• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.1
• /
• pp.138-149
• /
• 1994

This paper introduces a new monitoring technique which utilizes an adaptive signal processing for feature generation, coupled with a multilayered merual network for pattern recognition. The cutting force signal in face milling operation was modeled by a low order discrete autoregressive model, shere parameters were estimated recursively at each sampling instant using a parameter adaptation algorithm based on an RLS(recursive least square) method with discounted measurements. The influences of the adaptation algorithm parameters as well as some considerations for modeling on the estimation results are discussed. The sensitivity of the extimated model parameters to the tool state(new and worn tool)is presented, and the application of a multilayered neural network to tool state monitoring using the previously generated features is also demonstrated with a high success rate. The methodology turned out to be quite suitable for in-process tool wear monitoring in the sense that the model parameters are effective as tool state features in milling operation and that the classifier successfully maps the sensors data to correct output decision.

• Structural Engineering and Mechanics
• /
• v.25 no.5
• /
• pp.577-596
• /
• 2007

Recent development of fiber optic sensor technology has provided an excellent choice for civil engineers for performance monitoring of civil infrastructures. Fiber optic sensors have the advantages of small dimensions, good resolution and accuracy, as well as excellent ability to transmit signal at long distances. They are also immune to electromagnetic and radio frequency interference and may incorporate a series of interrogated sensors multiplexed along a single fiber. These advantages make fiber optic sensors a better method than traditional damage detection methods and devices to some extent. This paper provides a review of recent developments in fiber optic sensor technology as well as some applications of fiber optic sensors to the performance monitoring of civil infrastructures such as buildings, bridges, pavements, dams, pipelines, tunnels, piles, etc. Existing problems of fiber optic sensors with their applications to civil structural performance monitoring are also discussed.

• Proceedings of the IEEK Conference
• /
• 2003.07c
• /
• pp.2565-2568
• /
• 2003

This paper presents a behavioral data monitoring system based on WAP(wireless application protocol) service for the 24-hour continuous health state monitoring of the elderly and the disabled. The developed system transmits a character message to the predefined mobile cell phone through SMS service when an emergency state takes place. Simultaneously, the image captured by a CCD camera is transmitted to the server computer installed WAP service program. Then, the user of the cell phone who received he message can access the server and open the transmitted image. This system can be used for the effective health monitoring of the elderly and disabled.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.11a
• /
• pp.328-332
• /
• 1996

The compressor is one of important elements in refrigerator cycle and play an important role of refrigeration efficiency and quality. Therefore it is very important to monitor state of normal and abnormal compressor. In this research, technic of AE is used for monitoring abnormal rotary compressor and an AE parameter which is a most proper parameter to monitor the abnormal state of compressor is determined by signal processing, Finally, the monitoring result of rotary compressor is agreement with the result of life test.

• Proceedings of the KIEE Conference
• /
• 2001.07a
• /
• pp.473-475
• /
• 2001

We report the state of the development of monitoring system for 72.5kV GIS. In the first, the usual outline of the monitoring and diagnostic system for GIS was mentioned, and the detailed specifications and state of development were also described. Especially, we present items of monitoring for GIS such as the operating counter of CB, the leakage condition of $SF_6$ gas, the surge counter of LA and the leakage current of LA.

• Geomechanics and Engineering
• /
• v.11 no.4
• /
• pp.571-585
• /
• 2016

The crest of the Pubugou central core rockfill dam (CCRD) cracked in the first and second impounding periods. To evaluate the safety of the Pubugou CCRD, an inversion analysis of the constitutive model parameters for rockfill materials is performed based on the in situ deformation monitoring data. The aim of this work is to truly reflect the deformation state of the Pubugou CCRD and determine the causes of the dam crest cracks. A novel real-coded genetic algorithm based upon the differences in gene fragments (DGFX) is proposed. It is used in combination with the radial based function neural network (RBFNN) to perform the parameters back analysis. The simulated settlements show good agreements with the monitoring data, illustrating that the back analysis is reasonable and accurate. Furthermore, the deformation gradient of the dam crest has been analysed. The dam crest has a great possibility of cracking due to the uncoordinated deformation, which agrees well with the field investigation. The deformation gradient decreases to the value lower than the critical one and reaches a stable state after the second full reservoir.

• International Journal of Contents
• /
• v.3 no.1
• /
• pp.24-28
• /
• 2007

This paper embodies the agent based cinder monitoring system which supports PDA(Personal Digital Assistant). Monitoring system automatically manages data by using data managing agents such as a state managing agent, a location managing agent, a badness managing agent, a circumstances managing agent, etc, and uses a massive data processing agent to manage massive data. The development of agent based data monitoring system for the stable cinder reuse will be an epoch-making method to develop the process mechanized or manual-labored that widely spreads into the real-time automated process.

• International Journal of Contents
• /
• v.4 no.4
• /
• pp.7-11
• /
• 2008

This paper embodies the agent based cinder monitoring system which supports PDA{Personal Digital Assistant). Monitoring system automatically manages data by using data managing agents such as a state managing agent, a location managing agent, a badness managing agent, a circumstances managing agent, etc, and uses a massive data processing agent to manage massive data. The development of agent based data monitoring system for the stable cinder reuse will be an epoch-making method to develop the process mechanized or manual-labored that widely spreads into the real-time automated process.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.16 no.1
• /
• pp.99-109
• /
• 2012

This study aimed to develop a Structural Health Monitoring System for steel beams in the manner of suggesting and verifying a theoretical formula for displacement estimation using strain gauges, and estimating the loading points and magnitude. According to the results of this study, it was found that when a load of 160kN (56% of the yield load) was applied, the error rate of the deflection obtained with a strain gauge at the point of maximum deflection compared to the deflection measured with a displacement meter was within 2%, and that the estimates of the magnitude and points of load application also showed the error rate of not more than 1%. This suggests that the displacement and load of steel beams can be measured with strain gauges and further, it will enable more cost-effective sensor designing without displacement meter or load cell. The Structural Health Monitoring System program implemented in Lab VIEW gave graded warnings whenever the measured data exceeds the specified range (strength limit state, serviceability limit state, yield strain), and both the serviceability limit state and strength limit state could be simultaneously monitored with strain gauge alone.

• Geomechanics and Engineering
• /
• v.17 no.4
• /
• pp.375-383
• /
• 2019

In underground retreating longwall coal mining, hard roof collapse is one of the most challenging safety problems for mined-out areas. Identifying precursors for hard roof collapse is of great importance for the development of warning systems related to collapse geohazards and ground control. In this case study, the Xinhe mine was chosen because it is a standard mine and the minable coal seam usually lies beneath hard strata. Real-time monitoring of hard roof collapse was performed in longwall face 5301 of the Xinhe mine using support resistance and microseismic (MS) monitoring; five hard roof collapse cases were identified. To reveal the characteristics of MS activity during hard roof collapse development and to identify its precursors, the change in MS parameters, such as MS event rate, energy release, bursting strain energy, b value and the relationships with hard roof collapse, were studied. This research indicates that some MS parameters showed irregularity before hard roof collapse. For the Xinhe coalmine, a substantial decrease in b value and a rapid increase in MS event rate were reliable hard roof collapse precursors. It is suggested that the b value has the highest predictive sensitivity, and the MS event rate has the second highest.