• Nuclear Engineering and Technology
• /
• 제32권3호
• /
• pp.261-273
• /
• 2000

During an extensive review made as part of the Integrated Diagnosis System project of the Maiden Reactor Project, MOAS (Maryland Operator Advisory System) was identified as one of the most thorough systems developed thus far. MOAS is an integrated on-line diagnosis system that encompasses diverse functional aspects that are required for an effective process disturbance management: (1) intelligent process monitoring and alarming, (2) on-line sensor data validation and sensor failure diagnosis, (3) on-line hardware (besides sensors) failure diagnosis, and (4) real-time corrective measure synthesis. The MOAS methodology was used at the Maiden Man-Machine Laboratory HAMMLAB of the OECD Maiden Reactor Project. The performance of MOAS, developed in G2 real-time expert system shell for the high-pressure preheaters of the NORS process in the HAMMLAB, was tested against a variety of transient scenarios, including failures of the control valves and sensors, and tube leakage of the preheaters. These tests showed that MOAS successfully carried out its intended functions, i.e., quickly recognizing an occurring disturbance, correctly diagnosing its cause, and presenting advice on its control to the operator. The lessons learned and insights gained during the implementation and performance tests also are discussed.

• Journal of Biosystems Engineering
• /
• 제34권6호
• /
• pp.470-475
• /
• 2009

This study was performed to present the diagnosis basis of cooling performance deficiency according to air quantity included in refrigerant of air-conditioner by detecting the temperatures and pressures of refrigerant pipeline. The car air-conditioner of SONATA III (Hyundai motor Co., Korea) was tested by maximum cooling condition at 1500 rpm of engine speed in the room with controlled air condition at $33\sim35^{\circ}C$ and 55~57% RH. Measured variables were temperature differences between inlet and outlet pipe surface of the compressor (Tcom), condenser (Tcon), receive dryer (Trec) and evaporator (Teva), and high pressure (HP) and low pressure (LP) in the refrigerant pipeline, and temperature difference (Tcoo) between inlet and outlet air of the cooling vent of evaporator. Control variables were the refrigerant charging weight and the vacuum degree in the refrigerant pipeline before charging refrigerant. From the test, it was represented that the measuring values of (Tcom), LP and (Tcoo) were enabled to make the diagnosis of cooling performance deficiency according to quantity included in refrigerant of air-conditioner. The ranges of Tcom, LP and Tcoo to make the diagnosis of cooling performance deficiency were respectively less than $55^{\circ}C$, more than 166.7 kPa-g(1.7 kgf/$cm^2$) and less than $13.7^{\circ}C$. In the case of using only external sensors and the condition under the normal performances of air conditioner, it was considered that the ranges of LP and Tcoo to make the diagnosis of cooling performance deficiency were respectively more than 166.7 Pa and less than $12^{\circ}C$.

• Journal of Animal Science and Technology
• /
• 제65권2호
• /
• pp.365-376
• /
• 2023

Pig breeding management directly contributes to the profitability of pig farms, and pregnancy diagnosis is an important factor in breeding management. Therefore, the need to diagnose pregnancy in sows is emphasized, and various studies have been conducted in this area. We propose a computer-aided diagnosis system to assist livestock farmers to diagnose sow pregnancy through ultrasound. Methods for diagnosing pregnancy in sows through ultrasound include the Doppler method, which measures the heart rate and pulse status, and the echo method, which diagnoses by amplitude depth technique. We propose a method that uses deep learning algorithms on ultrasonography, which is part of the echo method. As deep learning-based classification algorithms, Inception-v4, Xception, and EfficientNetV2 were used and compared to find the optimal algorithm for pregnancy diagnosis in sows. Gaussian and speckle noises were added to the ultrasound images according to the characteristics of the ultrasonography, which is easily affected by noise from the surrounding environments. Both the original and noise added ultrasound images of sows were tested together to determine the suitability of the proposed method on farms. The pregnancy diagnosis performance on the original ultrasound images achieved 0.99 in accuracy in the highest case and on the ultrasound images with noises, the performance achieved 0.98 in accuracy. The diagnosis performance achieved 0.96 in accuracy even when the intensity of noise was strong, proving its robustness against noise.

