• Nuclear Engineering and Technology
• /
• v.53 no.1
• /
• pp.148-163
• /
• 2021

Timely fault identification is important for safe and reliable operation of the electric valve system. Many research works have utilized different data-driven approach for fault diagnosis in complex systems. However, they do not consider specific characteristics of critical control components such as electric valves. This work presents an integrated shallow-deep fault diagnostic model, developed based on signals extracted from DN50 electric valve. First, the local optimal issue of particle swarm optimization algorithm is solved by optimizing the weight search capability, the particle speed, and position update strategy. Then, to develop a shallow diagnostic model, the modified particle swarm algorithm is combined with support vector machine to form a hybrid improved particle swarm-support vector machine (IPs-SVM). To decouple the influence of the background noise, the wavelet packet transform method is used to reconstruct the vibration signal. Thereafter, the IPs-SVM is used to classify phase imbalance and damaged valve faults, and the performance was evaluated against other models developed using the conventional SVM and particle swarm optimized SVM. Secondly, three different deep belief network (DBN) models are developed, using different acoustic signal structures: raw signal, wavelet transformed signal and time-series (sequential) signal. The models are developed to estimate internal leakage sizes in the electric valve. The predictive performance of the DBN and the evaluation results of the proposed IPs-SVM are also presented in this paper.

• 한국연소학회:학술대회논문집
• /
• 2015.12a
• /
• pp.325-326
• /
• 2015

Combustion of coke grains in a pellet used to be modeled using the shrinking core model in the previous indurator simulations. This leads to the discussions about its propriety due to the fundamental assumptions of the model inconsistent with the particle characteristics. The current study presents the grain model as an improvemen, and the differently used reaction models are compared. In addition, the simulations assuming changed particle conditions are conducted to display the effects of using the grain model.

• 한국연소학회:학술대회논문집
• /
• 2006.04a
• /
• pp.181-188
• /
• 2006

Operation parameters for large scale industrial facility such as iron making plant are carefully selected through elaborate tests and monitoring rather than through a mathematical modeling. One of the recent progresses for better energy utilization in iron ore sintering process is the distribution pattern of fuel inside a macro particle which is formed with fines of iron ore, coke and limestone. Results of model tests which have been used as a basis for the improved operation in the field are introduced and a theoretical modeling study is presented to supplement the experiment-based approach with fundamental arguments of physical modeling, which enables predictive computation beyond the limited region of tests and adjustment. A single fuel particle model along with one-dimensional bed combustion model of solid particles are utilized, and thermal processes of combustion and heat transfer are found to be dominant consideration in the discussions of productivity and energy utilization in the sintering process.

• Journal of Korean Society of Water and Wastewater
• /
• v.19 no.5
• /
• pp.632-638
• /
• 2005

Membrane fouling index such as Silt Density Index (SDI) and Modified Fouling Index (MFI) is an important parameter in design of the integrated RO/NF membrane processes for drinking water treatment. In this study, the effect of particle, membrane and feed water characteristics on membrane fouling index were investigated systematically. Higher fouling index values were observed when filtering suspensions with smaller particle size and higher feed particle concentration. Larger membrane resistance due to smaller pore size resulted in an increased membrane fouling index. The variations of feed water hardness and TDS concentrations did not show any impact on fouling index, suggesting that there were no significant colloidal interactions among particles and thus the porosity of particle cake layer accumulated on the membrane surface could be assumed to be 0.36 according to random packing density. Based on the experimental observations, fundamental membrane fouling index model was developed using Happel Cell. The effect of primary model parameters including particle size ($a_p$), particle concentration ($C_o$), membrane resistance ($R_m$), were accurately assessed without any fitting parameters, and the prediction of membrane fouling index such as MFI exhibited very good agreement with the experimental results.

• Journal of Distribution Science
• /
• v.11 no.3
• /
• pp.5-11
• /
• 2013

Purpose - Going concern is one of fundamental concepts in accounting and auditing and sometimes the assessment of a company's going concern status that is a tough process. Various going concern prediction models' based on statistical and data mining methods help auditors and stakeholders suggested in the previous literature. Research design - This paper employs a data mining approach to prediction of going concern status of Iranian firms listed in Tehran Stock Exchange using Particle Swarm Optimization. To reach this goal, at the first step, we used the stepwise discriminant analysis it is selected the final variables from among of 42 variables and in the second stage; we applied a grid-search technique using 10-fold cross-validation to find out the optimal model. Results - The empirical tests show that the particle swarm optimization (PSO) model reached 99.92% and 99.28% accuracy rates for training and holdout data. Conclusions - The authors conclude that PSO model is applicable for prediction going concern of Iranian listed companies.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.27-30
• /
• 2012

One of the most fundamental functions required for an intelligent agent is to estimate its current position based upon uncertain sensor data. In this paper, we explain the implementation of a robot localization system using Particle filters, which are the most effective one of the probabilistic localization methods, and then present the result of experiments for evaluating the performance of our system. Through conducting experiments to compare the effect of the noise-free model with that of the noisy state transition model considering inherent errors of robot actions, we show that it can help improve the performance of the Particle filter localization to apply a state transition model closely approximating the uncertainty of real robot actions.

