• Journal of Institute of Control, Robotics and Systems
• /
• v.8 no.10
• /
• pp.827-832
• /
• 2002

We propose a prediction method of the pollutant and a synchronous classification of the current state of SOx emission in the power plant. We use the auto-regressive with exogeneous (ARX) model as a predictor of SOx emission and use a radial basis function network (RBFN) as a pattem classifier. The ARX modeling scheme is implemented using recursive least squares (RLS) method to update the model parameters adaptively. The capability of SOx emission monitoring is utilized with the application of the RBFN classifier. Experimental results show that the ARX model can predict the SOx emission concentration well and ARX modeling parameters can be a good feature for the state monitoring. in addition, its validity has been verified through the power spectrum analysis. Consequently, the RBFN classifier in combination with ARX model is shown to be quite adequate for monitoring the state of SOx emission.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2014.02a
• /
• pp.262.2-262.2
• /
• 2014

Plasma processing is an essential process for pattern etching and thin film deposition in nanoscale semiconductor device fabrication. It is necessary to maintain plasma chamber in steady-state in production. In this study, we determined plasma chamber state with residual gas analysis with self-plasma optical emission spectroscopy. Residual gas monitoring of fluorocarbon plasma etching chamber was performed with self-plasma optical emission spectroscopy (SPOES) and various chemical elements was identified with a SPOES system which is composed of small inductive coupled plasma chamber for glow discharge and optical emission spectroscopy monitoring system for measuring optical emission. This work demonstrates that chamber state can be monitored with SPOES and this technique can potentially help maintenance in production lines.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.7 no.3
• /
• pp.14-21
• /
• 1998

The in-process detection of the state of cutting tool is one of the most important technical problem in Intelligent Machining System. This paper presents a method of detecting the state of cutting tool in turning process, by using Artificial Neural Network. In order to sense the state of cutting tool. the sensor fusion of an acoustic emission sensor and a force sensor is applied in this paper. It is shown that AErms and three directional dynamic mean cutting forces are sensitive to the tool wear. Therefore the six pattern features that is, the four sensory signal features and two cutting conditions are selected for the monitoring system with Artificial Neural Network. The proposed monitoring system shows a good recogniton rate for the different cutting conditions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.5
• /
• pp.1082-1086
• /
• 2007

This research has a purpose of constructing the data monitoring system that makes two-tier work state in the brick production factory to unification by reusing cinder. Monitoring system automatically manages data by using data managing processes such as a state managing process, a location managing process, a badness managing process, a circumstances managing process. In this research, the data management monitoring system manufactures state information of each processes received from RFID and transmits them to data monitoring system. Analyzed data through this system reuses the cinder, so it can effectively manage the production process of the factory which produces bricks through processing automation, faulty-ratio minimization, real-time monitoring and loading managing.

• Geomechanics and Engineering
• /
• v.14 no.5
• /
• pp.421-428
• /
• 2018

In deep mining, the lateral deformation of strip coal pillar appears to be a new characteristic. In order to study the lateral deformation of coal-mass, a monitoring method and monitoring instrument were designed to investigate the lateral deformation of strip coal pillar in Tangkou Coalmine with the mining depth of over 1000 m. Because of without influence of repeated mining, the bedding sandstone roof is easy to break and the angle between maximum horizontal stress and the roadway is small, the maximum lateral deformation is only about 287 mm lower than the other pillars in the same coalmine. In deep mining, the energy accumulation and release cause a discontinuous damage in the heterogeneous coal-mass, and the lateral deformation of coal pillar shows discontinuity, step and mutation characters. These coal-masses not only show a higher plasticity but also the high brittleness at the same time, and its burst tendency is more obvious. According to the monitoring results and theoretical calculations, the yield zone of the coal pillar width is determined as 15.6 m. The monitoring results presented through this study are of great significance to the stability analysis and design of coal pillar.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.332-335
• /
• 1997

With the advance of precision technique, the optical system is more precise and complex and the machining method of optical element which is composed of micro-grooves is developed. Especially, the method of micro-grooving using diamond tool is used widely owing to many merit, but has problems of damage of surface roughness due to tool wear and tool fracture. This paper deals with state monitoring using AE RMS in the micro-grooving. The change of AE RMS is very small with increment of cutting velocity and depth of cut. In spite of constance magnitude of principal force in machining using diamond tool of tool wear and tool fracture, AE RMS is highly fluctuated. Because changing of cutting state has relevance to surface roughness profile, surface toughness profile is expected using AE RMS.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.1
• /
• pp.13-20
• /
• 2012