• 한국자동차공학회논문집
• /
• 제24권1호
• /
• pp.99-111
• /
• 2016

This paper presents an integrated fault diagnosis algorithm for driving motor of In-wheel independent drive electric vehicle. Especially, this paper proposes a method that integrated the high level fault diagnosis and the low level fault diagnosis in order to improve a robustness and performance of the fault diagnosis system. The high level fault diagnosis is performed using the vehicle dynamics analysis and the low level fault diagnosis is carried using the motor system analysis. The validity of the high level fault diagnosis algorithms was verified through $Carsim^{(R)}$ and MATLAB/$Simulink^{(R)}$ cosimulation and the low level fault diagnosis's validity was shown by applying it to a MATLAB/$Simulink^{(R)}$ interior permanent magnet synchronous motor control system. Finally, this paper presents a fault diagnosis strategy by combining the high level fault diagnosis and the low level fault diagnosis.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2004년도 하계학술대회 논문집 Vol.5 No.2
• /
• pp.1121-1124
• /
• 2004

Aging test to estimate life property of polymer insulator is executed through several international standard such as IEC 61109 and CEA tracking wheel test, but is not getting clear conclusion yet. There are two methods in the diagnosis method of polymer insulator such as off-line and on-line. The diagnosis methods in off-line are external condition analysis by the eye, contaminant analysis on surface, surface analysis, pollution withstand voltage test, power frequency flashover voltage test, lightning impulse flashover test, tensile fracture load test and flexural load test. The diagnosis methods in off-line most are the method for virgin and last aged sample. However, the diagnosis method in on-line is method that can be evaluate sample state as progressing continuously aging test in beginning, The diagnosis method in on-line is arranged as following: leakage current measurement, electric field, surface state investigation, thermal image, emitting light measurement and then so. In this paper, the tracking performance of polymer insulator with salt solution which is added surface active agent. The diagnosis of insulator sample has been analyzed by leakage current and visual examination.

• 한국자동차공학회논문집
• /
• 제16권4호
• /
• pp.173-178
• /
• 2008

Electro-hydraulic brake system has many advantages. It provides improved braking performance and stability functions. It also removes complex mechanical parts for freedom of design, improves maintenance requirements and reduces unit weight. However, the EHB system should be dependable and have back-up redundancy in case of a failure. In this paper, the model-based fault diagnosis system is developed to monitor the brake status using the analytical redundancy method. The performance of the model-based fault diagnosis system is verified in real-time simulation. It demonstrates the effectiveness of the proposed system in various faulty cases.

• 한국해양공학회지
• /
• 제16권5호
• /
• pp.61-65
• /
• 2002

The fault detection and diagnosis of rotating machinery widely used in plants including the ship are important for maintaining the performance of Plants. Recently, the wavelet transform has been recognized an efficient method to detect a little variation of physical quantities by the synchronous localization of time and frequency domains using the translation and dilation of signals. In this Paper, In order to develop efficient and reliable fault detection and diagnosis system rotating machines, the performance of wavelet transformation to detect a little variation of machine status and neural network to diagnose the cause of machine faults are investigated and experimented.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 A
• /
• pp.271-273
• /
• 1999

In this paper 30 kVA Super-Conducting Generator's test and analysis results of OCC and SCC are presented. Also the test and FE analysis results of the generator under 1.2, 2.4, and 3.6[kW] load are described. For FE analysis of the generator's performance, the external circuit is coupled with the FE region. The generator's end winding reactance is obtained based on the design data, actual dimension, preliminary FE analysis, and empirical formulas. The comparison of FE analysis coupled with external circuit to the test results shows a good agreement.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 추계학술대회 논문집 전기물성,응용부문
• /
• pp.37-39
• /
• 2002

UHF method is very effective to diagnosis for partial discharge of GIS. In generally, inner UHF sensor can be attached on sheath cover of GIS under construction for periodic inspection. However, there is no inner UHF sensor for GIS of the domestic substation. We used the outer UHF sensor attached on spacer for GIS of existing substation. In this paper, we report the diagnosis result of partial discharge on 800kV GIS in domestic substation. From these results, we can find the quantity, reason and location of PD and certificate the performance of UHF method for partial discharge diagnosis of GIS.

• Journal of information and communication convergence engineering
• /
• 제17권2호
• /
• pp.128-134
• /
• 2019

Based on the concept of Industry 4.0, various sensors are attached to facilities and equipment to collect data in real time and diagnose faults using analyzing techniques. Diagnostic technology continuously monitors faults or performance degradation of facilities and equipment in operation and diagnoses abnormal symptoms to ensure safety and availability through maintenance before failure occurs. In this paper, we propose a model to analyze the data and diagnose the state or failure using machine learning. The diagnosis model is based on a support vector machine (SVM)-based diagnosis model and a self-learning one-class SVM-based diagnostic model. In the future, it is expected that this model can be applied to facilities used in the entire industry by applying the actual data to the diagnostic model proposed in this paper, conducting the experiment, and verifying it through the model performance evaluation index.