• 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.

• Imaging Science in Dentistry
• /
• v.53 no.1
• /
• pp.43-51
• /
• 2023

Purpose: This study aimed to assess texture analysis(TA) of cone-beam computed tomography (CBCT) images as a quantitative tool for the differential diagnosis of odontogenic and non-odontogenic maxillary sinusitis(OS and NOS, respectively). Materials and Methods: CBCT images of 40 patients diagnosed with OS (N=20) and NOS (N=20) were evaluated. The gray level co-occurrence (GLCM) matrix parameters, and gray level run length matrix texture (GLRLM) parameters were extracted using manually placed regions of interest on lesion images. Seven texture parameters were calculated using GLCM and 4 parameters using GLRLM. The Mann-Whitney test was used for comparisons between the groups, and the Levene test was performed to confirm the homogeneity of variance (α=5%). Results: The results showed statistically significant differences(P<0.05) between the OS and NOS patients regarding 3 TA parameters. NOS patients presented higher values for contrast, while OS patients presented higher values for correlation and inverse difference moment. Greater textural homogeneity was observed in the OS patients than in the NOS patients, with statistically significant differences in standard deviations between the groups for correlation, sum of squares, sum of entropy, and entropy. Conclusion: TA enabled quantitative differentiation between OS and NOS on CBCT images by using the parameters of contrast, correlation, and inverse difference moment.

• Korean Journal of Oriental Medicine
• /
• v.12 no.2 s.17
• /
• pp.93-101
• /
• 2006

Pulse feeling is one of the most important diagnosis method in Oriental medicine. But it is not easy to make an objective and standardized diagnosis. In this study, we found how to quantify diagnosis. Specially dally the high practicality in clinic, we search some parameters especially well-related to floating and sinking pulse by statistic analysis. By extension, we find the pulse patterns of the floating and sinking pulse. We choose 15 subjects diagnosed as floating pulse and 15 subjects diagnosed as sinking pulse by oriental doctors. And their pulse signals were acquired by Pulse analyzer which has piezoresistive pressure sensor. For the quantification of the floating and sinking pulse, at first, we examined the parameters which were highly correlated with oriental doctor's diagnosis. And then we derived pulse patterns of the floating-sinking pulse from preprocessed signal and its ensemble average. We also looked trend variation (PH-Curve) between contact and pulse pressure. As a result, statistically there is the biggest difference between contact pressure, the maximum pulse pressure, diastolic area (Ad) and floating and sinking data. Through the PH-Curve, which represented the relationship between contact and pulse pressure, we could divide the floating and sinking pulse clearly. As a basic research of pulse diagnosis algorithm, we can contribute to select essential parameters in diagnosis algorithm And using these diagnosis method, we expect to find typical pulse patterns and some useful parameters about other pulses like slow/rapid, large/fine pulse and so on. We hope that this study will contribute pulse objectification.

• Journal of the Korean Society of Safety
• /
• v.34 no.4
• /
• pp.59-67
• /
• 2019

Since it is really hard to construct process models based on prior process knowledges, various statistical approaches have been employed to build fault diagnosis models. However, the crucial drawback of these approaches is that the solutions may vary according to the fault magnitude, even if the same fault occurs. In this study, the parameter monitoring approach is suggested. When a fault occurs in a chemical process, this leads to trigger the change of a process model and the monitoring parameters of process models is able to provide the efficient fault diagnosis model. A few important variables are selected and their predictive models are constructed by partial least square (PLS) method. The Euclidean norms of parameters of PLS models are estimated and a fault diagnosis can be performed as comparing with parameters of PLS models based on normal operational conditions. To improve the monitoring performance, cumulative summation (CUSUM) control chart is employed and the changes of model parameters are recorded to identify the type of an unknown fault. To verify the efficacy of the proposed model, Tennessee Eastman (TE) process is tested and this model can be easily applied to other complex processes.

• Tribology and Lubricants
• /
• v.14 no.3
• /
• pp.74-80
• /
• 1998

The morphologies of the wear particles are directly indicative of wear process occuring in the machine. The analysis of wear particle morphology can therefore provide very early detection of a fault and can also ofen facilitate a dignosis. For this work, the neural network was applied to identify friction coefficient through four shape parameters (50% volumetric diameter, aspect, roundness and reflectivity) of wear debris generated from the machine. The averages of these parameters were used as inputs to the network. It is shown that collect identification of friction coefficient depends on the ranges of these shape parameters learned. The various kinds of the wear debris had a different pattern characteristics and recognized relation between the friction condition and materials very well by neural network. We discuss how the network determines difference in wear debris feature, and this approach can be applied for machine condition monitoring and fault diagnosis.

