated control angle from the estimated electrical rotor speed is used for vector control such as the indirect vector control of the induction machine. Thus, very stable cold starting is performed regardless of the machine load condition or inertia changing.

• Proceedings of the KIPE Conference
• /
• 1999.07a
• /
• pp.390-393
• /
• 1999

For high performance ac drives, the speed sensorless vector control and a speed control algorithm base on the Fuzzy PI controller have received increasing attention. A Fuzzy PI controller is used for robust and fast speed control and space vector modulation method is used for PWM wave generation in this proposed system. The computer simulation results show that the proposed controller are more excellent control characteristics than conventional PI controller in transient-state response.

• Journal of Institute of Control, Robotics and Systems
• /
• v.2 no.2
• /
• pp.67-72
• /
• 1996

This paper presents a parameter adaptive control law that stabilizes and asymptotically regulates any single-input, linear time-invariant, controllable and observable, discrete-time system when only the upper bounds on the order of the system is given. The algorithm presented in this paper comprises basically a nonlinear state feedback law which is represented by functions of the state vector in the controllable subspace of the model, an adaptive identifier of plant parameters which uses inputs and outputs of a certain length, and an adaptive law for feedback gain adjustment. A new psedu-inverse algorithm is used for the adaptive feedback gain adjustment rather than a least-square algorithm. The proposed feedback law results in not only uniform boundedness of the state vector to zero. The superiority of the proposed algorithm over other algorithms is shown through some examples.

• Journal of Korean Society for Quality Management
• /
• v.38 no.3
• /
• pp.354-362
• /
• 2010

This paper presents a non-linear control chart based on support vector machine regression (SVM-R) to improve the accuracy of fault detection of cyclic signals. The proposed algorithm consists of the following two steps. First, the center line of the control chart is constructed by using SVM-R. Second, we calculate control limits by variances that are estimated by perpendicular and normal line of the center line. For performance evaluation, we apply proposed algorithm to the industrial data of the chemical vapor deposition process which is one of the semiconductor processes. The proposed method has better fault detection performance than other existing method

• Proceedings of the KIEE Conference
• /
• 1998.07f
• /
• pp.2002-2004
• /
• 1998

In this paper, the compensation algorithm of the stator resistance which is essential to improving the performance of the direct vector control system is proposed. This paper focuses on the improvement in the torque response of the direct vector control in a constant speed region. The conventional compensation algorithms are analyzed and a new method is developed to compensate the stator resistance in the direct vector control system. In addition, the effect of the variation of the stator resistance on the drive performance is analyzed for the vector control. The proposed algorithm is very simple to implement that does not require the modifications on the motor model or additional interrupts of the controller. Also, the value of the stator resistance can be obtained in real-time through the measurement of the terminal voltage and current. From the simulation and experimental results, the validity of the proposed scheme is confirmed.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.149-152
• /
• 2004

Speed and torque control of PMSM(Permanent Magnet Synchronous Motor) are usually achieved by using position and speed sensors which require additional mounting space, reduce the reliability in harsh environments and increase the cost of a motor. Therefore, many studies have been performed for the elimination of speed and position sensors. In this paper, a novel speed sensorless control of a permanent magnet synchronous motor based on SVMR(Support Vector Machine Regression) is presented. The SVM regression method is an algorithm that estimates an unknown mapping between a system's input and outputs, from the available data or training data. Two well-known different voltage model is necessary to estimate the speed of a PMSM. The validity and the usefulness of proposed algorithm are thoroughly verified through numerical simulation.

• Proceedings of the KIPE Conference
• /
• 1999.07a
• /
• pp.540-543
• /
• 1999

This paper describes a speed sensorless algorithm for vector control system with compensated stator resistance and rotor time constant of induction motor using a model reference adaptive system(MRAS). The system are composed of two MRAC, one is a rotor speed estimation and a stator resistor identification by back-EMF observer, other is used to identify rotor time constant by magnetizing current observer, so that the estimation can be cover a very low speed range with a robust control. The suggest control strategy and estimation method have been validated by simulation study. In the simulation using Matlab/Simulik, the proposed speed sensorless vector control system are shown to operate very well in spite of variable rotor time constant and load fluctuation.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.1013-1016
• /
• 2000

In this study, the estimate speed of rotor in the induction motor with Model Reference Adaptive control System (MARC) principle and to study that vector control system feedbacks speed estimated to speed control system and its result is as follows; Considering with explanation an influence of speed estimation mechanism depend on error about the second resistance size established, it estimates the deviation of the second resistance establishment and exhibits a compensation method, what is more, it designs a reparation program using the fuzzy algorithm and testifies the result with the computer simulation. And besides, it composes the load torque estimation and estimates the load torque, as the result, feedback-compensating the result of estimation, it improves the efficiency. In consequence, it makes a good result for more powerful vector control system about the outside trouble.