• Design & Manufacturing
• /
• 제15권3호
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• 대한기계학회논문집A
• /
• 제20권10호
• /
• pp.3142-3151
• /
• 1996

As plastics shrink when changing from a molten to a solid state, mold cavities must by made larger than the product specification, In making molded gears, the teeth in the cavity must be carefully compensated for shrinkage so that the teeth of gears will have the correct profile. Two compensation methods are widely used in the cavity design. One is the compensation of a module and the other is the modification of a pressure angle and profile shifting coefficient. These methods, however, do not provide a gear cavity with all disign parameters for gears and several parameters are determined by experience. In this paper, the new design technique, namely the compensation method of design parameters, was proposed , which is based on the three kinds of shrinkage rates obtained from the measuring data of the prototype of molded gears. Using the shrinkage rates in the tip circle, tooth heigth and tooth thickness, we calculate the whole design parameters of a gear cavity. Thus, the gear cavity is considered as a complete gear with the compensated module, pressure angle, profile shifting coefficient, clearance coefficient and back lash amount so that the formula of gears can be applied to the cavity design effectively. Experimental results show that more precision molded gears can be made by using the proposed design method.