• Design & Manufacturing
• /
• v.16 no.3
• /
• pp.1-8
• /
• 2022

In this study, an artificial neural network(ANN) was constructed to establish the relationship between process condition prameters and the qualities of the injection-molded product in the injection molding process. Six process parmeters were set as input parameter for ANN: melt temperature, mold temperature, injection speed, packing pressure, packing time, and cooling time. As output parameters, the mass, nominal diameter, and height of the injection-molded product were set. Two learning structures were applied to the ANN. The single-task learning, in which all output parameters are learned in correlation with each other, and the multi-task learning structure in which each output parameters is individually learned according to the characteristics, were constructed. As a result of constructing an artificial neural network with two learning structures and evaluating the prediction performance, it was confirmed that the predicted value of the ANN to which the multi-task learning structure was applied had a low RMSE compared with the single-task learning structure. In addition, when comparing the quality specifications of injection molded products with the prediction values of the ANN, it was confirmed that the ANN of the multi-task learning structure satisfies the quality specifications for all of the mass, diameter, and height.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.151-160
• /
• 2024

Artificial Neural Networks that enabled Artificial Intelligence are being used in many fields. However, the application to mechanical structures has several problems and research is incomplete. One of the problems is that it is difficult to secure a large amount of data necessary for learning Artificial Neural Networks. In particular, it is important to detect and recognize external forces and forces for safety working and accident prevention of mechanical structures. This study examined the possibility by applying the Current Neural Network of Artificial Neural Networks to detect and recognize the load on the machine. Tens of thousands of data are required for general learning of Recurrent Neural Networks, and to secure large amounts of data, this paper derives load data from ANSYS structural analysis results and applies a stacked auto-encoder technique to secure the amount of data that can be learned. The usefulness of Stacked Auto-Encoder data was examined by comparing Stacked Auto-Encoder data and ANSYS data. In addition, in order to improve the accuracy of detection and recognition of load data with a Recurrent Neural Network, the optimal conditions are proposed by investigating the effects of related functions.

• Explosives and Blasting
• /
• v.28 no.2
• /
• pp.17-27
• /
• 2010

With the development of modern society, there have been great technical advances, and the meaning, shape, and type of preservation objects have also become diverse. However, the legislation of executives established in 1961 has nt yet been revised realistically. Thatses administrative problems related to the usge and storage of explosives. In this study, the cases of civilian's question and thought that had been submitted to the government agency were surveyed. In order to analyze the effects of preservation object, ENPro3.1, which is a simulation program to analyze the sound pressure, was used to estimate the blast pressure when a magazine containing preservation objects exploded. With the damage due to the blast pressure, the problem with the safe distance depending on the preservation object levels was investigated. From the investigation, the blast pressures in the two cases with the artificial structures at the real distance 309 m and without the artificial structures at the legitimate standard space distance 440 m, were found to be 123 dB(L) and 138 dB(L), respectively. That means the influence of blast pressure in shorter distance with artificial structures is 15 dB(L) lower than longer distance without them. Therefore, it is recommended to apply the preservation distance based on the engineering analysis with a consideration of surrounding environment.

• Journal of the Korean Geographical Society
• /
• v.42 no.1 s.118
• /
• pp.121-132
• /
• 2007

This paper examines the spatial and temporal variability in the water depth caused by artificial structures in Geum Estuary of South Korea. Water depth data set extracted from marine maps of 1979, 1990, 1996 and 2004 were used in a GIS to derive volumetric estimates of gains and losses of sedimentary material. Artificial structures caused above 2m in water depth to be shallow between 1979 and 2002 in the estuary system, particularly through disturbance of a natural transport in suspended sediment concentrations. The mutt significant change in suspended sediment transport were observed in area affected by embankment for fresh water, inducing the water depth shallower than before in almost 80% of the area. This was probably because of an continuous abundant mud supply from coastal river oven after blocking the fresh water. The spatial analysis made it possible to identify area wide patterns of water depth change subject to many different type of artificial structures, which tanner be acquired by traditional field sampling. It is anticipated thai this research could be used as a valuable reference to confirm the outputs from past field researches for sedimental process in more visual and quantitative manner.

• Journal of Korean Association for Spatial Structures
• /
• v.18 no.2
• /
• pp.11-14
• /
• 2018

• Smart Structures and Systems
• /
• v.15 no.4
• /
• pp.1139-1158
• /
• 2015

This paper proposes an efficient system identification method for modeling nonlinear behavior of civil structures. This method is developed by integrating three different methodologies: principal component analysis (PCA), artificial neural networks, and fuzzy logic theory, hence named PANFIS (PCA-based adaptive neuro-fuzzy inference system). To evaluate this model, a 3-story building equipped with a magnetorheological (MR) damper subjected to a variety of earthquakes is investigated. To train the input-output function of the PANFIS model, an artificial earthquake is generated that contains a variety of characteristics of recorded earthquakes. The trained model is also validated using the1940 El-Centro, Kobe, Northridge, and Hachinohe earthquakes. The adaptive neuro-fuzzy inference system (ANFIS) is used as a baseline. It is demonstrated from the training and validation processes that the proposed PANFIS model is effective in modeling complex behavior of the smart building. It is also shown that the proposed PANFIS produces similar performance with the benchmark ANFIS model with significant reduction of computational loads.

