• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.227-233
• /
• 2021

Predictive maintenance has been one of important applications of data science technology that creates a predictive model by collecting numerous data related to management targeted equipment. It does not predict equipment failure with just one or two signs, but quantifies and models numerous symptoms and historical data of actual failure. Statistical methods were used a lot in the past as this predictive maintenance method, but recently, many machine learning-based methods have been proposed. Such proposed machine learning-based methods are preferable in that they show more accurate prediction performance. However, with the exception of some learning models such as decision tree-based models, it is very difficult to explicitly know the structure of learning models (Black-Box Model) and to explain to what extent certain attributes (features or variables) of the learning model affected the prediction results. To overcome this problem, a recently proposed study is an explainable artificial intelligence (AI). It is a methodology that makes it easy for users to understand and trust the results of machine learning-based learning models. In this paper, we propose an explainable AI method to further enhance the explanatory power of the existing learning model by targeting the previously proposedpredictive model [5] that learned data from a core facility (Hyper Compressor) of a domestic chemical plant that produces polyethylene. The ensemble prediction model, which is a black box model, wasconverted to a white box model using the Explainable AI. The proposed methodology explains the direction of control for the major features in the failure prediction results through the Explainable AI. Through this methodology, it is possible to flexibly replace the timing of maintenance of the machine and supply and demand of parts, and to improve the efficiency of the facility operation through proper pre-control.

• Journal of the Korean Institute of Gas
• /
• v.26 no.1
• /
• pp.7-19
• /
• 2022

Hydrogen purification is generally performed through chemical and physical methods. Among various types of purification method PSA(Pressure Swing Adsorption) is widely used with its purification capacity and economic efficiency. In Korea, most of the hydrogen used in automobiles and power generation fuel cells is purified using PSA. Hydrogen produced in petrochemical complexes has difficulties in transportation. The government is planning to install hydrogen extractors that produce hydrogen directly from consumers in connection with the city gas supply chain, and companies are also installing related research and demonstration facilities one after another. Europe and others have recently established safety standards related to PSA and are making efforts for systematic safety management at the construction and operation stage, but domestic safety standards related to PSA are still insufficient. This study aims to identify problems of existing facilities through surveys and risk assessment by companies operating existing PSA, and to prepare domestic technical standards including them in overseas technical standards to promote the safety of new and existing PSA systems.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.4
• /
• pp.353-358
• /
• 2022

Bulky iron-core potential transformers (PT) are installed in a tank of gas insulated switchgears (GIS) for a system voltage measurement in power substations. In this paper, we studied an electronic voltage transformer (EVT) embedded in a spacer for miniaturization, eco-friendliness, and performance improvement of GIS. The prototype EVT consists of a capacitive probe (CP) that can be embedded in a spacer and a voltage Follower with a high input and a low output impedance. The CP was fabricated in the form of a Flexible-PCB to acquire the insulation performance and to withstand vibration and shock during operation. Voltage ratio of the prototype EVT is about 42,270, and the frequency bandwidth of -3 dB ranges from 0.33 Hz to 3.9 MHz. The voltage ratio error evaluated at about 6%, 12% and 18% of the rated voltage of 170 kV was 0.32%, and the phase error was 12.9 minutes. These results were within the accuracy for the class 0.5 specified in IEC 60044-7 and satisfy even in ranges from 80% to 120% of the rated voltage. If the prototype EVT replaces the conventional iron-core potential transformer, it is expected that the height of the GIS could be reduced by 11% and the amount of SF₆ will be reduced by at least 10%.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.169-174
• /
• 2022

The purpose of the study is to research the legal nature and essence of corrupt behavior, as well as the international and national legal aspects of the fight against corruption. The article discloses the relation between the factual results of the operation of anti-corruption normative and legal acts and the goals and objectives for which they were adopted. The effectiveness of the regulatory effect and quality of anti-corruption legislation is determined by the example of the Russian Federation. The article provides an analysis of theoretical aspects of the theory and history of the formation and development of anti-corruption legislation (on the example of Russia and some other countries, as well as international legal norms) giving several practical examples from foreign legislation demonstrating the structure of the system of government bodies battling against corrupt behavior (including its latent forms). The authors suggest that there is a need for a unified conception of information and propaganda support of state anti-corruption activities. This will make it possible to inform the population that the state is actively working to prevent corruption threats and to bring perpetrators to justice, as well as contribute to citizens' trust in the state policy in this area. At the same time, it is necessary to regularly inform the citizens about the provisions of the anti-corruption legislation, explaining the importance of their observance.

• 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.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.2
• /
• pp.94-107
• /
• 2022

Accidents prevention and mitigation is the highest priority of nuclear power plant (NPP) operation, particularly in the aftermath of the Fukushima Daiichi accident, which has reignited public anxieties and skepticism regarding nuclear energy usage. To deal with accident scenarios more effectively, operators must have ample and precise information about key safety parameters as well as their future trajectories. This work investigates the potential of machine learning in forecasting NPP response in real-time to provide an additional validation method and help reduce human error, especially in accident situations where operators are under a lot of stress. First, a base-case SGTR simulation is carried out by the best-estimate code RELAP5/MOD3.4 to confirm the validity of the model against results reported in the APR1400 Design Control Document (DCD). Then, uncertainty quantification is performed by coupling RELAP5/MOD3.4 and the statistical tool DAKOTA to generate a large enough dataset for the construction and training of neural-based machine learning (ML) models, namely LSTM, GRU, and hybrid CNN-LSTM. Finally, the accuracy and reliability of these models in forecasting system response are tested by their performance on fresh data. To facilitate and oversee the process of developing the ML models, a Systems Engineering (SE) methodology is used to ensure that the work is consistently in line with the originating mission statement and that the findings obtained at each subsequent phase are valid.

