• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 1998.04a
• /
• pp.83-90
• /
• 1998

The morphologies of the wear debris are directly indicative of wear processes occuring in machinery and their severity. The neural network was applied to identify friction condition from the lubricated moving system. The four parameter(50% volumetric diameter, aspect, roundness and reflectivity) of wear debris are used as inputs to the network and learned the friction coefficient. It is shown that identification results depend on the ranges of these shape parameter learned. The three kinds of the wear debris had a different pattern characteristic and recognized the friction condition and materials very well by neural network. We dicuss between the characteristic of wear debris and the friction coefficient and how the network determines difference in wear debris feature.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.7 no.5
• /
• pp.92-97
• /
• 1998

The morpholgies of the wear particles are directly indicative of wear processes occuring in machinery and their severity. The neural network was applied to identify wear debris generated from the machine driving system. The four parameters(50% volumetric diameter, aspect, roundness and reflectivity) of wear debris are used as inputs to the network and learned the friction condition of five values(material 3, applied load 1, sliding distance 1). It is shown that identification results depend on the ranges of these shape parameters learned. The three kinds of the wear debris had a different patter characteristic and recognized the friction condition and materials very well by artificial neural network. We discussed how the network determines differencee in wear debris feature, and this approach can be applied to foreseeability and decisio for moving condition of the Machine driving system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.5
• /
• pp.2610-2616
• /
• 2014

An ejector is a kind of pump which is using pressure energy of high pressure fluid. This study aims to investigate performance influencing according to change the ejector mixing section shape using CFD simulation by Finite Volume Method. Optimum conditions were suggested 3 kind of variable such as nozzle diameter, nozzle length, distance from nozzle tip to the diffuser inlet. The results, It was confirmed that the diameter of the nozzle was the greatest effect in performance of the ejector. The diameter of the nozzle get smaller, mixing ratio was increased. On the other hand, nozzle length, distance from nozzle tip to the diffuser inlet had little effect on performance. It was proposed specific Mixing section, Nozzel diameter 23.8mm using the Artificial Neural Network.

• Journal of Korean Society of Water and Wastewater
• /
• v.27 no.4
• /
• pp.413-428
• /
• 2013

In this study, Ant Colony Algorithm(ACO) was used for optimal model. ACO which are metaheuristic algorithm for combinatorial optimization problem are inspired by the fact that ants are able to find the shortest route between their nest and food source. For applying the model to water distribution systems, pipes, tanks(reservoirs), pump construction and pump operation cost were considered as object function and pressure at each node and reservoir level were considered as constraints. Modified model from Ostfeld and Tubaltzev(2008) was verified by applying 2-Looped, Hanoi and Ostfeld's networks. And sensitivity analysis about ant number, number of ants in a best group and pheromone decrease rate was accomplished. After the verification, it was applied to real water network from S water treatment plant. As a result of the analysis, in the Two-looped network, the best design cost was found to $419,000 and in the Hanoi network, the best design cost was calculated to $6,164,384, and in the Ostfeld's network, the best design cost was found to $3,525,096. These are almost equal or better result compared with previous researches. Last, the cost of optimal design for real network, was found for 66 billion dollar that is 8.8 % lower than before. In addition, optimal diameter for aged pipes was found in this study and the 5 of 8 aged pipes were changed the diameter. Through this result, pipe construction cost reduction was found to 11 percent lower than before. And to conclusion, The least cost design model on water distribution system was developed and verified successfully in this study and it will be very useful not only optimal pipe change plan but optimization plan for whole water distribution system.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.6
• /
• pp.1-9
• /
• 2000

This paper presents a Cluster Oriented Multistage Interconnection Network called COMR. COMR can be constructed suitable for the parallel application with localized communication by providing the shortcut path inside the processor-memory cluster which has frequent data communication. We evaluate the performance of COMR with respect to probability of acceptance, bandwidth, cost-effectiveness and average distance under varying degrees of localized communication. According to the result of analysis for performance evaluation, COMR shows higher performance than the regular MINs of the same network size in the highly localized communication. In the worst case, the diameter of an N$\times$N COMR is only n+1 which has only one stage more as compared the MIN with the same network size. Therefore COMR can be used as an attractive interconnection network for parallel applications with not only the localized communication distribution but also the uniform distribution in shared-memory multiprocessor system.

