• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.870-881
• /
• 2020

Because SCADA monitoring data of wind turbines are large and fast changing, the unbalanced proportion of data in various working conditions makes it difficult to process fault feature data. The existing methods mainly introduce new and non-repeating instances by interpolating adjacent minority samples. In order to overcome the shortcomings of these methods which does not consider boundary conditions in balancing data, an improved over-sampling balancing algorithm SC-SMOTE (safe circle synthetic minority oversampling technology) is proposed to optimize data sets. Then, for the balanced data sets, a fault diagnosis method based on improved k-nearest neighbors (kNN) classification for wind turbine blade icing is adopted. Compared with the SMOTE algorithm, the experimental results show that the method is effective in the diagnosis of fan blade icing fault and improves the accuracy of diagnosis.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.57-64
• /
• 2024

In the industrial field, robots are used to increase productivity by replacing labors with dangerous, difficult, and hard tasks. However, failures of individual industrial robots in the entire production process may cause product defects or malfunctions, and may cause dangerous disasters in the case of manufacturing parts used in automobiles and aircrafts. Although requirements for early diagnosis of industrial robot failures are steadily increasing, there are many limitations in early detection. This paper introduces methods for diagnosing robot failures using sound-based data and deep learning. This paper also analyzes, compares, and evaluates the performance of failure diagnosis using various deep learning technologies. Furthermore, in order to improve the performance of the fault diagnosis system using deep learning technology, we propose a method to increase the accuracy of fault diagnosis based on an inference window. When adopting the inference window of deep learning, the accuracy of the failure diagnosis was increased up to 94%.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.12 no.2
• /
• pp.107-126
• /
• 2008

Background : There was seldom study about method that diagnose 8 Constitution beside method of pulse diagnosis in 8 Constitution Medicine. Objectives : This study is to make out 8 Constitution Medicine Diagnosis Expert System Development used CBR(Case based Reasoning). Methods : First, at case base construction process we constructed case base for CBR embodiment because gathering 925 cases all to patient who constitution is verified, and second, at study model establishment process superior expert system development by purpose CBR of reasoning process dividing fundamental type CBR that spend basis data value and expert type CBR that reflect weight in basis data value accordin I II III to advice expert opinion, and third, system embodiment process explained about way to give process and weight that diagnose constitution through Nearest Neighbor Method sampling process of CBR techniques, and fourth, at system estimation process we selected superior CBR model because comparing and estimate the diagnosis rate of expert system with fundamental type system (GECBR) model and expert type I II III CBR system (AVCBR, AACBR, AGCBR) model that reflect expert opinion in fundamental type system. GECBR and AGCBR chose on superior study model. Through such 4 study process, we developed 8 constitution diagnosis expert system lastly. Results : 1. When we select GECBR that is fundamental type by reasoning system, diagnosis rate 78.91% of 8 constitution diagnosis expert system is expected, and the constitution diagnosis rate Hepatonia 90.4%, Cholecystonia 63.0%, Pancreotonia 91.1%, Gastrotonia 0%, Pulmotonia 71.2%, Colonotonia 74.4%, Renotonia 37.5%, Vesicotonia 67.1% expect. 2. When we select AGCBR that is expert type III by reasoning system, diagnosis rate 77.51% of 8 constitution diagnosis expert system is expected, and the constitution diagnosis rate Hepatonia 93.4%, Cholecystonia 58.5%, Pancreotonia 91.1%, Gastrotonia 0%, Pulmotonia 73.1%, Colonotonia 64.4%, Renotonia 41.7%, Vesicotonia 72.2% expect. Conclusion : Based on this study, 8 constitution diagnosis expert system may give help to diagnose 8 constitution, and it is going to utilize as objective estimation tool of 8 constitution diagnosis, and further study for 8 Constitution Medicine Diagnosis Expert System Development used CBR(Case based Reasoning) is needed to supplement this study.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.12 no.1
• /
• pp.142-184
• /
• 2008

Background: There was seldom study about method that diagnose 8 Constitution beside method of pulse diagnosis in 8 Constitution Medicine. Objectives: This study is to make out 8 Constitution Medicine Diagnosis Expert System Development used CBR(Case based Reasoning). Methods: First, at case base construction process we constructed case base for CBR embodiment because gathering 925 cases all to patient who constitution is verified, and second, at study model establishment process superior expert system development by purpose CBR of reasoning process dividing fundamental type CBR that spend basis data value and expert type I II III CBR that reflect weight in basis data value according to advice expert opinion, and third, system embodiment process explained about way to give process and weight that diagnose constitution through Nearest Neighbor Method sampling process of CBR techniques, and fourth, at system estimation process we selected superior CBR model because comparing and estimate the diagnosis rate of expert system with fundamental type system (GECBR) model and expert type I II III CBR system (AVCBR, AACBR, AGCBR) model that reflect expert opinion in fundamental type system. GECBR and AGCBR chose on superior study model. Through such 4 study process, we developed 8 constitution diagnosis expert system lastly. Results: 1. When we select GECBR that is fundamental type by reasoning system, diagnosis rate 78.91% of 8 constitution diagnosis expert system is expected, and the constitution diagnosis rate Hepatonia 90.4%, Cholecystonia 63.0%, Pancreotonia 91.1%, Gastrotonia 0%, Pulmotonia 71.2%, Colonotonia 74.4%, Renotonia 37.5%, Vesicotonia 67.1% expect. 2. When we select AGCBR that is expert type III by reasoning system, diagnosis rate 77.51% of 8 constitution diagnosis expert system is expected, and the constitution diagnosis rate Hepatonia 93.4%, Cholecystonia 58.5%, Pancreotonia 91.1%, Gastrotonia 0%, Pulmotonia 73.1%, Colonotonia 64.4%, Renotonia 41.7%, Vesicotonia 72.2% expect. Conclusion: Based on this study, 8 constitution diagnosis expert system may give help to diagnose 8 constitution, and it is going to utilize as objective estimation tool of 8 constitution diagnosis, and further study for 8 Constitution Medicine Diagnosis Expert System Development used CBR(Case based Reasoning) is needed to supplement this study.

• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2003.11a
• /
• pp.224-228
• /
• 2003

The basic Principles and methods of the on-line monitoring of tribology parameters (friction coefficient and wear allowance) and fault diagnosis for the hoist disc brake system were introduced, the method were based on the spring force and oil pressure of the brake system and the hoist kinematics parameters. The experiment on the monitoring and diagnosis of hoist brake system were carried out. The research results showed: the monitoring and diagnosis methods are feasible.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.28 no.6
• /
• pp.469-476
• /
• 2008

Condition based maintenance(CBM) for the preventive diagnosis of important equipments related to safety or accident in power plant is essential by using the suitable methods based on actual power plant conditions. To improve the reliability and accuracy of the measured value at the minute leak situation, and also to monitor continuously internal leak condition of power plant valve, the development of a diagnosis and monitoring technique using multi-measuring method should be performed urgently. This study was conducted to estimate the feasibility of multi-measuring method using three different methods such as acoustic emission(AE) method, thermal image measurement and temperature difference$({\Delta}T)$ measurement that are applicable to internal leak diagnosis for the power plant valve. From the experimental results, it was suggested that the multi-measuring method could be an effective way to precisely diagnose and evaluate internal leak situation of valve.

• Proceedings of the KIPE Conference
• /
• 2003.11a
• /
• pp.210-213
• /
• 2003

Short-circuited can have significant effects on a generator and its performance. One of effective method detecting inter-turn short circuits on round rotor winding is a method using sensor detecting. But the method needs duplicate design of sensor for characteristic change according to types and forms of generator. Thus rotor shorted-turn diagnosis method without sensor is needed for detecting short turn when generator is driven. Diagnosis method without sensor depend on change of electric property in generator For the reason, this paper presents characteristic analysis of shorted-turns in generator by detecting the output voltage of generator.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.10 no.1
• /
• pp.78-97
• /
• 2006

Background: There was seldom study about method that estimate expertness of pulse diagnosis in 8 Constitution Medicine in spite of the diagnostician importance in 8 Constitution Medicine Objectives: This study is to evaluate diagnostician's consistency and accuracy about pulse diagnosis in 8 Constitution Medicine using Cage R&R study. Methods: The subjects were comprised of 28 volunteers. Among theme, 3 diagnosticians and 10 participants were chosen through questionnaire. Diagnosticians diagnosed participant's Constitution by pulse diagnosis in 8 Constitution Medicine with hiding their eyes by eyepatch. MINITAB statistical software(ver. 13.20) was used for statistical analysis: Attribute Cage R&R study was used to verify the results. Results: 1. In the measurements of consistency, diagnostician b(agreement=80%, Value of k=0.8276)was very good, diagnostician a(agreement=70%, Value of k=0.7465) was good, and diagnostician c(agreement=50%, Value of k=0.5365) was moderate. 2. In the measurements of accuracy, diagnostician b(agreement =70%, Value of t=0.6812) was good, diagnostician a(agreement=60%. Value of t=0.6414) was good, and diagno-stician c(agreement=0%, Value of k=-0.1000) was poor. 3. In cofidence of diagnosis, diagnostician c was 75%, diagnostician a was 70%, and diagnostician b was 64%. Conclusion: The results suggest that diagnostician's consistency and accuracy about pulse diagnosis in 8 Constitution Medicine can be evaluated by Cage R&R study. further study is needed for estimation method of pulse diagnosis in 8 Constitution Medicine.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.215-222
• /
• 2006

People health improvement is becoming new subject through the combining with the oriental medicine diagnosis theory and IT technology. To do this, firstly, it needs sicked data that supply the visualization, objectification and quantification method. Especially, if an ocular inspection can be more objective and visual expression in oriental medicine, it seems to offer the biggest opportunity in diagnosis field. In this study, I propose a diagnosis to check the symptoms of heart diagnosis. Our research aim is on the visualization of diagnosis using image processing system which it can be actual analysis about the symptom of heart. To catch up this study, through the color support assistance by face image processing, I devide the face area and analyze the face form and also extract face characteristic point in heart disease diagnosis using oriental medicine based on an ocular inspection method. I would like to prove the usefulness of the method that proposed by an experiment.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• v.4B no.4
• /
• pp.206-210
• /
• 2004

This paper deals with a parameter estimation of the DC-DC converter system for its diagnosis. Especially, we present the results of parameter estimation for the DC-DC converter model by the system identification method. The parameter estimation for the DC-DC converter system aims at the diagnosis of its operating status. For the operating status diagnosis of the DC-DC converter system, we assume that the DC-DC converter system is an equivalent model of the Buck converter and estimate the main parameter for on-line diagnosis. In addition, for verification of an estimated parameter, we compare a bode plot of the estimated system transfer function and measurement results of the HP4194 instrument. It is a control system analyzer for system transfer function measurement. Our results confirm that the main parameter for diagnosis of the DC-DC converter system can be estimated by the system identification method and that the aging status of the system can be predicted by these results on operating status.