• Journal of the Korean Institute of Gas
• /
• v.26 no.2
• /
• pp.9-13
• /
• 2022

Electric wheelchairs, the output from the motor is mainly applied to a speed reducer using a power transmission device such as a belt or a chain. However, although a speed reducer using a belt or chain is a simple device, it occupies a lot of space and has a space limitation, so it is not suitable for an electric wheelchair driving part. However, since the speed reducer of the planetary gear type is decelerated on the same axis, the volume can be reduced, so the space constraint is less than that of the belt or chain type reducer. Therefore, in this study, a driving part that can obtain great propulsion with a speed reducer using a planetary gear type was developed through a study on the driving part of a wheelchair that can be switched between manual and electric. Accordingly, the tooth shape of the planetary gear applied to the reducer was designed using the Kisssoft program. In addition, the drive part was designed to be applicable to the existing wheelchair wheels, and the mechanism was optimized for the manual/electric switching principle and operation principle of the drive part. Based on the research contents, the final design and manufacture of the wheelchair reducer drive unit in the form of a planetary gear having one sun gear, two planetary gears and one ring gear was carried out.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.641-648
• /
• 2022

In this study, the performance of the NHPP software reliability model with exponential distribution (Exponential Basic, Inverse Exponential, Lindley, Rayleigh) characteristics was comparatively analyzed, and based on this, the optimal reliability model was also presented. To analyze the software failure phenomenon, the failure time data collected during system operation was used, and the parameter estimation was solved by applying the maximum likelihood estimation method (MLE). Through various comparative analysis (mean square error analysis, true value predictive power analysis of average value function, strength function evaluation, and reliability evaluation applied with mission time), it was found that the Lindley model was an efficient model with the best performance. Through this study, the reliability performance of the distribution with the characteristic of the exponential form, which has no existing research case, was newly identified, and through this, basic design data that software developers could use in the initial stage can be presented.

• Tribology and Lubricants
• /
• v.39 no.4
• /
• pp.139-147
• /
• 2023

Cavitation phenomena observed during the operation of a submerged plain journal bearing (PJB) can affect bearing performance parameters such as dynamic coefficients, whirl frequency ratio, and critical mass. This study presents numerical solutions of the Reynolds equation for steadily and dynamically loaded submerged PJBs with half-Sommerfeld (HS), Reynolds, and Jakobsson-Floberg-Olsson (JFO) cavitation models when the supply pressure is larger or equal to the cavitation pressure. The loads at various eccentricity ratios are identical; however, the attitude angle is approximately 6% smaller when the eccentricity ratio is between 0.2 and 0.7 and the JFO model is used, compared to that when the Reynolds model is used. Dynamic coefficients obtained with the HS and Reynolds model show good agreement with each other, except for k_xz, which is sensitive to changes in the force normal to the rotor weight, and is attributed to the difference in the attitude angle obtained with each cavitation model. Stiffness coefficients are determined using the pressure distribution in the film, and therefore, when the JFO model is used, the direct stiffness coefficients are affected and show opposite signs for most eccentricity ratios. The mass-conservative JFO model can predict at least a 30% smaller critical mass compared to that using the HS and Reynolds models. Thus, the instability analysis results can change based on the cavitation model used in a submerged PJB. The results of this research indicate that the JFO model should be used when designing a rotor system supported by submerged PJBs.

• Research in Community and Public Health Nursing
• /
• v.33 no.4
• /
• pp.357-371
• /
• 2022

Purpose: This study aims to investigate factors related to long-term length of stay (LOS) of patients with chronic diseases in Korean veterans hospitals. Methods: The subjects were 196 elderly patients with chronic disease staying in the hospital for more than 10 days, Data were collected by the survey of patients with structured questionnaires and medical records review by nurses from July 15 to August 10, 2019. Collected data were analyzed using t-test, ANOVA, Pearson's correlation coefficient and stepwise multiple regression. Results: The present and desired LOS were 37.78±32.66 days and 60.87±45.95 days, respectively. Factors affecting hospital LOS were found to be main disease (genitourinary) (p<.001), assistance in activities of daily living (p<.001), area of hospital (p<.001), payment of medical fees (p=.026), hospital satisfaction (p=.036) and the explanatory power of these variables was 26.4%. The most common health problems that need to be solved after discharge were symptom alleviation and health promotion. These problems can be solved using community-based facility services or visiting medical-welfare services (especially home care nursing). Conclusion: In order to reduce hospital LOS, the following measures are required: personalized self-management education, provision of transportation services for dialysis therapy of inactive patients, linking patients with visiting medical-welfare services including home care nursing and mobile healthcare services, operation of the case management system including the notice of the discharge date at admission, interim check of patient status, and connecting the patient with community resources or transferring the patient to long-term care facilities at discharge.