This paper proposes a marine engine state monitoring system using a DPQ (Distributed Precedence Queue) mechanism which collects the state of bearings, temperature and pressure of engine through the CAN network. The CAN is developed by Bosch Corp. in the early 1980' for automobile network. The data from various sensors attached in the marine engine are converted to digital by the analog to digital converter and formatted to fit the CAN protocol at the CAN module. All the CAN modules are connected to the SPU (Signal Processing Unit) module for the efficient communication and processing. This design reduces the cost for wiring and improves the data transmission reliability by recognizing the sensor errors and data transmission errors. The DPQ mechanism is newly developed for the performance improvement of the marine engine system, which is demonstrated through the experiments.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2000.04a
• /
• pp.8-13
• /
• 2000

Die polishing technology is very critical to determine quality and performance of the final products. Die polishing processes have not been automated because the automation requires a great deal of experience and skill of experts. Thus, to implement a fully automated polishing process, the development of polishing status monitoring system replacing the skill of experts is critical. AE is known to be closely related to material removal rate(MRR). As the surface is rougher, MRR gets larger and AE increased. The surface roughness can be indirectly estimated using the AE signal measured during automatic die polishing process. In this study, The polishing state monitoring system using AEms signal was developed. This system can be not only to monitor the abnormal state but also to estimate a state of surface roughness of polishing surface qualitatively.

• Journal of Biosystems Engineering
• /
• v.28 no.1
• /
• pp.53-58
• /
• 2003

This study was carried out to design, construct, and test a greenhouse monitoring system fur the environment and status of control devices in a greenhouse from a remote site using internet. The measuring items selected out of many environmental factors were temperature, humidity, solar radiation, CO$_2$, SOx, NOx concentration, EC, pH of nutrient solution, the state of control devices, and the image of greenhouse. The developed greenhouse monitoring system was composed of the network system and the measuring module. The network system consists of the three kinds of monitors named the Croup Monitor. the Client Monitor and the Server Monitor. The results of the study are summarized as follows. 1. The measuring module named the House Monitor. which is used to watch the state of the control device and the environment of the greenhouse, was developed to a embedded monitoring module using one chip microprocessor 2. For all measuring items. the House Monitor showed a satisfactory accuracy within the range of ${\pm}$0.3%FS. The House Monitors were connected to the Croup Monitor by communication method of RS-485 type and could operate under power and communication fault condition within 10 hours. The Croup Monitor was developed to receive and display measurement data received from the House Monitors and to control the greenhouse environmental devices. 3. The images of the plants inside greenhouse were captured by PC camera and sent to the Group Monitor. The greenhouse manager was able to monitor the growth state of plants inside greenhouse without visiting individual greenhouses. 4. Remote monitoring the greenhouse environment and status of control devices was implemented in a client/server environment. The client monitor of the greenhouse manager at a remote site or other greenhouse manager was able to monitor the greenhouse environment and the state of control devices from the Server Monitor using internet.

• Structural Monitoring and Maintenance
• /
• v.1 no.1
• /
• pp.111-130
• /
• 2014

The increased use of carbon fiber reinforced polymer (CFRP) in retrofitting reinforced concrete (RC) members has led to the need to develop non-destructive techniques that can monitor and characterize the unique damage mechanisms exhibited by such structural systems. This paper presented the damage characterization results of six CFRP retrofitted RC beam specimens tested in the laboratory and monitored using acoustic emission (AE). The focus of this study was to continuously monitor the change in AE parameters and analyze them both qualitatively and quantitatively, when brittle failure modes such as debonding occur in these beams. Although deterioration of structural integrity was traceable and can be quantified by monitoring the AE data, individual failure mode characteristics could not be identified due to the complexity of the system failure modes. In all, AE was an effective non-destructive monitoring tool that can trace the failure progression in RC beams retrofitted with CFRP. It would be advantageous to isolate signals originating from the CFRP and concrete, leading to a more clear understanding of the progression of the brittle damage mechanism involved in such a structural system. For practical applications, future studies should focus on spectral analysis of AE data from broadband sensors and automated pattern recognition tools to classify and better correlate AE parameters to failure modes observed.