• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.5
• /
• pp.553-560
• /
• 2003

On-site diagnosis of chiller performance is an essential step fur energy saving business. The main purpose of the on-site diagnosis is to predict the COP of a target chiller. Many models based on thermodynamics background have been proposed for this purpose. However, they have to be modified from chiller to chiller and require deep insight into thermodynamics that most of field engineers are often lacking in. This study focuses on developing an easy-to-use diagnostic technique that is based on adaptive neuro-fuzzy inference system (ANFIS). Quality of the training data for ANFIS, sampled over June through September, is assessed by checking COP prediction errors. The architecture of the ANFIS, its error bounds, and collection of training data are described in detail.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2006.05a
• /
• pp.213-217
• /
• 2006

An intelligent performance diagnostic program using the Neural Network was proposed for PW206C turboshaft engine. It was selected as a power plant for the tilt rotor type Smart UAV (Unmanned Aerial Vehicle) which has been developed by KARI (Korea Aerospace Research Institute). For teaming the NN, a BPN with one hidden, one input and one output layer was used. The input layer had seven neurons of variations of measurement parameters such as SHP, MF, P2, T2, P4, T4 and T5, and the output layer used 6 neurons of degradation ratios of flow capacities and efficiencies for compressor, compressor turbine and power turbine. Database for network teaming and test was constructed using a gas turbine performance simulation program. From application results for diagnostics of the PW206C turboshaft engine using the learned networks, it was confirmed that the proposed diagnostics algorithm could detect well the single fault types such as compressor fouling and compressor turbine erosion.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.10 no.2
• /
• pp.15-22
• /
• 2006

An intelligent performance diagnostic program using the Neural Network was proposed for PW206C turboshaft engine. It was selected as a power plant for the tilt rotor type Smart UAV(Unmanned Aerial Vehicle) which is being developed by KARI (Korea Aerospace Research Institute). For teeming the NN(Neural Network), a BPN(Back Propagation Network) with one hidden, one input and one output layer was used. The input layer has seven neurons: variations of measurement parameters such as SHP, MF, P2, T2, P4, T4 and T5, and the output layer uses 6 neurons: degradation ratios of flow capacities and efficiencies for compressor, compressor turbine and power turbine, respectively, Database for network teaming and test was constructed using a gas turbine performance simulation program. From application of the learned networks to diagnostics of the PW206C turboshaft engine, it was confirmed that the proposed diagnostics algorithm could detect well the single fault types such as compressor fouling and compressor turbine erosion.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2005.11a
• /
• pp.289-292
• /
• 2005

Because of accumulation of operation time, the performance of main components(compressor, combustor, turbine, etc.) come to be deteriorated in gas-turbine engine. So, high reliability and minimun of expense are important problem for engine manufacturer and user in operation of gas-turbine engine. In this study, the diagnostic code of the engine performance using the thermodynamic sensitivity between the sensed parameters and the health parameters has been developed without an application of the commercial program. The single performance deterioration of the turbo-shaft engine has been estimated with this code.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.367-370
• /
• 2001

This paper proposes a new deterioration diagnostic technique for power facilities by analyzing the pulse-height analysis of leakage current. Until now, various deterioration diagnostic techniques to prevent power system failures by deterioration of power facilities are suggested, and most of which measures leakage current amplitude only as a estimation parameter. In this experiment, it is known that the pulse heights of the leakage current are increased according to deterioration progress as well as there comes remarkable changes in pulse height distribution thereto. Therefore, the use of pulse height distribution in deterioration diagnostic technique makes more accurate diagnosis than the conventional method by using only leakage current value. From the application test, it is confirmed that the proposed technique has sufficient performance to diagnose deterioration of power facilities.

• Journal of Appropriate Technology
• /
• v.6 no.1
• /
• pp.45-50
• /
• 2020

We developed the world's first wireless ultrasound diagnostic device. For the smooth delivery of pregnant women, the WHO requires four prior examinations, and the use of ultrasound diagnostic devices is essential for this purpose. However, income levels and medical facilities in developing countries are falling short. We conducted KOICA's CTS program in Vietnam using a self-developed radio ultrasound diagnostic device. We supplied Sonon300C, a portable wireless ultrasound diagnostic device, to health centers and hospitals in Huong-Hoa district, Vietnam, and conducted an outreach program in an effort to further enhance business performance. As a result, the rate of ultrasound diagnostics in the region reached 100% and the percentage of trained graduates increased to 59%.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.4
• /
• pp.293-299
• /
• 2021

Purpose: To accelerate magnetic resonance fingerprinting (MRF) by developing a flexible deep learning reconstruction method. Materials and Methods: Synthetic data were used to train a deep learning model. The trained model was then applied to MRF for different organs and diseases. Iterative reconstruction was performed outside the deep learning model, allowing a changeable encoding matrix, i.e., with flexibility of choice for image resolution, radiofrequency coil, k-space trajectory, and undersampling mask. In vivo experiments were performed on normal brain and prostate cancer volunteers to demonstrate the model performance and generalizability. Results: In 400-dynamics brain MRF, direct nonuniform Fourier transform caused a slight increase of random fluctuations on the T2 map. These fluctuations were reduced with the proposed method. In prostate MRF, the proposed method suppressed fluctuations on both T1 and T2 maps. Conclusion: The deep learning and iterative MRF reconstruction method described in this study was flexible with different acquisition settings such as radiofrequency coils. It is generalizable for different in vivo applications.

