• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.49 no.1
• /
• pp.31-36
• /
• 2000

To enhance the fault diagnosis ability for the dissolved gas analysis(DGA) of the power transformer, this paper proposes a learning vector quantization(LVQ) for the incipient fault recognition. LVQ is suitable expecially for pattern recognition such as fault diagnosis of power transformer using DGA because it improves the performance of Kohonen neural network by placing emphasis on the classification around the decision boundary. The capabilities of the proposed diagnosis system for the transformer DGA decision support have been extensively verified through the practical test data collected from Korea Electrical Power Corporation.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.26 no.3
• /
• pp.61-68
• /
• 2012

This paper deals with a fault diagnosis algorithm for open faults in the switching devices of PWM inverter-fed IPMSM (Interior Permanent Magnet Synchronous Motor) drive. The proposed diagnostic algorithm is realized in the controller using the informations of three-phase currents or reference line-to-line voltages, without requiring additional equipments for fault detection. Under switch open fault conditions, the conventional dq model used to control an AC motor cannot directly be applied for the analysis of drive system, since three-phase balanced condition does not hold. To overcome this limitation, a fault model based on the line-to-line voltages is employed for the simulation studies. For comparative performance evaluation through the experiments, the entire control system is implemented using digital signal processor (DSP) TMS320F28335. Simulations and experimental results are presented to verify the validity of the proposed diagnosis algorithm.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.54-63
• /
• 2023

High and intermittent loading cycles induce fatigue damage to transmission components, resulting in premature gearbox failure. To identify gearbox defects, numerous vibration-based diagnostics techniques, using several artificial intelligence (AI) algorithms, have recently been presented. In this paper, an optimized deep belief network (DBN) model for gearbox problem diagnosis was designed based on time-frequency visual pattern identification. To optimize the hyperparameters of the model, a particle swarm optimization (PSO) approach was integrated into the DBN. The proposed model was tested on two gearbox datasets: a wind turbine gearbox and an experimental gearbox. The optimized DBN model demonstrated strong and robust performance in classification accuracy. In addition, the accuracy of the generated datasets was compared using traditional ML and DL algorithms. Furthermore, the proposed model was evaluated on different partitions of the dataset. The results showed that, even with a small amount of sample data, the optimized DBN model achieved high accuracy in diagnosis.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.11 no.1
• /
• pp.95-103
• /
• 2003

Driving safety of a vehicle is largely influenced by the damper and the tire. Developed in this research is a fault diagnosis algorithm for the two components so that the driver can be promptly informed when fault occurs in one or both of them. To this end, the damper and the tire were modeled using the neural network from their experimental data, and fault diagnosis was made using frequency responses of the damping force and the dynamic wheel force. The algorithm was tested via experiments, and it demonstrated successful diagnostic performance under various driving conditions.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.7
• /
• pp.3651-3658
• /
• 2016

Computer-aided diagnosis of breast cancer is an important medical approach. In this research paper, we focus on combining two major methodologies, namely fuzzy base systems and the evolutionary genetic algorithms and on applying them to the Saudi Arabian breast cancer diagnosis database, to aid physicians in obtaining an early-computerized diagnosis and hence prevent the development of cancer through identification and removal or treatment of premalignant abnormalities; early detection can also improve survival and decrease mortality by detecting cancer at an early stage when treatment is more effective. Our hybrid algorithm, the genetic-fuzzy algorithm, has produced optimized systems that attain high classification performance, with simple and readily interpreted rules and with a good degree of confidence.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.4 no.1
• /
• pp.23-28
• /
• 2009

Testing of analog(and mixed-signal) circuits has been a difficult task for test engineers and effective test techniques to solve these problems are required. This paper develops a new technique which increases fault detection and diagnosis rates for analog circuits by using extended MTSS (Modified Time Slot Specification) technique based on MTSS proposed by the author. High performance current sensors with digital outputs are used as core components for these techniques. A fault diagnosis structure with minimal hardware overhead in ATE is also described.

