• Imaging Science in Dentistry
• /
• v.54 no.1
• /
• pp.71-80
• /
• 2024

Purpose: This study aimed to evaluate age-stratified radiographic features in temporomandibular joint osteoarthritis using cone-beam computed tomography. Materials and Methods: In total, 210 joints from 183 patients(144 females, 39 males, ranging from 12 to 88 years old with a mean age of 44.75±19.97 years) diagnosed with temporomandibular joint osteoarthritis were stratified by age. Mandibular condyle position and bony changes (flattening, erosion, osteophytes, subchondral sclerosis, and subchondral pseudocysts in both the condyle and articular eminence, thickening of the glenoid fossa, joint space narrowing, and joint loose bodies) were evaluated through cone-beam computed tomography. After adjusting for sex, the association between age groups and radiographic findings was analyzed using both a multiple regression model and a multinomial logistic regression model(α=0.05). Results: The prevalence of joint space narrowing and protruded condyle position in the glenoid fossa significantly increased with age (P<0.05). The risks of bony changes, including osteophytes and subchondral pseudocysts in the condyle; flattening, erosion, osteophyte, and subchondral sclerosis in the articular eminence; joint loose bodies; and thickening of the glenoid fossa, also significantly rose with increasing age (P<0.05). The number of radiographic findings increased with age; in particular, the increase was more pronounced in the temporal bone than in the mandibular condyle (P<0.05). Conclusion: Increasing age was associated with a higher frequency and greater diversity of bony changes in the temporal bone, as well as a protruded condyle position in the glenoid fossa, resulting in noticeable joint space narrowing in temporomandibular joint osteoarthritis.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.801-807
• /
• 2024

Linear motion robots are devices that perform functions such as transferring parts or positioning devices, and require high precision. In companies that develop linear robot application systems, human workers are in charge of quality control and fault diagnosis of linear robots, and the result and accuracy of a fault diagnosis varies depending on the skill level of the person in charge. Recently, there have been many attempts to utilize artificial intelligence to diagnose faults in industrial devices. In this paper, we present a system that automatically diagnoses linear rail and ball screw misalignment of a linear robot using transfer learning. In industrial systems, it is difficult to obtain a lot of learning data, and this causes a data imbalance problem. In this case, a transfer learning model configured by retraining an established model is widely used. The information obtained by using an acceleration sensor and torque sensor was used, and its usefulness was evaluated for each case. After converting the signal obtained from the sensor into a spectrogram image, the type of abnormality was diagnosed using an image recognition artificial intelligence classifier. It is expected that the proposed method can be used not only for linear robots but also for diagnosing other industrial robots.

• Journal of Mechanical Science and Technology
• /
• v.20 no.12
• /
• pp.2079-2086
• /
• 2006

A fundamental study for developing a fault diagnosis system of a pump is performed by using neural network. Acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer. And the codes of pump malfunctions were selected as units of output layer. Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. Neural network trained by acoustic signals can detect malfunction or diagnose fault of a given machine from the results.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2001.11a
• /
• pp.139-144
• /
• 2001

Insulation aging diagnosis system provides early warning regarding electrical equipment defect. Early warning is very important in that it can avoid great losses resulting from unexpected shutdown of the production line. Since relations of insulation aging and partial discharge dynamics are non-linear, it is very difficult to provide early warning in an electrical equipment. In this paper, we propose the design method of insulation aging diagnosis system that use a magnetic wave and acoustic signal to diagnoses an electrical equipment. Proposed system measures the partial discharge on-line from DAS(Data Acquisition System) and acquires 2D patterns from analyzing it. For filtering the noise contained in sensor signals we used ICA algorithms. Using this data, design of the neuro-fuzzy model that diagnoses an electrical equipment is investigated. Validity of the new method is asserted by numerical simulation.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.7
• /
• pp.928-933
• /
• 2018