• Design & Manufacturing
• /
• v.17 no.4
• /
• pp.72-78
• /
• 2023

Injection molding is a process widely used in various industries because of its high production speed and ease of mass production during the plastic manufacturing process, and the product is molded by injecting molten plastic into the mold at high speed and pressure. Since process conditions such as resin and mold temperature mutually affect the process and the quality of the molded product, it is difficult to accurately predict quality through mathematical or statistical methods. Recently, studies to predict the quality of injection molded products by applying artificial neural networks, which are known to be very useful for analyzing nonlinear types of problems, are actively underway. In this study, structural optimization of neural networks was conducted by applying multi-task learning techniques according to the characteristics of the input and output parameters of the artificial neural network. A structure reflecting the characteristics of each process step was applied to the input parameters, and a structure reflecting the quality characteristics of the injection molded part was applied to the output parameters using multi-tasking learning. Building an artificial neural network to predict the three qualities (mass, diameter, height) of injection-molded product under six process conditions (melt temperature, mold temperature, injection speed, packing pressure, pacing time, cooling time) and comparing its performance with the existing neural network, we observed enhancements in prediction accuracy for mass, diameter, and height by approximately 69.38%, 24.87%, and 39.87%, respectively.

• Journal of Korea Multimedia Society
• /
• v.17 no.6
• /
• pp.716-724
• /
• 2014

The pancake graph is node symmetric and is utilized on the data sorting algorithm. We propose a new half pancake graph that improve pancake graph's network cost. The half pancake degree is approximately half of pancakes degree and diameter is 3n+4. The pancake graph's network cost is $O(1.64n^2)$ and half pancake's is $O(1.5n^2)$. Additionally half pancake graph is sub graph of pancake graph. As this result, The several algorithms developed in pancake graph has the advantage of leverage on the pancake by adding constant cost.

• Tribology and Lubricants
• /
• v.11 no.3
• /
• pp.24-30
• /
• 1995

This paper was undertaken to recognize the pattern of the wear debris by neural network as a link for the development of diagnosis system for movable condition of the lubricated machine surface. The wear test was carried out under different experimental conditions using the wear test device was made in laboratory and wear testing specimen of the pin-on-disk type were rubbed in paraffine series base oil, by varying applied load, sliding distance and mating material. The neural network has been used to pattern recognition of four parameter (diameter, elongation, complex and contrast) of the wear debris and learned the friction condition of five values (material 3, applied load 1, sliding distance 1). The three kinds of the wear debris had a different pattern characteristic and recognized the friction condition and materials very well by the neural network. The characteristic parameter of the large wear debris over a few micron size enlarged recognition ability.

• Proceedings of the KSME Conference
• /
• 2001.11b
• /
• pp.365-370
• /
• 2001

In order to minimize unstable flow occurred at a multiblade fan/scroll system, optimal angle and shape of cut-off was determined by using two-dimensional turbulent fluid field analyses and neural network. The results of CFD analyses were used for learning as data of input and output of neural network. After learning neural network optimization process was accomplished for design variables, the angle and the shape of cut-off, in the design domain. As a result of optimization, the optimal angle and shape were obtained as 71 and 0.092 times the outer diameter of impeller, respectively, which are very similar values to previous studies. Finally, it was verified that the fluid field is very stable for optimal angle and shape of cut-off by two-dimensional CFD analysis.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 1997.10a
• /
• pp.135-144
• /
• 1997

This wear debris can be harvested from the lubricants of operating machinery and its morphology is directly related to the damage to the interacting surfaces from which the particles originated. The morphologies of the wear particles are therefore directly indica- rive of wear processes occuring in machinery and their severity. The neural network was applied to identify wear debris generated from the lubricated moving system. The four parameter(50% volumetric diameter, aspect, roundness and reflectivity) of wear debris are used as inputs to the network and learned the friction condition of five values(material 3, applied load 1, sliding distance 1). It is shown that identification results depend on the ranges of these shape parameter learned. The three kinds of the wear debris had a different pattern characteristic and recognized the friction condition and materials very well by neural network. We dicuss how the network determines difference in wear debris feature, and this approach can be applied to condition diagnosis of the lubricated moving system.