• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.4
• /
• pp.168-178
• /
• 2002

The CNC machine toots has two kinds of fault. One is the fault due to degraded parts and the other is the fault due to operation disability. The phenomena of degradation is predictable but the operational fault is unpredictable because it occurred without any warning. The major faults of CNC machine tool are operational faults which are charged over 70%. This paper describes the model of remote service and the intelligent fault diagnosis system to diagnosis operational faults of CNC machine tools. To generalize fault diagnosis, two diagnosis models such as SF(Switching Function) and SSF(Step Switching Function) are proposed. The SF is static model and SSF is dynamic model for expression of fault. The SF and SSF model can be generated using SFG(Switching Function Generator) which is developed in this research. The three major operational faults such as emergency stop error, cycle start disability and machine ready disability are applied to experiment of fault modeling. To remote service of faults fur CNC machine tool, the web server and client system based internet are proposed as the suitable environment. The developed two technologies are implemented with the internal function of open architecture controller. The implemental results for two technologies are presented to validate the proposed scheme.

• Korean Chemical Engineering Research
• /
• v.60 no.2
• /
• pp.223-228
• /
• 2022

In chemical processes, unintended faults can make serious accidents. To tackle them, proper fault diagnosis models should be designed to identify the root cause of faults. To design a fault diagnosis model, a process and its data should be analyzed. However, most previous researches in the field of fault diagnosis just handle the data set of benchmark processes simulated on commercial programs. It indicates that it is really hard to get fresh data sets on real processes. In this study, real faulty conditions of an industrial polystyrene process are tested. In this process, a runaway reaction occurred and this caused a large loss since operators were late aware of the occurrence of this accident. To design a proper fault diagnosis model, we analyzed this process and a real accident data set. At first, a mode classification model based on support vector machine (SVM) was trained and principal component analysis (PCA) model for each mode was constructed under normal operation conditions. The results show that a proposed model can quickly diagnose the occurrence of a fault and they indicate that this model is able to reduce the potential loss.

• 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.

• Journal of Korean Public Health Nursing
• /
• v.11 no.2
• /
• pp.131-140
• /
• 1997

School health aims to guide and manage growing students in order to grow healthily through the formation of healthy life habits, the self-control health management guide and the making of pleasant school health environments. The purpose of this study is to clarify the concepts, to draw common features, and develop a new approach for school health diagnosis through literature review. School health diagnosis is defined as the identification of actual and potential health problems in school health problems in population. It is a label that both describes a situation and implies an ethiology. Although it is widely acknowledeged that school health diagnosis is an essential precursor to school health nursing intervention, it still has ambiguous definition, unmeasurable goal. and a tenuous structure. In addition, the eclipse of school health diagnosis theory in the literature is so complete that some texts even exclude diagnosis as a stage of the nursing theory has not developed sufficiently to guide school nurses in the application of the nursing diagnosis with in the school. The Neuman's systems model provided the conceptual framework for this study and offered school health nursing the sort of clear structure that will assist them to clarify their work to nursing colleges and also to the client group with whom they will work. The Neuman model is fully congruent with today's health care philosophy by taking a wellness-orientaed approach, involving clients III their health care with prevention as intervention.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.233-238
• /
• 1993

In this paper, two diagnosis algorithms using the simple fuzzy, cognitive map (FCM) that is an useful qualitative model are proposed. The first basic algorithm is considered as a simple transition of Shiozaki's signed directed graph approach to FCM framework. And the second one is an extended version of the basic algorithm. In the extension, three important concepts, modified temporal associative memory (TAM) recall, temporal pattern matching algorithm and hierarchical decomposition are adopted. As the resultant diagnosis scheme takes short computation time, it can be used for on-line fault diagnosis of large scale and complex processes that conventional diagnosis methods cannot be applied. The diagnosis system can be trained by the basic algorithm and generates FCM model for every experienced process fault. In on-line application, the self-generated fault model FCM generates predicted pattern sequences, which are compared with observed pattern sequences to declare the origin of fault. In practical case, observed pattern sequences depend on transport time. So if predicted pattern sequences are different from observed ones, the time weighted FCM with transport delay can be used to generate predicted ones. The fault diagnosis procedure can be completed during the actual propagation since pattern sequences of tvo different faults do not coincide in general.

