• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.4
• /
• pp.457-466
• /
• 2021

This paper describes the design of model-based fault diagnosis software to apply to the propulsion system in tracked amphibious assault vehicle which consists of an engine, a transmission, a cooling system, and two waterjets. This software includes specific functions to detect the failures regarding sensor malfunctions, mechanical malfunctions, control errors, and communication errors. This software generates the proper malfunction codes which are classified as the warning and caution. In order to validate the fault diagnosis software, the manual and automatic test are performed using the test program with 32 test cases. Test results show that the designed fault diagnosis software is reliable and effective for applying to the propulsion system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.77-87
• /
• 2023

Wind turbines playing a critical role in renewable energy generation, accurately assessing their operational status is crucial for maximizing energy production and minimizing downtime. This study conducts a comparative analysis of different neural network models for wind turbine condition diagnosis, evaluating their effectiveness using a dataset containing sensor measurements and historical turbine data. The study utilized supervisory control and data acquisition data, collected from 2 MW doubly-fed induction generator-based wind turbine system (Model HQ2000), for the analysis. Various neural network models such as artificial neural network, long short-term memory, and recurrent neural network were built, considering factors like activation function and hidden layers. Symmetric mean absolute percentage error were used to evaluate the performance of the models. Based on the evaluation, conclusions were drawn regarding the relative effectiveness of the neural network models for wind turbine condition diagnosis. The research results guide model selection for wind turbine condition diagnosis, contributing to improved reliability and efficiency through advanced neural network-based techniques and identifying future research directions for further advancements.

• Nuclear Engineering and Technology
• /
• v.48 no.5
• /
• pp.1280-1290
• /
• 2016

This paper presents an advanced estimation method for obtaining the probability density functions of a damage parameter for valve leakage detection in a reciprocating pump. The estimation method is based on a comparison of model data which are simulated by using a mathematical model, and experimental data which are measured on the inside and outside of the reciprocating pump in operation. The mathematical model, which is simplified and extended on the basis of previous models, describes not only the normal state of the pump, but also its abnormal state caused by valve leakage. The pressure in the cylinder is expressed as a function of the crankshaft angle, and an additional volume flow rate due to the valve leakage is quantified by a damage parameter in the mathematical model. The change in the cylinder pressure profiles due to the suction valve leakage is noticeable in the compression and expansion modes of the pump. The damage parameter value over 300 cycles is calculated in two ways, considering advance or delay in the opening and closing angles of the discharge valves. The probability density functions of the damage parameter are compared for diagnosis and prognosis on the basis of the probabilistic features of valve leakage.

• Computers and Concrete
• /
• v.2 no.6
• /
• pp.439-454
• /
• 2005

When deterioration of concrete is observed in a structure, it is highly desirable to determine the cause of such deterioration. Only by understanding the cause can an appropriate repair strategy be implemented to address both the cause and the symptom. In colder climates, bridge deck deterioration is often caused by chlorides from de-icing salts, which penetrate the concrete and depassivate the embedded reinforcement, causing corrosion. Bridge decks can also suffer from other deterioration mechanisms, such as alkali-silica reaction, freeze-thaw, and shrinkage. There is a need for a comprehensive and integrative system to help with the inspection and evaluation of concrete bridge deck deterioration before decisions are made on the best way to repair it. The purpose of this research was to develop a model to help with the diagnosis of concrete bridge deck deterioration that integrates the symptoms observed during an inspection, various deterioration mechanisms, and the probability of their occurrence given the available data. The model displays the diagnosis result as the probability that one of four deterioration mechanisms, namely shrinkage, corrosion of reinforcement, freeze-thaw and alkali-silica reaction, is at fault. Sensitivity analysis was performed to determine which probabilities in the model require refinement. Two case studies are included in this investigation.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.241-251
• /
• 2022

Diagnosis and management of customer's skin condition is an important essential function in the cosmetics and beauty industry. As the social media environment spreads and generalizes to all fields of society, the interaction of questions and answers to various and delicate concerns and requirements regarding the diagnosis and management of skin conditions is being actively dealt with in the social media community. However, since social media information is very diverse and atypical big data, an intelligent skin condition diagnosis system that combines appropriate skin condition information analysis and artificial intelligence technology is necessary. In this paper, we developed the skin condition diagnosis system SCDIS to intelligently diagnose and manage the skin condition of customers by processing the text analysis information of social media into learning data. In SCDIS, an artificial neural network model, AnnTFIDF, that automatically diagnoses skin condition types using artificial neural network technology, a deep learning machine learning method, was built up and used. The performance of the artificial neural network model AnnTFIDF was analyzed using test sample data, and the accuracy of the skin condition type diagnosis prediction value showed a high performance of about 95%. Through the experimental and performance analysis results of this paper, SCDIS can be evaluated as an intelligent tool that can be used efficiently in the skin condition analysis and diagnosis management process in the cosmetic and beauty industry. And this study can be used as a basic research to solve the new technology trend, customized cosmetics manufacturing and consumer-oriented beauty industry technology demand.

