• Korean Chemical Engineering Research
• /
• v.48 no.6
• /
• pp.717-724
• /
• 2010

The flash point is one of the most important physical properties used to determine the potential for fire and explosion hazards of flammable liquids. Despite the needs of the experimental flash point data for the design and construction of chemical plants, there is often a significant gap between the demands for the data and their availability. This study have built and compared two models of partial least squares(PLS) and support vector machine(SVM) to predict the experimental flash points of 893 organic compounds out of DIPPR 801. As the independent variables of the models, 65 functional groups were chosen based on the group contribution method that was oriented from the assumption that each fragment of a molecule contributes a certain amount to the value of its physical property, and the logarithm of molecular weight was added. The prediction errors calculated from cross-validation were employed to determine the optimal parameters of two models. And, an optimization technique should be used to get three parameters of SVM model. This work adopted particle swarm optimization that is one of heuristic optimization methods. As the selection of training data can affect the prediction performance, 100 data sets of randomly selected data were generated and tested. The PLS and SVM results of the average absolute errors for the whole data range from 13.86 K to 14.55 K and 7.44 K to 10.26 K, respectively, indicating that the predictive ability of the SVM is much superior than PLS.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.5
• /
• pp.639-650
• /
• 2022

In areas where large-scale sediment transport occurs, it is important to apply appropriate countermeasure method because the phenomenon tends to accelerate by time duration. Among the various countermeasure methods applied so far, beach nourishment needs to be reviewed as an erosion prevention measure because the erosion pattern is mitigated and environmentally friendly depending on the particle size. In the case of beach nourishment. a detailed review is required to determine the size, range, etc., of an appropriate particle diameter. In this study, we investigated the characteristics of the related topographic change using the change in the particle size of nourishment materials, the application of partial area, and the condition under the coexistence of waves and wind as variables because those factors are hard to be analyzed and interpreted within results and limitation of that the existing numerical models are not able to calculate and result out so that it is required that phenomenon or efforts are reviewed at the same time through physical model experiments, field monitoring and etc. So we attempt to reproduce the tendency of beach erosion and deposition and predict possible phenomena in the future using machine learning techniques for phenomena that it is not able to be interpreted by numerical models. we used the hydraulic experiment results for the training data, and the accuracy of the prediction results according to the change in the training method was simultaneously analyzed. As a result of the study it was found that topographic changes using machine learning tended to be similar to those of previous studies in short-term predictions, but we also found differences in the formation of scour and sandbars.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1167-1181
• /
• 2021

In relation to the algae bloom, four types of blue-green algae that emit toxic substances are designated and managed as harmful Cyanobacteria, and prediction information using a physical model is being also published. However, as algae are living organisms, it is difficult to predict according to physical dynamics, and not easy to consider the effects of numerous factors such as weather, hydraulic, hydrology, and water quality. Therefore, a lot of researches on algal bloom prediction using machine learning have been recently conducted. In this study, the characteristic importance of water quality factors affecting the occurrence of Cyanobacteria harmful algal blooms (CyanoHABs) were analyzed using the random forest (RF) model for Bohyeonsan Dam and Yeongcheon Dam located in Yeongcheon-si, Gyeongsangbuk-do and also predicted the occurrence of harmful blue-green algae using the machine learning and deep learning models and evaluated their accuracy. The water temperature and total nitrogen (T-N) were found to be high in common, and the occurrence prediction of CyanoHABs using artificial neural network (ANN) also predicted the actual values closely, confirming that it can be used for the reservoirs that require the prediction of harmful cyanobacteria for algal management in the future.

• International Journal of Contents
• /
• v.8 no.2
• /
• pp.89-96
• /
• 2012

Scientific analysis of crime hot spots is essential in preventing and/or suppressing crime. However, results could be different depending on the analytic methods, which highlights the importance of choosing adequate tools. The purpose of this study was to introduce two advanced techniques for detecting crime hot spots, GAM and Local Moran's I, hoping for more police agencies to adopt better techniques.GAM controls for the number of population in study regions, but local Moran's I does not. That is, GAM detects high crime rate areas, whereas local Moran's I identifies high crime volume areas. For GAM, physical disorder was used as a proxy measure for population at risk based on the logic of the broken windows theory. Different regions were identified as hot spots. Although GAM is generally regarded as a more advanced method in that it controls for population, it's usage is limited to only point data. Local Moran's I is adequate for zonal data, but suffers from the unavoidable MAUP(Modifiable Areal Unit Problem).