• Nuclear Engineering and Technology
• /
• v.54 no.12
• /
• pp.4798-4808
• /
• 2022

The porous corrosion deposits (known as CRUD) adhered to the cladding have an important effect on the heat transfer from fuel rods to coolant in PWRs. The vapor film is the main constituent in the two-phase film boiling model. This paper presents a vapor film thickness correlation, associated with CRUD porosity, CRUD chimney density, CRUD particle size, CRUD thickness and heat flux. The dependences of the vapor film thickness on the various influential factors can be intuitively reflected from this vapor film thickness correlation. The temperature, pressure, and boric acid concentration distributions in CRUD can be well predicted using the two-phase film boiling model coupled with the vapor film thickness correlation. It suggests that the vapor thickness correlation can estimate the vapor film thickness more conveniently than the previously reported vapor thickness calculation methods.

• Journal of the Mineralogical Society of Korea
• /
• v.15 no.2
• /
• pp.95-103
• /
• 2002

The object of this study was to interpret the ralationship between expandability (% $S_{XRD}$), MacEwan crystallite thickness ( $N_{CSD}$), and mean fundamental particle thickness ( $N_{F}$ ) in illite-semctite mixed layer (I-S), quantitatively. This interpretation was extracted from comparison of two structural models (MacEwan crystallite model and fundamental particle model) of I-S mixed layers. In I-S structure, % $S_{XRD}$, $N_{CSD}$, and $N_{F}$ are not independent parameters but are related to each others by particular geometric relations. % $S_{XRD}$ is dependent on $N_{CSD}$ by short-stack effect, whereas, % $S_{XRD}$ and $N_{F}$ have relation to smectite interlayer number (Ns)=( $N_{F-}$1)/(100%/% $S_{XRD-}$ $N_{F}$ . Therefore, % $S_{XRD}$ and $N_{F}$ should satisfy a specific physical condition, 1< $N_{F}$ <100%/% $S_{XRD}$, because $N_{s}$ is positive. Based on this condition, this study suggested % $S_{XRD}$ vs $N_{F}$ diagram which can be used to interpret % $S_{XRD}$, $N_{F}$ , $N_{S}$ , and ordering, quantitatively. The diagram was examined by XRD data for I-S samples from Ceumseongsan volcanic complex, Korea. I-S samples showed that $N_{F}$ departs from the physical upper-limit ( $N_{F}$ =100%/% $S_{XRD}$) with decrease in % $S_{XRD}$. This phenomenon may happen due to decrease of stacking-capability of fundamental particles with their thickening.g.s with their thickening.g.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.54-66
• /
• 2020

Nowadays, the broad availability of cameras and embedded systems makes the application of computer vision very promising as a supporting technology for intelligent transportation systems, particularly in the field of vehicle tracking. Although there are several existing trackers, the limitation of using low-cost cameras, besides the relatively low processing power in embedded systems, makes most of these trackers useless. For the tracker to work under those conditions, the video frame rate must be reduced to decrease the burden on computation. However, doing this will make the vehicle seem to move faster on the observer's side. This phenomenon is called the fast motion challenge. This paper proposes a tracker called dynamic swarm particle (DSP), which solves the challenge. The term particle refers to the particle filter, while the term swarm refers to particle swarm optimization (PSO). The fundamental concept of our method is to exploit the continuity of vehicle dynamic motions by creating dynamic models based on PSO. Based on the experiments, DSP achieves a precision of 0.896 and success rate of 0.755. These results are better than those obtained by several other benchmark trackers.

• International Journal of Highway Engineering
• /
• v.19 no.6
• /
• pp.23-30
• /
• 2017

PURPOSES : In this paper, the applicability of DEM to a coarse graining method was evaluated by simulating a series of minicone tests for cement paste. METHODS : First, the fundamental physical quantities that are used in a static liquid bridge model were presented with three basic quantities based on the similarity principle and coarse graining method. Then, the scale factors and surface tensions for six different sizes of particles were determined using the relationship between the physical quantities and the basic quantities. Finally, the determined surface tensions and radii were utilized to simulate the fluidal behavior of cement paste under a minicone test condition, and the final shape of the cement paste with reference DEM particle radii was compared with the final shape of the others. RESULTS : The simulations with adjusted surface tensions for five different radii of particles and surface tension showed acceptable agreement with the simulation with regard to the reference size of the particle, although disagreement increases as the sizes of the particle radii increase. It seems reasonable to increase the particle radii by at least 0.196 cm considering the computational time reduction of 162 min. CONCLUSIONS : The coarse graining method based on the similarity principle is applicable for simulating the behavior of fluidal materials when the behavior of the materials can be described by a static liquid bridge model. However, the maximum particle radius should be suggested by considering not only the scale factor but also the relationship of the particle size and number with the radius of the curve of the boundary geometry.