Nowadays, gastropathy is a common disease. As endoscopic equipment are developed and used widely, it is possible to provide a large number of endoscopy images. Computer-aided Diagnosis (CADx) systems aim at helping physicians to identify possibly malignant abnormalities more accurately. In this paper, we present a CADx system to detect and classify the abnormalities of gastric lesions which include bleeding, ulcer, neuroendocrine tumor and cancer. We used an Inception module based deep learning model. And we used data augmentation for learning. Our preliminary results demonstrated promising potential for automatically labeled region of interest for endoscopy doctors to focus on abnormal lesions for subsequent targeted biopsy, with Az values of Receiver Operating Characteristic(ROC) curve was 0.83. The proposed CADx system showed reliable performance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.9
• /
• pp.1673-1679
• /
• 2010

A photovoltaic (PV) generator is significantly regarded as one important alternative of renewable energy systems recently. Fault detection and diagnosis of engineering dynamic systems is a fundamental issue to timely prevent unexpected damages in industry fields. This paper presents an intelligent monitoring approach and fault detection technique for PV generator systems by means of artificial neural network and statistical signal detection theory. We devise a multi-Fourier neural network model for representing dynamics of PV systems and apply a general likelihood ratio test (GLRT) approach for investigating our decision making algorithm in fault detection and diagnosis. We make use of a test-bed of ubiquitous sensor network (USN) based PV monitoring systems for testing our proposed fault detection methodology. Lastly, a real-time experiment is accomplished for demonstrating its reliability and practicability.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.7
• /
• pp.196-202
• /
• 1999

Recent trend changes a criterion for evaluation of burner that environmental problem is raised as global issue. For efficient driving problem, the higher thermal efficiency and the lower oxygen in exhaust gas, burner is evaluated the better. For environmental problem, burner must satisfy $NO_{X}$ limit and CO limit. Consequently, 'good burner' means on whose thermal efficiency is high under the constraint of $NO_{X}$ and CO consistency. To make existing burner satisfy recent criterion, it is highly recommended to develop feedback control scheme whose output is the consistency of $NO_{X}$ and CO. This paper describes development of real time flame diagnosis technique that evaluate and diagnose combustion state such as consistency of components in exhaust gas, stability of flame in quantitative sense. This study focuses on wave length of luminescence from chemical reaction measurement of the luminescence via optical measuring apparatus and derive correlation with consistency of components in exhaust gas by image processing technique.

• Industrial Engineering and Management Systems
• /
• v.4 no.2
• /
• pp.192-197
• /
• 2005

Among many amplitude parameters, Kurtosis (4-th normalized moment of probability density function) is recognized to be the sensitive good parameter for machine diagnosis. Kurtosis has a value of 3.0 under normal condition and the value generally goes up as the deterioration proceeds. In this paper, simplified calculation method of kurtosis is introduced for the analysis of impact vibration with one sided affiliated impact vibration which occurs towards the progress of time. That phenomenon is often watched in the failure of such as bearings’ outer race. One sided affiliated impact vibration is approximated by one sided triangle towards the progress of time and simplified calculation method is introduced. Varying the shape of one sided triangle, various models are examined and it is proved that new index is a sensitive good index for machine failure diagnosis. Utilizing this method, the behavior of kurtosis is forecasted and analyzed while watching machine condition and correct diagnosis is executed.

• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.3-4
• /
• 2015

A self-organizing map (SOM) is a good tool to visualize applied data in the form of a feature map. With the help of such functions, a disaster risk diagnosis based on the residential house structure is tried in this study. According to some computer simulations with actual residential data, it is found that overall tendencies in the developed feature map are acceptable. Then, it is concluded that the proposed method is an effective means to estimate disaster risk appropriately.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.137-142
• /
• 2003

A fundamental study for developing a system of fault diagnosis of a pump is performed by using neural network. The acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The signals were obtained in various driving frequencies in order to obtain many types of data from a limited number of pumps. The acoustic data in frequency domain were managed to multiples of real driving frequency with the aim of easy comparison. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer, Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. The results showed neural network trained by acoustic signals can be used as a simple method far a detection of machine malfunction or fault diagnosis.