• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.65-68
• /
• 1996

Robotic manipulators have become increasingly important in the field of flexible automation. High speed and high-precision trajectory tracking are indispensable capabilities for their versatile application. The need to meet demanding control requirement in increasingly complex dynamical control systems under significant uncertainties, leads toward design of intelligent manipulation robots. This paper presents a new approach to the design of neural control system using digital signal processors in order to improve the precision and robustness. The TMS32OC31 is used in implementing real time neural control to provide an enhanced motion control for robotic manipulators. In this control scheme, the networks introduced are neural nets with dynamic neurons, whose dynamics are distributed over all the, network nodes. The nets are trained by the distributed dynamic back propagation algorithm. The proposed neural network control scheme is simple in structure, fast in computation, and suitable for implementation of real-time, control. Performance of the neural controller is illustrated by simulation and experimental results for a SCARA robot.

• Transactions on Control, Automation and Systems Engineering
• /
• v.1 no.1
• /
• pp.62-68
• /
• 1999

FCM(Fuzzy Cognitive Map) is proposed for representing causal reasoning. Its structure allows systematic causal reasoning through a forward inference. Authors have already proposed a diagnostic system based on FCM to utilized to identify the true origin of fault by on-line pattern diagnosis. In FCM based fault diagnosis, Temporal Associative Memories (TAM) recall of FCM is utilized to identify the true origin of fault by on-line pattern match where predicted pattern sequences obtained from TAM recall of fault FCM models are compared with actually observed ones. In engineering processes, the propagation delays are induced by the dynamics of processes and may vary with variables involved. However, disregarding such propagation delays in FCM-based fault diagnosis may lead to erroneous diagnostic results. To solve the problem, a concept of FTCM(Fuzzy Time Cognitive Map) is introduced into FCM-based fault diagnosis in this work. Expecially, translation method of FTCM makes it possible to diagnose the fault for some discrete time. Simulation studies through two-tank system is carried out to verify the effectiveness of the proposed diagnostic scheme.

• Proceedings of the KSME Conference
• /
• 2000.04a
• /
• pp.73-78
• /
• 2000

On this study, the fatigue crack propagation of super duplex stainless steel is investigated in conditions of various volume fraction of austenite phase by changing heat treatment temperature. And we analysed acoustic emission signals during the fatigue test by time-frequency analysis methods. As the temperature of heat treatment increased, volume fraction of austenite decreased and coarse grain was obtained. The specimen heat treated at $1200^{\circ}C$ had longer fatigue life and slower rate of crack growth. As a result of time-frequency analyze of acoustic emission signals during fatigue test, main frequency was $200{\sim}300kHz$ having no correlation with heat treatment and crack length, and 500kHz was obtained by dimple and separate of inclusion

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.05b
• /
• pp.169-172
• /
• 2004

We present the basic properties of a superconducting current limiting fuse (SCLF) based on YBCO/Au films. The SCLFs consists of YBCO stripes covered with Au layers for current shunt. Under the source voltage of 100 $V_{rms}$, the longer the duration time of fault current was, the shorter its discharge time was. The duration time of fault current and its discharge time were reduced by increased voltages in the range of 200 - 300 $V_{rms}$. We thought that this was because the quench propagation was limited by local melting generated with higher voltage.

• International Journal of Highway Engineering
• /
• v.7 no.3 s.25
• /
• pp.63-69
• /
• 2005

For many years, the compressive strength of concrete has been regarded as an important index in determining concrete pavement quality. The compressive strength of the sample cores from the field has been used as quality index of concrete pavement. However, this process is time consuming and requires a lot of labor. Recently, the M-E Design Methodology in the pavement design based on the elastic modulus has been adopted. Therefore, several NDT methodologies have been adopted for QA/QC in the field and for the pavement design. Among various NDT methods, the wave propagation method can be used to measure the elastic modulus of concrete because the wave velocity is directly related to the elastic modulus. Therefore, in this study the wave propagation method was used for estimating the concrete modulus. The relationship between the compressive strength measured in he laboratory and the elastic modulus measured by the wave propagation method was analyzed, and the compressive strength was estimated from the elastic modulus for various mix types. The results showed that the relationship between the elastic modulus and the compressive strength was observed and the relationship varied depending on the aggregate types.

