• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.185-195
• /
• 2018

As machines have been automated in the field of industries in recent years, it is a paramount importance to manage and maintain the automation machines. When a fault occurs in sensors attached to the machine, the machine may malfunction and further, a huge damage will be caused in the process line. To prevent the situation, the fault of sensors should be monitored, diagnosed and classified in a proper way. In the paper, we propose a sensor fault detection scheme based on SVM and CNN to detect and classify typical sensor errors such as erratic, drift, hard-over, spike, and stuck faults. Time-domain statistical features are utilized for the learning and testing in the proposed scheme, and the genetic algorithm is utilized to select the subset of optimal features. To classify multiple sensor faults, a multi-layer SVM is utilized, and ensemble technique is used for CNN. As a result, the SVM that utilizes a subset of features selected by the genetic algorithm provides better performance than the SVM that utilizes all the features. However, the performance of CNN is superior to that of the SVM.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.6 no.4
• /
• pp.327-343
• /
• 2004

During tunnel construction, ground failures often occur due to existence of weak zones, such as faults, joints, and cavities, ahead of tunnel face. It is hard to detect effectively weak zones, which can lead underground structure to fail after excavation and before supporting, by using conventional characterization methods. In this study, an enhanced analytical method of predicting weak zones ahead of tunnel face is developed to overcome some problems in the conventional geophysical exploration methods. The analytical method is based on Coulomb's and Gauss' laws with considering the characteristics of electric fields subjected to rock mass. Using the developed method, closed form solutions are obtained to detect a spherical shaped zone and an oriented fault ahead of tunnel face respectively. The analytical results suggest that the presence of weak zones and their sizes, location, and states can be accurately predicted by combining a proper inversion process with resistance measured from several electrodes on the tunnel face. It appears that the skin depth or resistivity in rock mass is affected by the diameter of tunnel face, natural electric potential and noises induced by experimental measurement and spatial distribution of uncertain properties. The developed analytical solution is verified through experimental tests. About 1800 concrete blocks of 5cm by 5cm by 5cm in size are prepared and used to model a joint rock mass around tunnel face. Weak zones are simulated ahead of tunnel face with a material which has relatively higher conductivity than concrete blocks. Experimental results on the model test show a good agreement with analytical results.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.3
• /
• pp.192-201
• /
• 2016

Condition Monitoring System (CMS) has been used to detect unexpected faults of wind turbine caused by the abrupt change of circumstances or the aging of its mechanical part. In fact, it is a very hard work to do regular inspection for its maintenance because wind turbine is located on the mountaintop or sea. The purpose of this study is to find out distribution patterns of vibration signals measured from the main mechanical parts of wind turbine according to its operation condition. To this end, acceleration signals of main bearing, gearbox, generator, wind speed, rotational speed, etc were measured through the long period more than 2 years and trend analyses on each signal were conducted as a function of the rotational speed. In addition, correlation analysis among the signals was done to grasp the relation between mechanical parts. As a result, the vibrations were dependent on the rotational speed of main shaft and whether power was generated or not, and their distributions at a specific rotational speed could be approximated to Weibull distribution. It was also investigated that the vibration at main bearing was correlated with vibration at gearbox each other, whereas vibration at generator should be dealt with individually because of generating mechanism. These results can be used for improving performance of CMS that early detects the mechanical abnormality of wind turbine.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.10
• /
• pp.2619-2627
• /
• 2009

The ground fault is occupying 70% among the total number of faults in ungrounded distribution power system. When the ground fault occurs in ungrounded system, the fault current is so small that it is hard to detect. But fault handling is very important because to continue power supply during fault conditions may cause the fault spreading and the distribution device in trouble. This paper presents the fault line detection method by using GPT signal detecting zero sequence voltage, and the fault section detection method by detecting whether GPT signal is disappeared or not during shifting normally open switch, which is connecting switch between distribution lines with open state in order to restore the outage area under emergency situation, and during isolating each section one by one which belongs to the fault line. This method is efficient because there is no whole power interruption during the fault section detection, and it is possible to perform both the fault section detection and the service restoration for the outage area at the same time, and it can apply to various distribution system configuration. Program for the fault restoration was developed applying proposed method, and it has been validated by applying to the pilot project of distribution automation system in Vietnam which has the ungrounded distribution system.