• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.398-404
• /
• 2021

This paper proposes a method of using a magnetic position sensor to detect accurately the rotor position required to perform vector control of a permanent-magnet synchronous motor, particularly the initial rotor position at startup. In the existing vector control systems, the initial rotor position was determined using the output signals of the Hall sensors, or the control was performed in a sensorless method without using such a sensor. On the other hand, the accuracy is degraded due to the occurrence of a position detection error, and the practicality was not satisfactory. This paper attempts to detect the initial rotor position using a magnetic position sensor to solve this problem. This method is used to solve the deteriorating starting characteristics of the motor in the vector control system. In addition, to lower the price of a low-power vector control inverter, this paper proposes a method of integrating the existing sensors and reducing the price to less than half using a magnetic position sensor for speed and position detection.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.3
• /
• pp.23-31
• /
• 2010

The increasing demands on low-power, and low-complexity video encoder have been motivating extensive research activities on distributed video coding (DVC) in which the encoder compresses frames without utilizing inter-frame statistical correlation. In DVC encoder, contrary to the conventional video encoder, an error control code compresses the video frames by representing the frames in the form of syndrome bits. In the meantime, the DVC decoder generates side information which is modeled as a noisy version of the original video frames, and a decoder of the error-control code corrects the errors in the side information with the syndrome bits. The noisy observation, i.e., the side information can be understood as the output of a virtual channel corresponding to the orignal video frames, and the conditional probability of the virtual channel model is assumed to follow a Laplacian distribution. Thus, performance improvement of DVC systems depends on performances of the error-control code and the optimal reconstruction step in the DVC decoder. In turn, the performances of two constituent blocks are directly related to a better estimation of the parameter of the correlation channel. In this paper, we propose an algorithm to estimate the parameter of the correlation channel and also a low-complexity version of the proposed algorithm. In particular, the proposed algorithm minimizes squared-error of the Laplacian probability distribution and the empirical observations. Finally, we show that the conventional algorithm can be improved by adopting a confidential window. The proposed algorithm results in PSNR gain up to 1.8 dB and 1.1 dB on Mother and Foreman video sequences, respectively.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.6
• /
• pp.994-1002
• /
• 2008

In this paper a novel tracking system is described, regarding the influence of shadow between array, aimed at improving the efficiency of PV tracking system. Comparing with a building site versus capacity power, domestic solar powers have a limited siting. Therefore, each array interferes with the shadow of other arrays. The loss by influence of those shadow can be compensated for by means of control algorithm of the tracking device. The paper suggests a method controlling an altitude for length which is received the shadow influence of PV array. By using an azimuth of current solar position and the length between arrays, the controller of tracking device is able to calculate the length between actual arrays and make a comparison of the shadow length at a specific time with the length between arrays. When the shadow length is longer than the length between arrays, the controller of tracking device can adjust a position by compensating error altitude of the length between arrays at an altitude of current solar position. In the paper, we develop the control algorithm able to minimize the loss caused by the influence of shadow on the PV tracking system, and compared this with conventional output system. The controller has been tested in the laboratory with proposed algorithm and shows excellent performance.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.2
• /
• pp.131-139
• /
• 2013

In recent years alternative navigation system such as a DBRN (Data-Base Referenced Navigation) system using geophysical information is getting attention in the military navigation systems in advanced countries. Specifically TRN (Terrain Referenced Navigation) algorithm research is important because TRN system is a practical DBRN application in South Korea at present time. This paper presents an integrated navigation algorithm that combines a linear profile-based TRN and INS (Inertial Navigation System). We propose a correlation analysis method between TRN performance and terrain roughness index. Then we propose a conditional position update scheme that utilizes the position output of the conventional linear profile type TRN depending on the terrain roughness index. Performance of the proposed algorithm is verified through Monte Carlo computer simulations using the actual terrain database. The results show that the TRN/INS integrated algorithm, even when the initial INS error is present, overcomes the shortcomings of linear profile-based TRN and improves navigation performance.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.2
• /
• pp.77-86
• /
• 2004

In general, small-sized neural networks, even though they show good generalization performance, tend to fail to team the training data within a given error bound, whereas large-sized ones learn the training data easily but yield poor generalization. Therefore, a way of achieving good generalization is to find the smallest network that can learn the data, called the optimal-sized neural network. This paper proposes a new scheme for network pruning with ‘impact factor’ which is defined as a multiplication of the variance of a neuron output and the square of its outgoing weight. Simulation results of function approximation problems show that the proposed method is effective in regression.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.144-150
• /
• 2020

Reinforcement learning is a technology that can present successful and creative solutions in many areas. This reinforcement learning technology was used to deploy containers from cloud servers to fog servers to help them learn the maximization of rewards due to reduced traffic. Leveraging reinforcement learning is aimed at predicting traffic in the network and optimizing traffic-based fog computing network environment for cloud, fog and clients. The reinforcement learning system collects network traffic data from the fog server and IoT. Reinforcement learning neural networks, which use collected traffic data as input values, can consist of Long Short-Term Memory (LSTM) neural networks in network environments that support fog computing, to learn time series data and to predict optimized traffic. Description of the input and output values of the traffic-based reinforcement learning LSTM neural network, the composition of the node, the activation function and error function of the hidden layer, the overfitting method, and the optimization algorithm.

• Journal of Advanced Research in Ocean Engineering
• /
• v.3 no.3
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.6
• /
• pp.524-530
• /
• 2002

This note suggests a stepwise fuzzy moving sliding surface using Sugeno-type fuzzy system and presents a sliding mode control scheme using it. The fuzzy system has the angle of state error vector and the distance from the origin in the phase plane as inputs and a first-order linear differential equation as output. The surface initially passes arbitrary initial states and subsequently moves towards a predetermined surface via rotating or shifting. This method reduces the reaching and tracking time and improves robustness. Conceptually the slope of the Proposed fuzzy moving sliding surface increases stepwise in the stable region of the phase plane. The surface, however, rotates continuously because the surface is a fuzzy system. The asymptotic stability of the fuzzy sliding surface is proved. The validity of the proposed control scheme is shown in computer simulation for a second-order nonlinear system.

• Journal of Advanced Marine Engineering and Technology
• /
• v.31 no.2
• /
• pp.138-144
• /
• 2007

The variation of the crankshaft speed in a multi-cylinder engine is determined by the resultant gas pressure torque and the torsional deformation of the crankshaft. Under steady state operation, the crankshaft speed has a quasi-periodic variation. For the diagnosis the engine instantaneous speed versus crankshaft angle is utilized. This paper describes a simple measurement method of the engine instantaneous speed versus crankshaft angle using the teeth on the flywheel of the crankshaft. Two non-contacting magnetic pickup combinations detect the crank angle and TDC position for the data acquisition. The results from experiments on a 6 cylinder marine diesel engine demonstrate that the crankshaft speed variation are detected with good resolution. And the crankshaft speed variation is investigated according to the operation conditions. Also, it is confirmed that the engine output measured by EMS can be evaluated larger than the actual value due to TDC position error caused by instantaneous speed variation.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.449-456
• /
• 2004

This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained an ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.