• Korean Chemical Engineering Research
• /
• v.55 no.5
• /
• pp.629-637
• /
• 2017

Severe dust explosions occurred frequently in food processing industries and explosion damage increase by flame propagation in pipes or plants. However there are few fire explosion data available due to various powder characteristics. We investigated the characteristics of ignition and explosion on sugar, cornstarch and flour dust with high frequency accidents and high social demand. The measurements showed the median diameter of 27.56, 14.76, $138.5{\mu}m$ and ignition temperature has been investigated using by thermo-gravimetric analysis (TGA) and differential scanning calorimeter (DSC). The maximum explosion pressure ($P_m$) and dust explosion index ($K_{st}$) of sugar, cornstarch and flour are 7.6, 7.6, 6.1 bar and 153, 133, 61 [$m{\cdot}bar/s$], respectively. The flame propagation time in duct was calculated in order to evaluate the damage increase due to flame propagation during dust explosion. The explosion hazard increase due to flame propagation was higher in the order of sugar, flour and cornstarch dust.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.1
• /
• pp.155-163
• /
• 2019

The knowledge about drought propagation is very important in accurate estimation of hydrological drought characteristics and efficient development of early warning system. This study investigated a probabilistic relationship of drought propagation based on Bayesian network model for historic period and for future projection under climate change scenario RCP 8.5 over the Han River basin. The results revealed that the propagation rate and lag time have increasing and decreasing trends from the historic period of 1967-2013 to the future periods of 2014-2053 and 2054-2100 under climate change, respectively. The probabilistic results of Bayesian model revealed that the probability of occurrence of lag time varied spatially and decreased when the intensity of meteorological drought changed from moderate to severe and extreme condition during 1967-2013. The values of probability increased in the first future period of 2014-2053 in several sub-basins and slight decreased in the second period of 2054-2100. The proposed probabilistic results will be useful for the decision makers to develop related policies with an appropriate insight toward the future drought status.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.15 no.1
• /
• pp.13-24
• /
• 2013

Various elastic wave-based site investigation methods have been used to characterize subsurface ground because the dynamic properties can be correlated with various geotechnical parameters. Although the inherent spatial variability of the geotechnical parameters affects the P-wave propagation characteristics, ground heterogeneity has not been considered as an influential factor. Thus, the effect of heterogeneous ground on the travel-time shift and wavefront characteristics of elastic waves through stochastic numerical analyses is investigated in this study. The effects of the relative correlation lengths and relative propagation distances on the travel-time shift of P-waves considering various intensities of ground heterogeneity were investigated. Heterogeneous ground fields of stiffness (e.g., the coefficient of variation = 10 ~ 40%) were repeatedly realized in numerical finite difference grids using the turning band method. Monte Carlo simulations were undertaken to simulate P-wave propagation in heterogeneous ground using a finite difference method-based numerical approach. The results show that the disturbance of the wavefront becomes more significant with stronger heterogeneity and induces travel-time delays. The relative correlation lengths and propagation distances are systematically related to the travel-time shift.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.1
• /
• pp.49-54
• /
• 2013

Japan and South Korea since 2004 until now for the broadcast channel interference, by measuring the ongoing conflict are expected to prepare for the future, but Korea's preparation are not enough. In this study, it is pointed that cause of the interference through channel environmental analysis, and effective application of propagation prediction model was carried out between neighboring countries. Between Korea and Japan, radio duct occurs on hold due to changes in the refractive gradient, and comfirmed occurrence of broadcasts interference. The results are presented that 1% time variable, -91.80 [N-units/km], 10% time variable, -43.92 [N-units/km], 50% time variable, -586.19 [N-units/km], for effective refractive gradient. Proposed refractive gradient could contribute to actual radio propagation prediction.