• Journal of Electrical Engineering and Technology
• /
• v.2 no.2
• /
• pp.280-285
• /
• 2007

This paper presents a robustly adaptive flux observer for speed-sensorless induction motor control. The proposed approach employs additional robustifying signals to cope with the parametric uncertainties instead of designing an estimator, which has been normally used in power electronic drives. For that, the sliding-mode like adaptive controls are designed and their gain parameters are determined so that the observer dynamics are stable in the sense of Lyapunov, and furthermore they can guarantee the robustness against parametric uncertainties in induction motor systems. Estimated rotor speed is to be used to generate feedback control signal for the speed sensorless vector control system. To show the validity and efficiency of the proposed system, simulation results are presented.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.578-578
• /
• 2002

Thermal infrared imaging is a highly promising technology for condition monitoring and predictive maintenance of electronic, electrical and mechanical elements in nuclear power plants. However, conventional low-cost infrared imaging systems suffer from poor spatial resolution compared to commercial CCD cameras. This paper describes an approach to enhance inspection performances for calandria reactor area of Wolsung nuclear power plant through the technique of superimposing thermal infrared image into real CCD image. In the occurrence of thermal abnormalities on observation points and areas of calandria reactor area, unusual hot image taken from thermal infrared camera is mapped upon real CCD image. The performance of the technique has been evaluated in the experiment carried out at Wolsung nuclear power plant in the overhaul period. The results show that localizations of thermal abnormalities on calandria reactor face can be estimated accurately.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.777-780
• /
• 2003

We have tried to create a vision system like human eye for a long time. We have obtained some distinguished results through many studies. Stereo vision is the most similar to human eye among those. This is the process of recreating 3-D spatial information from a pair of 2-D images. In this paper, we have designed a stereo matching algorithm based on systolic array architecture using edges and pixel data. This is more advanced vision system that improves some problems of previous stereo vision systems. This decreases noise and improves matching rate using edges and pixel data and also improves processing speed using high integration one chip FPGA and compact modules. We can apply this to robot vision and automatic control vehicles and artificial satellites.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.30.2-30
• /
• 2001

As the era of the human friendly robot looms, the intelligent autonomous mobile robots have obtained tremendous interests in recent years. The robots may be service robots for serving human or industrial robots for replacing human. For the coexistance with human, the robots must be able to feel and recognize three dimensional space that human live. In this paper, we propose three dimensional environmental modeling method based on a neural network technique called Growing Neural Gas Network. The purpose of this neural network is to generate a graphical structure which reflects the topology of the input space. Through this method, the robots´ surroundings are autonomously segmented ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.42.3-42
• /
• 2001

A human is an expert in manipulation. We have acquired skills to perform dexterous operations based upon knowledge and experience attained over a long period of time. It is important in robotics to understand these human skills, and utilize them to bring about better robot control and operation It is hoped that the neurocontroller can be trained and organized by simply presenting human teaching data, which implicate human intention, strategy and expertise. In designing a neurocontroller, we must determine the size of neurocontroller. Improper size may not only incur difficulties in training neural nets, e.g. no convergence, but also cause instability and erratic behavior in machines. Therefore, it is necessary to determine the proper size of neurocontroller for human control transfer. In this paper, a new pruning method is developed, based on the penalty-term methods. This method makes ...

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.30.3-30
• /
• 2001

In this paper, we designed the 6-wheeled mobile robot (6-WMR) with the passive linkage mechanism which enables 6-WMR to passively adapt to the given stairs. To overcome the limit of adaptability to the terrain of conventional WMR and improve the energy efficiency, we proposed the new WMR using the passive linkage mechanism. The passive linkage mechanism consists of the simple four-bar linkage mechanism which allows 6-WMR to climb stairs with adaptability and an additional link which is connected to the four-bar linkage mechanism by a pin-slot joint to enable 6-WMR to passively go up the stairs. We made a miniature model of the proposed 6-WMR ...

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.3
• /
• pp.301-306
• /
• 2021

In this paper, we propose a modified back-stepping control method in view of the dynamic model of mobile manipulator has the nonholonomic constraints, these constraints should be considered to design a tracking controller for the mobile manipulator. The conventional back-stepping controller includes the dynamics and kinematics of the mobile robot systems. and the modified adaptive back0stepping method is applied to constructing the controller. The proposed controller can realize the tracking trajectory of the reference path. The efficiency and robustness of this control method is demonstrated by the simulation.

• Annual Conference of KIPS
• /
• 2013.05a
• /
• pp.501-503
• /
• 2013

This project presents a concept of mobile robots using prototypes, computing proposal oriented to embedded systems implementation. We implement our system using GPS module, Ultrasonic sensor(range sensors), H-bridge dual stepper control, DTMF(Dual-tone Multi-Frequency ) and LCD module. In this paper we construct a mechanical simple mobile robot model, which can measure the distance from obstacle with the aid of sensor and should able to control the speed of motor accordingly. Modules were interfaced with FPGA(Field Programmable Gate Array) controller for hardware implementation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.1076-1094
• /
• 2022

Technology for emotion recognition is an essential part of human personality analysis. To define human personality characteristics, the existing method used the survey method. However, there are many cases where communication cannot make without considering emotions. Hence, emotional recognition technology is an essential element for communication but has also been adopted in many other fields. A person's emotions are revealed in various ways, typically including facial, speech, and biometric responses. Therefore, various methods can recognize emotions, e.g., images, voice signals, and physiological signals. Physiological signals are measured with biological sensors and analyzed to identify emotions. This study employed two sensor types. First, the existing method, the binary arousal-valence method, was subdivided into four levels to classify emotions in more detail. Then, based on the current techniques classified as High/Low, the model was further subdivided into multi-levels. Finally, signal characteristics were extracted using a 1-D Convolution Neural Network (CNN) and classified sixteen feelings. Although CNN was used to learn images in 2D, sensor data in 1D was used as the input in this paper. Finally, the proposed emotional recognition system was evaluated by measuring actual sensors.