• Journal of Radiation Protection and Research
• /
• v.34 no.1
• /
• pp.31-36
• /
• 2009

The purpose of this study is to measure the tube voltage, the tube current/volume, exposure time and exposure dose of diagnostic X-ray unit in each doctor offices, hospitals and general hospitals for evaluating the performance of such device, to learn the method and technology of its measurement and to suggest its importance. Research subjects were total 30 X-ray units and divided into groups of 10 X-ray units each. The tube voltage, the tube current/volume, exposure time and exposure dose were measured using percentage average error, and then reproducibility of exposure dose was measured through calculating coefficient of variation. The results are like followings; The tube voltage correctness examination showed that incongruent devices among total 30 X-ray units were 5 devices (16.7%). The tube current correctness examination showed that incongruent X-ray units were 3 devices (10.0%). The tube current volume correctness examination showed that incongruent X-ray units were 4 devices (13.3%). Finally, according to exposure time correctness examination, incongruent X-ray units were 5 devices (16.7%) and according to reproducibility examination of exposure dose, incongruent X-ray units were 7 devices (23.3%). Above results showed serious problem in performance management based on management regulation of diagnostic X-ray unit; it means that regular checkout and safety management are required, and as doing so, patients will be able to receive good quality of medical service by the reduction of radiation exposure time, image quality administration, unnecessary retake and etc. Therefore, this study suggests that the performance of diagnostic X-ray units should be checked regularly.

• Korean Journal of Radiology
• /
• v.22 no.9
• /
• pp.1579-1586
• /
• 2021

Objective: To evaluate the diagnostic performance of the modified Korean Thyroid Imaging Reporting and Data System (K-TIRADS), and compare it with the 2016 version of K-TIRADS using the Thyroid Imaging Network of Korea. Materials and Methods: Between June and September 2015, 5708 thyroid nodules (≥ 1.0 cm) from 5081 consecutive patients who had undergone thyroid ultrasonography at 26 institutions were retrospectively evaluated. We used a biopsy size threshold of 2 cm for K-TIRADS 3 and 1 cm for K-TIRADS 4 (modified K-TIRADS 1) or 1.5 cm for K-TIRADS 4 (modified K-TIRADS 3). The modified K-TIRADS 2 subcategorized the K-TIRADS 4 into 4A and 4B, and the cutoff sizes for the biopsies were defined as 1 cm for K-TIRADS 4B and 1.5 cm for K-TIRADS 4A. The diagnostic performance and the rate of unnecessary biopsies of the modified K-TIRADS for detecting malignancy were compared with those of the 2016 K-TIRAD, which were stratified by nodule size (with a threshold of 2 cm). Results: A total of 1111 malignant nodules and 4597 benign nodules were included. The sensitivity, specificity, and unnecessary biopsy rate of the benign nodules were 94.9%, 24.4%, and 60.9% for the 2016 K-TIRADS; 91.0%, 39.7%, and 48.6% for the modified K-TIRADS 1; 84.9%, 45.9%, and 43.5% for the modified K-TIRADS 2; and 76.1%, 50.2%, and 40.1% for the modified K-TIRADS 3. For small nodules (1-2 cm), the diagnostic sensitivity of the modified K-TIRADS decreased by 5.2-25.6% and the rate of unnecessary biopsies reduced by 19.2-32.8% compared with those of the 2016 K-TIRADS (p < 0.001). For large nodules (> 2 cm), the modified K-TIRADSs maintained a very high sensitivity for detecting malignancy (98%). Conclusion: The modified K-TIRADSs significantly reduced the rate of unnecessary biopsies for small (1-2 cm) nodules while maintaining a very high sensitivity for malignancy for large (> 2 cm) nodules.

• Korean Journal of Radiology
• /
• v.20 no.5
• /
• pp.749-758
• /
• 2019

Objective: To investigate whether a computer-aided diagnosis (CAD) system based on a deep learning framework (deep learning-based CAD) improves the diagnostic performance of radiologists in differentiating between malignant and benign masses on breast ultrasound (US). Materials and Methods: B-mode US images were prospectively obtained for 253 breast masses (173 benign, 80 malignant) in 226 consecutive patients. Breast mass US findings were retrospectively analyzed by deep learning-based CAD and four radiologists. In predicting malignancy, the CAD results were dichotomized (possibly benign vs. possibly malignant). The radiologists independently assessed Breast Imaging Reporting and Data System final assessments for two datasets (US images alone or with CAD). For each dataset, the radiologists' final assessments were classified as positive (category 4a or higher) and negative (category 3 or lower). The diagnostic performances of the radiologists for the two datasets (US alone vs. US with CAD) were compared Results: When the CAD results were added to the US images, the radiologists showed significant improvement in specificity (range of all radiologists for US alone vs. US with CAD: 72.8-92.5% vs. 82.1-93.1%; p < 0.001), accuracy (77.9-88.9% vs. 86.2-90.9%; p = 0.038), and positive predictive value (PPV) (60.2-83.3% vs. 70.4-85.2%; p = 0.001). However, there were no significant changes in sensitivity (81.3-88.8% vs. 86.3-95.0%; p = 0.120) and negative predictive value (91.4-93.5% vs. 92.9-97.3%; p = 0.259). Conclusion: Deep learning-based CAD could improve radiologists' diagnostic performance by increasing their specificity, accuracy, and PPV in differentiating between malignant and benign masses on breast US.