• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.9
• /
• pp.29-35
• /
• 2019

The structure of the machinery industry due to the 4th industrial revolution is changing from precision and durability to intelligent and smart machinery through sensing and interconnection(IoT). There is a growing need for research on prognostics and health management(PHM) that can prevent abnormalities in processing machines and accurately predict and diagnose conditions. PHM is a technology that monitors the condition of a mechanical system, diagnoses signs of failure, and predicts the remaining life of the object. In this study, the vibration generated during machining is measured and a classification algorithm for normal and fault signals is developed. Arbitrary fault signal is collected by changing the conditions of un stable supply cutting oil and fixing jig. The signal processing is performed to apply the measured signal to the learning model. The sampling rate is changed for high speed operation and performed machine learning using raw signal without FFT. The fault classification algorithm for 1D convolution neural network composed of 2 convolution layers is developed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.09a
• /
• pp.770-771
• /
• 2005

• Bulletin of the Korean Chemical Society
• /
• v.34 no.3
• /
• pp.967-970
• /
• 2013

• Asia pacific journal of information systems
• /
• v.12 no.2
• /
• pp.119-135
• /
• 2002

Those making decisions are no longer located in the same workplace. Wireless technology appears promising as a method to promote group performance in circumstances dependent on time, but not member proximity. However, the success of wireless technology in group decision-making situations has not yet been proven. This paper seeks to learn whether wireless technology affects the performance of group decision-making tasks that should be resolved urgently and/or sources of idea are disconnected with on-line network.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.05a
• /
• pp.1301-1302
• /
• 2005

• Proceedings of the SAREK Conference
• /
• 2004.06a
• /
• pp.202-202
• /
• 2004

• Proceedings of the Korean Nuclear Society Conference
• /
• 2005.10a
• /
• pp.1057-1058
• /
• 2005

• 한국정보디스플레이학회:학술대회논문집
• /
• 2008.10a
• /
• pp.1269-1271
• /
• 2008

We find some array mura are caused by S/D bridge or channel open in 4 mask process. The gray tone PR thickness non-uniformity is the main reason of these defects. By the adjustment of exposure and dry etch parameters, S/D bridge and channel open ratio drops by 10.87%.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.15 no.26
• /
• pp.77-84
• /
• 1992

This paper constructs Croup Technology process-based learning curve model adjusted to a Group Technology environment which accounts for shared learning that occurs when multiple products utilize some of the same process steps. Through this constructed model, the estimated times and productivity of labor calculated by the Group Technology process-based learning curve model are compared with those generated by employing product-based 1 earning curve model. For sensitivity analysis of the model, the impact of learning rate and the ordered production quantity on the ratio differences between Group Technology process-based learning curve model and product-based learning curve model are examined. These results indicate the critical importance of employing Group Technology process-based learning curve model when a process spans multiple products.

• Proceedings of the Korean Society for Food Science of Animal Resources Conference
• /
• 2005.05a
• /
• pp.159-163
• /
• 2005

Ninety KNP were divided into three group by differential market weight(20 of each group): Live weight of Group 1(G 1), Group 2(G 2) and Group 3(G 3) were 50-59kg, 60-69kg, 70-80kg, respectively. Values of pH and shear force showed an increase, while cooking loss showed decreased with increased weight. In color analysis, $a^{\ast}$ value in meat and $b^{\ast}$ value in backfat of KNP showed higher as slaughter weight increased. Slaughter weight did not significantly affect the fatty acid composition of subcutaneous fat of KNP. With the exception of oleic acid in intermuscular fat, there were no significant weight-dependent differences in the fatty acid profiles.