• Journal of Multimedia Information System
• /
• v.3 no.2
• /
• pp.1-8
• /
• 2016

In this paper, we propose a method to automatically diagnose various diseases. The input data consists of electrocardiograph (ECG) recordings. We extract R-to-R interval (RRI) signals from ECG recordings, which are preprocessed to remove trends and ectopic beats, and to keep the signal stationary. After that, we perform some prospective analysis to extract time-domain parameters, frequency-domain parameters, and nonlinear parameters of the signal. Those parameters are unique for each disease and can be used as the statistical symptoms for each disease. Then, we perform feature selection to improve the performance of the diagnosis classifier. We utilize the selected features to diagnose various diseases using machine learning. We subsequently measure the performance of the machine learning classifier to make sure that it will not misdiagnose the diseases. The first two steps, which are R-to-R extraction and preprocessing, have been successfully implemented with satisfactory results.

• Speech Sciences
• /
• v.5 no.1
• /
• pp.151-165
• /
• 1999

This paper describes a series of researches to diagnose vocal diseases using the statistical method and the acoustic signal analysis method. Speech materials are collected at the hospital. Using the pathological database, the basic parameters for the diagnosis are obtained. Based on the statistical characteristics of the parameters, valid parameters are chosen and those are used to diagnose the pathological speech signal. Cepstrum is used to extract parameters which represents characteristics of pathological speech. 3 layered neural network is used to train and classify pathological speech into normal, benign and malignant case.

• Korean Journal of Veterinary Research
• /
• v.56 no.3
• /
• pp.161-166
• /
• 2016

Hyperadrenocorticism (HAC) is a common endocrinopathy among dogs that causes multisystemic signs. This study was conducted to evaluate cardiocirculatory, biochemical, and hemostatic parameters in dogs with HAC at diagnosis, in addition to verifying whether abnormal parameters could be controlled by initial treatment with trilostane. Fifteen dogs with HAC were assessed by systolic blood pressure measurement, electrocardiography, Doppler echocardiography, serum concentration of troponin I, and biochemical and hemostatic profile at diagnosis and after trilostane therapy. Unlike biochemical parameters, hemostatic and cardiocirculatory parameters were not significantly influenced by the onset of treatment. The authors believe that clinical treatment with trilostane for 3 to 4 months might not be sufficient for the stabilization of cardiocirculatory abnormalities such as hypertension. Therefore, dogs with HAC must receive cardiocirculatory monitoring at diagnosis and during drug treatment.

• Tribology and Lubricants
• /
• v.18 no.4
• /
• pp.285-290
• /
• 2002

Integrated condition monitoring is required to monitor effectively the machine conditions since machine failures could not be monitored accurately by any single measurement parameter. Application of various condition monitoring techniques is therefore preferred in many cases in order to diagnosis the machine condition. However it inevitably requires lots of maintenance cost and sometimes it could be proved to over-maintenance unnecessarily. This could happen especially when one measurement parameter closely correlates to another. Therefore correlation analysis of various monitoring parameters has to be performed to improve the reliability of diagnosis. In this work, Pearson correlation coefficient was used to analyze the correlation between condition monitoring parameters of an over-loaded machine system where the vibration, wear and temperature were monitored simultaneously. The result showed that Pearson correlation coefficient could be regarded as a good measure for evaluating the availability of condition monitoring technology.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.12
• /
• pp.1090-1095
• /
• 2012

In this paper, we propose a model-based fault diagnosis method applied to vibration data. The fault detection is performed by comparing estimated parameters with normal parameters and deciding if the observed changes can be explained satisfactorily in terms of noise or undermodelling. The key feature of this method is that it accounts for the effects of noise and model mismatch. And we aslo design a classifier for the fault isolation by applying the multiclass SVM (Support Vector Machine) to the estimated parameters. The proposed fault detection and isolation methods are applied to an engine vibration data to show a good performance. The proposed fault detection method is compared with a signal-based fault detection method through a performance analysis.