• Journal of Power System Engineering
• /
• v.9 no.4
• /
• pp.187-193
• /
• 2005

In this paper, we proposes a man-machine interface design for fault diagnosis system with inter-node search method in a Petri net model. First, complicated fault cases are modeled as the Petri net graph expressions. Next, to find out causes of the faults on which we focus, a Petri net model is analyzed using the backward reasoning of transition-invariance in the Petri net. In this step, the inter-node search method algorithm is applied to the Petri net model for reducing the range of sources in faults. Finally, the proposed method is applied to a fault diagnosis of a refrigeration system to confirm the validity of the proposed method.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.1-12
• /
• 2022

The current progression in the Internet of Things (IoT) and Machine Learning (ML) based technologies converted the traditional healthcare system into a smart healthcare system. The incorporation of IoT and ML has changed the way of treating patients and offers lots of opportunities in the healthcare domain. In this view, this research article presents a new IoT and ML-based disease diagnosis model for the diagnosis of different diseases. In the proposed model, vital signs are collected via IoT-based smart medical devices, and the analysis is done by using different data mining techniques for detecting the possibility of risk in people's health status. Recommendations are made based on the results generated by different data mining techniques, for high-risk patients, an emergency alert will be generated to healthcare service providers and family members. Implementation of this model is done on Anaconda Jupyter notebook by using different Python libraries in it. The result states that among all data mining techniques, SVM achieved the highest accuracy of 0.897 on the same dataset for classification of Parkinson's disease.

• Research in Community and Public Health Nursing
• /
• v.11 no.1
• /
• pp.3-20
• /
• 2000

The purpose of this study was to compare the concept of community and community health, community health assessment tool, and community health nursing diagnosis based on the concept of 'Community as Client'. The method for this purpose was to search the articles and textbooks related to community assessment and review the contents by the researchers who were 5 community health nursing faculties and 1 doctoral candidate. The sources of articles were limited in Public Health Nursing and the Journal of Community Health Nursing. As the result, three types of conceptual model were classified: epideiological model. fuctional model. system model. System model by Newman and Helvie included more comprehensive concept of community health than others. Helvie model suggested the most specific indicators among them. The components of nursing diagnosis in the system model had the subjectives. problems and the related factors. It makes the nursing care plan related to the nursing diagnosis. But there was no nursing diagnosis system among the three model. It is needed to compare the nursing intervention based on the concept of 'Community as Client'. It will be helpful to the community health nursing practice to develop the nursing diagnosis system based on the system model. For the community health nursing education, it is suggested to try the case study by the using three types of model. Finally, it is needed to validate the community assessment tool in Korean setting.

• Smart Structures and Systems
• /
• v.5 no.2
• /
• pp.153-171
• /
• 2009

In this paper, the analytical fault detection and diagnosis (FDD) is presented using model-based and signal-based methodology with wavelet analysis on signals obtained from sensors and sensor networks. In the model-based FDD, we present the modeling of contact interface found in soft materials, including the biomedical contacts. Fingerprint analysis and signal-based FDD are also presented with an experimental framework consisting of a mechanical pneumatic system typically found in manufacturing automation. This diagnosis system focuses on the signal-based approach which employs multi-resolution wavelet decomposition of various sensor signals such as pressure, flow rate, etc., to determine leak configuration. Pattern recognition technique and analytical vectorized maps are developed to diagnose an unknown leakage based on the established FDD information using the affine mapping. Experimental studies and analysis are presented to illustrate the FDD methodology. Both model-based and wavelet-based FDD applied in contact interface and manufacturing automation have implication towards better quality of life by applying theory and practice to understand how effective diagnosis can be made using intelligent FDD. As an illustration, a model-based contact surface technology an benefit the diabetes with the detection of abnormal contact patterns that may result in ulceration if not detected and treated in time, thus, improving the quality of life of the patients. Ultimately, effective diagnosis using FDD with wavelet analysis, whether it is employed in biomedical applications or manufacturing automation, can have impacts on improving our quality of life.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.1
• /
• pp.57-64
• /
• 2017

In order to reduce damages to major railroad components, which have the potential to cause interruptions to railroad services and safety accidents and to generate unnecessary maintenance costs, the development of rolling stock maintenance technology is switching from preventive maintenance based on the inspection period to predictive maintenance technology, led by advanced countries. Furthermore, to enhance trust in accordance with the speedup of system and reduce maintenances cost simultaneously, the demand for fault diagnosis and prognostic health management technology is increasing. The objective of this paper is to propose a highly reliable learning model using various machine learning algorithms that can be applied to critical rolling stock components. This paper presents a model for railway rolling stock component fault diagnosis and conducts a mechanical failure diagnosis of motor components by applying the machine learning technique in order to ensure efficient maintenance support along with a data preprocessing plan for component fault diagnosis. This paper first defines a failure diagnosis model for rolling stock components. Function-based algorithms ANFIS and SMO were used as machine learning techniques for generating the failure diagnosis model. Two tree-based algorithms, RadomForest and CART, were also employed. In order to evaluate the performance of the algorithms to be used for diagnosing failures in motors as a critical railroad component, an experiment was carried out on 2 data sets with different classes (includes 6 classes and 3 class levels). According to the results of the experiment, the random forest algorithm, a tree-based machine learning technique, showed the best performance.