• Journal of Korean Academy of Nursing Administration
• /
• v.9 no.4
• /
• pp.651-661
• /
• 2003

Purpose: This is the descriptive research project of which purpose is to acquire the practice, research, and educational data by establishing the database after confirming, classifying, and relating the nursing diagnosis, nursing intervention, and nursing outcome of Breast cancer patients by using the Yoo Hyung-sook's(2001) related 3N database model as the tool. Method : The Nursing Data occurring on Breast cancer patients nursing process was mapped to nursing diagnosis of NANDA, nursing interventions of NIC, nursing outcomes of NOC the 3N database linkage database which is related with the nursing process that was developed by using Yoo Hyung-sook's(2001). Result : 1. The nursing diagnosis were totally 505, and 26 articles of the nursing diagnosis were applied among 149 nursing diagnosis classification systems. 2. As for the nursing intervention, 250 articles(5l.4%) of nursing intervention were applied among 486 nursing intervention classification systems. 3. Regarding the nursing outcome, 28 articles(1l.2%l of the nursing outcome were applied among 250 nursing outcome classification systems. Conclusion: The result of this research in which the relating among the nursing diagnosis, nursing intervention, and nursing outcome of Breast cancer patients by using 3N nursing database was established is thought to be applied in the research and practice as well as to be utilized in the lecture or practice of the nursing process.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.3
• /
• pp.365-373
• /
• 2018

In this paper, inter-turn fault diagnosis of the interior permanent magnet synchronous motor (IPMSM) is performed in offline state by linking the finite element analysis (FEA) tool and control simulation tool. In order to diagnose the inter-turn fault, it is important to select the current value to determine the fault. First, the basic principles for inter-turn fault diagnosis of IPMSM are explained and co-analysis model for fault diagnosis is constructed. Further, in order to select the appropriate high frequency voltage, the change of the current value to be judged as failure was analyzed at various voltage and frequency conditions, and the change of the current value according to the number of the failed windings was analyzed. Finally, the current value to be judged as failure is selected.

• Journal of Environmental Science International
• /
• v.27 no.6
• /
• pp.447-456
• /
• 2018

In this research, the target process was a modified type of a conventional aeration tank with four different influent feeding points and alternated aeration to obtain nitrogen removal. For more accurate switching of influent feeding, the process was operated under a designed control strategy based on monitoring of $NH_4-N$ and $NO_X-N$ concentrations in the tank. However, the strategy did have some limitations. For example, it was not sensitive to detecting the end of each reaction when losing the balance between nitrification and denitrification of each opposite part of biological tank. To overcome the limitations of the existing control strategy, a diagnosis-based control strategy was suggested in this research using the diagnosis results classified as normal (N), ammonia accumulation (AA) and nitrate accumulation (NA). Using the pre-designed rules for control actions, the aeration and volume of the aerated part of the reactor could be increased or decreased at a fixed mode time. In simulations of the suggested diagnosis-based control strategy, the $NH_4-N$ and $NO_X-N$ removal rates in the reactor were maintained at higher levels than those of the existing control strategy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.11
• /
• pp.6502-6508
• /
• 2014

The concept of Communities of Practice (CoPs) has been highlighted as an effective method for knowledge sharing in Knowledge Management (KM) and has been utilized strategically by many organizations. Therefore, the need to diagnose knowledge sharing activities in CoPs has increased. Previous studies of CoP strategies has generally suggested broad guidelines without diagnosing the current knowledge sharing status of individual CoPs. Furthermore, diagnosis methodologies are not connected to the strategic direction and require considerable time and effort to conduct regularly. The purpose of this paper was to develop a sustainable diagnosis framework for identifying knowledge sharing activities in virtual CoPs and to suggest strategies for CoPs-based on the proposed diagnosis framework. Finally, the proposed diagnosis framework was applied to an educational service case.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.6
• /
• pp.287-294
• /
• 2019

With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.