• The Transactions of the Korean Institute of Power Electronics
• /
• v.9 no.6
• /
• pp.620-627
• /
• 2004

As h-bridge multilevel inverter is connected with series of single phase power cell, so it obtain high voltage using low voltage power semi-conductor and output voltage similar to sine wave. In this topology, the number of power cell increases in proportion to the output voltage level. Therefore, there are drawbacks that are responsibility against operating ability of main controller and signal wire increase. However, we can overcome this problems by the substitution of serial communication for the PWM signal in power cell control. Additionally, it has merits of reliability and maintenance. This paper deals with the synchronization and phase-shift method of power cell PWM using CAN(Controller Area Network) communication interrupt in H-bridge multilevel inverter. The advantages of proposed method are signal-line simplification using serial communication between main controller and cell controller, burden reduction in main controller, modularization of power cell, easy protection of each power cell, expandability improvement and reliability increase of control signal and power cell. This paper establishes propriety and reliability of proposed method through experiment of 13-level H-bridge multilevel inverter.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.708-711
• /
• 1997

This paper proposes the hybrid algorithm for the optimization of the structure and parameters of the fuzzy neural networks by genetic algorithms (GA) to improve the behaviour and the design of fuzzy neural networks. Fuzzy neural networks have a distinguishing feature in that they can possess the advantage of both neural networks and fuzzy systems. In this way, we can bring the low-level learning and computational power of neural networks into fuzzy systems and also high-level, human like IF-THEN rule thinking and reasoning of fuzzy systems into neural networks. As a result, there are many research works concerning the optimization of the structure and parameters of fuzzy neural networks. In this paper, we propose the hybrid algorithm that can optimize both the structure and parameters of fuzzy neural networks. Numerical example is provided to show the advantages of the proposed method.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.4
• /
• pp.60-67
• /
• 2005

Compared with conventional welding, laser spot welding offers a unique combination of high speed, precision and low heat distortion. This combination of advantages is attractive for manufacturing industries including automotive and electronics companies. In this paper, a real time monitoring scheme fur a pulsed Nd:YAG laser spot welding was suggested. Acoustic emission (AE) signals were collected during welding and analyzed for given process conditions such as laser power and pulse duration. A back propagation artificial neural network, with AE frequency content inputs, was used to predict the weldability of stainless steel sheets.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.6
• /
• pp.1932-1940
• /
• 2000

We must solve problems caused by mobile computing environments for supporting efficient mobile computing services. The problem is the use of wireless medium having high error rates and low bandwidth, and the sudden network disconnection to reduce the power consumption of a mobile host and the cost of the network connection. For these problems, we proposed the architecture of the partial connection manager and designed and implemented that in this paper. In particular, The partial connection manager creates the limited number of mobile agents according to priority and sends them in parallel to server systems and combines results of them process rapidly the user request. By applying the proposed partial connection manager to the mobile computing services called cybermarket, we knew that the mobile agent technique could be suited to the mobile computing environment and overcome the partial connection problem caused by eh mobile computing environment.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2002.05a
• /
• pp.213-217
• /
• 2002

Recently the subject of "wavelet analysis" has be drawn by both mathematical and engineering application fields such as Signal Processing, Compression/Decomposition, Wavelet-Neural Network, Statistics and etc. Even though its similar to courier analysis, wavelet is a versatile tool with much mathematical content and great potential for applications. Especially, wavelet transform uses localizable various mother wavelet functions in time-frequency domain. Therefore, wavelet transform has good time-analysis ability for high frequency component, and has good frequency-analysis ability for low frequency component. Using the discriminative ability is more easy method than other conventional techniques. In this paper, Morlet wavelet transform was applied to discriminate the kind of line fault by acquired data from real power transformation network. The experimental result presented that Morlet wavelet transform is easier, and more useful method than the FFW (Fast courier Transform).ransform).

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.516-518
• /
• 1995

This paper presents an integrated fault diagnosis expert system for power systems. The proposed system diagnoses various faults occurred in both substations and transmission lines even in the case that substation fault is spreaded over the network. To cope with this problem, A meta-inference method is proposed. This scheme shares same the data structure with the pre-developed intelligent operational aid expert system installed in a practical sub-control center, without modification. This advanced integrated diagnosis system is developed using a low cost personal computer owing to the special modular programming technique. Case studies show a promising possibility of the proposed method.

• Journal of Korea Multimedia Society
• /
• v.21 no.9
• /
• pp.1090-1098
• /
• 2018

MQTT is a lightweight messaging protocol that can be used for low power IoT devices. The MQTT basically uses single MQTT broker to indirectly share message information between publishers and subscribers. This approach has a weakness in regard to traffic overflow, connection fault, security, etc. In this paper, we propose a distributed MQTT broker architecture that solves the problems in single MQTT broker structure. The distributed MQTT broker architecture is expected to support new application services that cannot be supported by a conventional MQTT architecture. We have designed and implemented a distributed MQTT broker architecture based on the RPL protocol that has been widely used for IoT network. The experiment results show that the proposed MQTT broker architecture represents better publishing/subscribing latency and network stability than the conventional MQTT broker architecture.

• Journal of Sensor Science and Technology
• /
• v.16 no.6
• /
• pp.467-474
• /
• 2007

The real-time monitoring about the activity of the human provides useful information about the activity quantity and ability. The present study implemented a small-size and low-power acceleration monitoring system for convenient monitoring of activity quantity and recognition of emergent situations such as falling during daily life. For the wireless transmission of acceleration sensor signal, we developed a wireless transmission system based on a wireless sensor network. In addition, we developed a program for storing and monitoring wirelessly transmitted signals on PC in real-time. The performance of the implemented system was evaluated by assessing the output characteristic of the system according to the change of posture, and parameters and acontext recognition algorithm were developed in order to monitor activity volume during daily life and to recognize emergent situations such as falling. In particular, recognition error in the sudden change of acceleration was minimized by the application of a falling correction algorithm

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.4
• /
• pp.151-156
• /
• 2021

Low-end IoT devices do not have enough computation and memory resources for DNN learning and inference. Integer quantization of real-type neural network models can reduce model size, hardware computational burden, and power consumption. This paper describes the design and implementation of a web-based quantization platform for CNN deep learning accelerator chips. In the web service platform, we implemented visualization of the model through a convenient UI, analysis of each step of inference, and detailed editing of the model. Additionally, a data augmentation function and a management function of files that store models and inference intermediate results are provided. The implemented functions were verified using three YOLO models.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.139-141
• /
• 2019

This paper proposes the application of LoRa network, which has been under various research recently, to use control system for the transfer of Unmanned Vehicle. LoRa( Long Range) has a wide coverage of up to30 km, and is characterized by large-scale low-power long-distance radio communication. LoRa has already been studied in various industries. It is also proposed to study various functions by utilizing LoRa network and applying it to the control system of the uninhabited entity.