• Journal of Industrial Technology
• /
• v.18
• /
• pp.379-384
• /
• 1998

Conventional short-term load forecasting techniques have limitation in their use on holidays due to dissimilar load behaviors of holidays and insufficiency of pattern data. Thus, a new short-term load forecasting method for special days in anomalous load conditions is proposed in this paper. The proposed method uses two Artificial Neural Networks(ANN); one is for the estimation of load curve, and the other is for the estimation of minimum and maximum value of load. The forecasting procedure is as follows. First, the normalized load curve is estimated by ANN. At next step, minimum and maximum values of load in a special day are estimated by another ANN. Finally, the estimate of load in a whole special day is obtained by combining these two outputs of ANNs. The proposed method shows a good performance, and it may be effectively applied to the practical situations.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.05a
• /
• pp.991-996
• /
• 2004

The international competition in refrigerator markets has continuously required the research for sound quality of a refrigerator to improve the quality of a life. In this paper, A new method for evaluation of the sound quality of a refrigerator is developed based on human sensibility engineering by using ANN(Artificial neural network). Finally it is applied to evaluate the sound qualify of refrigerator on the production line.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.11
• /
• pp.1195-1202
• /
• 2004

The international competition in refrigerator markets has continuously required the research for sound quality of a refrigerator to improve the quality of a life. In this paper, A new method for evaluation of the sound quality of a refrigerator is developed based on human sensibility engineering by using ANN(artificial neural network). In this paper, the loudness and the sharpness of the refrigerator's signals was used for the input value in ANN's training process because the loudness and the sharpness has a good correlation between the output of the ANN and the target of the individual evaluation In the training process. Two input factor was used repeatedly in the training process to get more optimum weighting value. And then finally we developed the sound quality index of a refrigerator. The developed sound quality index was confirmed by the 96.5 % of correlation between the output of the ANN and the real evaluation. It will be applied to evaluate the sound quality of a refrigerator in the industry.