• Earthquakes and Structures
• /
• v.14 no.5
• /
• pp.425-436
• /
• 2018

The design of seismically isolated structures considering the stochastic nature of excitations, base isolators' design parameters, and superstructure properties requires robust reliability analysis methods to calculate the failure probability of the entire system. Here, by applying artificial neural networks, we proposed a robust technique to accelerate the estimation of failure probability of equipped isolated structures. A three-story isolated building with susceptible facilities is considered as the analytical model to evaluate our technique. First, we employed a sensitivity analysis method to identify the critical sources of uncertainty. Next, we calculated the probability of failure for a particular set of random variables, performing Monte Carlo simulations based on the dynamic nonlinear time-history analysis. Finally, using a set of designed neural networks as a surrogate model for the structural analysis, we assessed once again the probability of the failure. Comparing the obtained results demonstrates that the surrogate model can attain precise estimations of the probability of failure. Moreover, our proposed approach significantly increases the computational efficiency corresponding to the dynamic time-history analysis of the structure.

• Journal of the Korean Institute of Navigation
• /
• v.17 no.1
• /
• pp.61-78
• /
• 1993

Large offshore structure are to be considered for oil storage facilities , marine terminals, power plants, offshore airports, industrial complexes and recreational facilities. Some of them have already been constructed. Some of the envisioned structures will be of the artificial-island type, in which the bulk of structures may act as significant barriers to normal waves and the prediction of the wave intensity will be of importance for design of structure. The present study deals wave scattering problem combining reflection and diffraction of waves due to the shape of the impermeable rigid upright structure, subject to the excitation of a plane simple harmonic wave coming from infinity. In this study, a finite difference technique for the numerical solution is applied to the boundary integral equation obtained for wave potential. The numerical solution is verified with the analytic solution. The model is applied to various structures, such as the detached breakwater (3L${\times}$0.1L), bird-type breakwater(318L${\times}$0.17L), cylinder-type and crescent -type structure (2.89L${\times}$0.6L, 0.8L${\times}$0.26L).The result are presented in wave height amplification factors and wave height diagram. Also, the amplification factors across the structure or 1 or 2 wavelengths away from the structure are compared with each given case. From the numerical simulation for the various boundary types of structure, we could figure out the transformation pattern of waves and predict the waves and predict the wave intensity in the vicinity of large artificial structures.

• Computers and Concrete
• /
• v.7 no.3
• /
• pp.271-283
• /
• 2010

Testing of ultrasonic pulse velocity (UPV) is one of the most popular and actual non-destructive techniques used in the estimation of the concrete properties in structures. In this paper, artificial neural network (ANN) approach has been proposed for the evaluation of relationship between concrete compressive strength, UPV, and density values by using the experimental data obtained from many cores taken from different reinforced concrete structures with different ages and unknown ratios of concrete mixtures. The presented approach enables to find practically concrete strengths in the reinforced concrete structures, whose records of concrete mixture ratios are not yet available. Thus, researchers can easily evaluate the compressive strength of concrete specimens by using UPV values. The method can be used in conditions including too many numbers of the structures and examinations to be done in restricted time duration. This method also contributes to a remarkable reduction of the computational time without any significant loss of accuracy. Statistic measures are used to evaluate the performance of the models. The comparison of the results clearly shows that the ANN approach can be used effectively to predict the compressive strength of concrete by using UPV and density data. In addition, the model architecture can be used as a non-destructive procedure for health monitoring of structural elements.

• Journal of Ecology and Environment
• /
• v.32 no.2
• /
• pp.83-86
• /
• 2009

We conducted a landscape analysis to investigate the possibility of adverse effects of anthropogenic light sources, such as roads and residential buildings, on Lethocerus deyrollei on Jeju Island, Wetlands inhabited by L. deyrollei had fewer anthropogenic structures within a 3 km radius that had the potential to produce artificial light at night than wetlands not inhabited by L. deyrollei, In particular, the presence of artificial lights within a 1 km radius appears to reduce the probability of inhabitation by L. deyrollei, Our results suggest that artificial light sources may be critical determinants of L. deyrollei inhabitation patterns in a landscape, and that habitats that have a buffer area of at least 600$\sim$700 m radius free from residential buildings are the most appropriate habitats for L. deyrollei.