• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.18 no.10
• /
• pp.791-799
• /
• 2006

The fault diagnosis technologies may be applied in order to decrease the energy consumption and the maintenance cost of an air-conditioning system. In this paper, a fault diagnosis algorithm was developed by using a neural no-fault model and a dual fuzzy logic. Five different faults, such as the compressor valve leakage, the liquid line blockage, the condenser fouling, the evaporator fouling, and the refrigerant leakage of an air-conditioning system, were considered. The fault diagnosis algorithm was tested by using a fault simulation facility. Test results showed that the algorithm developed for this study was effective to detect and diagnose various faults. Therefore, this algorithm may be practically used for the fault diagnosis of an air-conditioning system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• Proceedings of the SAREK Conference
• /
• 2005.06a
• /
• pp.164-164
• /
• 2005

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.3
• /
• pp.1-13
• /
• 2010

The aim of this study is to analyze gold-silver mineral potential in the Taebaeksan mineralized district, Korea using a Geographic Information System(GIS) and an artificial neural network(ANN) model. A spatial database considering Au and Ag deposit, geology, fault structure and geochemical data of As, Cu, Mo, Ni, Pb and Zn was constructed for the study area using the GIS. The 46 Au and Ag mineral deposits were randomly divided into a training set to analyze mineral potential using ANN and a test set to verify mineral potential map. In the ANN model, training sets for areas with mineral deposits and without them were selected randomly from the lower 10% areas of the mineral potential index derived from existing mineral deposits using likelihood ratio. To support the reliability of the Au-Ag mineral potential map, some of rock samples were selected in the upper 5% areas of the mineral potential index without known deposits and analyzed for Au, Ag, As, Cu, Pb and Zn. As the result, No. 4 of sample exhibited more enrichments of all elements than the others.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.5
• /
• pp.1401-1408
• /
• 2000

Critical prediction models that determine whether a design entity is fault-prone or non fault-prone play an important role in reducing system development cost because the problems in early phases largely affected the quality of the late products. Real-time systems such as telecommunication system are so large that criticality prediction is more important in real-time system design. The current models are based on the technique such as discriminant analysis, neural net and classification trees. These models have some problems with analyzing cause of the prediction results and low extendability. In this paper, we propose a criticality prediction model using fuzzy rulebase constructed by genetic algorithm. This model makes it easy to analyze the cause of the result and also provides high extendability, high applicability, and no limit on the number of rules to be found.