• Transactions of the Korean Society of Pressure Vessels and Piping
• /
• v.19 no.1
• /
• pp.44-51
• /
• 2023

The RCP is one of the main components in nuclear power plants and plays an important role in circulating coolant to the RCS system. Currently, nuclear plants are monitored using various monitoring systems. However, since they operate independently according to their functional purpose, it is not able to analyze vibration and operation/performance information comprehensively, and thus failure diagnosis accuracy is limited. In addition, these systems do not provide some important information (such as fault type, parts and cause) necessary for emergency actions, but provide only alarm information. To improve these technical problems, this study proposes a diagnosis technique (M/L, Rule-based model, Data-driven model, Narrow band model) and methodology for comprehensive analysis.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.4C
• /
• pp.313-320
• /
• 2012

An ECG(Electrocardiogram) compression can increase the processing speed of system as well as reduce amount of signal transmission and data storage of long-term records. Whereas conventional performance evaluations of loss or lossless compression algorithms measure PRD(Percent RMS Difference) and CR(Compression Ratio) in the viewpoint of engineers, this paper focused on the performance evaluations of compression algorithms in the viewpoint of diagnostician who diagnosis ECG. Generally, for not effecting the diagnosis in the ECG compression, the position, length, amplitude and waveform of the restored signal of PQRST wave should not be damaged. AZTEC, a typical ECG compression algorithm, is validated its effectiveness in conventional performance evaluation. In this paper, we propose novel performance evaluation of AZTEC in the viewpoint of diagnostician.

• Journal of the Korean Society of Safety
• /
• v.33 no.2
• /
• pp.21-27
• /
• 2018

The expansion and stable operation of electric power facilities are important factors with development of industrial facilities in modern society. In high-voltage equipment such as GIS, the insulation characteristics may be deterioated by environment-friendly gas adaption and miniaturization. There is also the possibility of accidents due to insulation breakdown due to the deterioration of power facilities. Therefore, it is necessary to extend the diagnosis system to continuously monitor the danger signals of these power equipment and to prevent accidents. Most of the internal defects in the GIS system are conductive particles, floating electrode defects, protrusion defects, and the like. In this case, a partial discharge phenomenon is accompanied. These partial discharge signals occur irregularly and various noise signals are included in the field, so it is difficult to evaluate the reliability in the development of the diagnostic system. In this paper, a study was made on equipment capable of generating a partial discharge simulated signal that can be adjusted in size and frequency to be applied to a diagnostic device by electromagnetic wave detection method. The PD simulated pulse generator consists of a user interface module, a high-voltage charging module, a pulse forming circuit, a voltage sensor and an embedded controller. In order to simulate the partial discharge phenomenon similar to the actual GIS, a discharge cell was designed and fabricated. The application of the prototype pulse generator to the commercialized PD diagnosis module confirmed that it can be used to evaluate the performance of the diagnostic device. It can be used for the development of GIS diagnosis system and performance verification for reliability evaluation.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.445-454
• /
• 2023

Recently, various fault diagnosis studies are being conducted utilizing data from collaborative robots. Existing studies performing fault diagnosis on collaborative robots use static data collected based on the assumed operation of predefined devices. Therefore, the fault diagnosis model has a limitation of increasing dependency on the learned data patterns. Additionally, there is a limitation in that a diagnosis reflecting the characteristics of collaborative robots operating with multiple joints could not be conducted due to experiments using a single motor. This paper proposes an LSTM diagnostic model that can overcome these two limitations. The proposed method selects representative normal patterns using the correlation analysis of vibration and current data in single-axis and multi-axis work environments, and generates residual patterns through differences from the normal representative patterns. An LSTM model that can perform gear wear diagnosis for each axis is created using the generated residual patterns as inputs. This fault diagnosis model can not only reduce the dependence on the model's learning data patterns through representative patterns for each operation, but also diagnose faults occurring during multi-axis operation. Finally, reflecting both internal and external data characteristics, the fault diagnosis performance was improved, showing a high diagnostic performance of 98.57%.