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.731-734
• /
• 2002

There have been no obvious design criteria of high efficient displacement pump using a dimensionless parameter which can represent many physical aspect of displacement pump could be very useful to estimate displacement pump performance. Many dimensionless analysis methods have been developed in fluid dynamics, machine design and so on. In this study a new dimensionless parameter is developed for estimate displacement pump performance and efficiency, until now to evaluate the performance of displacement pumps which are widely used in industry field, primarily experimental methods have been used. The dimensionless parameter contains many physical information about pump design. For example, they are the relation between flow rate and power, displacement operation displacement and size, inlet and outlet valve size. And the developed dimensionless functions are induced from numerical method.

• Journal of Korea Technical Association of The Pulp and Paper Industry
• /
• v.37 no.3
• /
• pp.33-40
• /
• 2005

In this study, a nano-colloidal silica sol was applied to control the anti-slip property by spraying on kraft paper. Two kinds of nano-colloidal silica sol which have cationic and anionic charge were applied in kraft paper, and the friction and physical strength properties of kraft paper were investigated. The application of colloidal silica sol on wet web in wet-end process by spraying method was tried to improve the friction property and to avoid the general problems of machine contaminations caused by the scattering of sprayed silica particles in dryer part. The physical properties of sheet were also improved by the application of wet web spraying method, and the optimum conditions of wet web spraying operation were closely related with the conditions of pH and electrical charge of wet web and silica sol.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2003.11a
• /
• pp.291-305
• /
• 2003

In this work we developed the closed-loop model of a paper machine during grade change with the intention to provide a reliable dynamic model to be used in the model-based grade change control scheme. During the grade change, chemical and physical characteristics of paper process change with time. It is very difficult to represent these characteristics on-line by using physical process models. In this work, the wet circulation part and the drying section were considered as a single process and closed-loop identification technique was used to develop the grade change model. Comparison of the results of numerical simulations with plant operation data demonstrates the effectiveness of the model identified.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.12
• /
• pp.40-45
• /
• 1999

Electrical damages to critical parts in rotation machinery have caused may machinery failures and hours of costly downtime. The problem of shaft currents generated in non-electrical machines have puzzled both users and manufacturers of these machines. The main solution for preventing electro- magnetic type damage is to demagnetize all of the machinery parts, however this is costly and time consuming. Therefore a thorough investigation into the causes and physical characteristics of electro- magnetic shaft currents is needed. In this paper, the self excitation theory was developed for a simple model, and axial flux Faraday disk machine surrounded by a long solenoid. Experimental tests were conducted to investigate the physical characteristics on an electromagnetic self excitation rig. The theory showed that the directions of both the shaft rotation and the coil turns should e identical if self excitation is to occur. From the tests, the electromagnetic type shaft current had both AC and DC components occurred at all vibration frequencies. This could point to the way to detect small instabilities or natural frequency locations by monitoring shaft currents.

• Journal of Korea Technical Association of The Pulp and Paper Industry
• /
• v.35 no.5
• /
• pp.46-52
• /
• 2003

In this work we developed the closed-loop model of a paper machine during grade change with the intention to provide a reliable dynamic model to be used in the model-based grade change control scheme. During the grade change, chemical and physical characteristics of paper process change with time. It is very difficult to represent these characteristics on-line by using physical process models. In this work, the wet circulation part and the drying section were considered as a single process and closed-loop identification technique was used to develop the grade change model. Comparison of the results of numerical simulations with mill operation data demonstrates the effectiveness of the model identified.

• KIEAE Journal
• /
• v.14 no.1
• /
• pp.39-48
• /
• 2014

In the previous test, the verification of the standard floor impact source was carried out comparing the physical characteristics with living impact sources. The result was appeared the validation of the standard impact source was very low because of differences of physical characteristics. This study aims to evaluate annoyance and loudness of standard impact source which is used for the measurement of floor impact sound, and to compare the annoyance and loudness of living impact sources which are produced in real life. The impact sources considered are tapping machine, tire and impact ball as standard sources, and nine real sources which were chosen from the existing researches. The result showed differences of annoyance and loudness between standard impact sources and living impact sources, which means the standard impact sources may rate the performance of floor system inappropriately. In the future, the rating method should be examined how the standard impact sources are similar with real sources in the point of rating the performance of floor system.