日本ゴム協会誌
Print ISSN : 0029-022X
検索
詳細検索
OR
閲覧
検索
91 巻, 1 号
選択された号の論文の6件中1～6を表示しています
すべての抄録を表示する
    • |<
    • <
    • 1
    • >
    • >|
研究論文
  • ディープラーニングを用いたゴム中フィラー凝集構造の画像判別の特性評価
    萩田 克美, 冨永 哲雄, 曽根 卓男, 高橋 一郎, CHONHO LEE, 荻野 正雄
    2018 年 91 巻 1 号 p. 3-8
    発行日: 2018年
    公開日: 2018/05/03
    DOIhttps://doi.org/10.2324/gomu.91.3
    ジャーナル フリー
    抄録を表示する抄録を非表示にする

    Image classification with deep learning of convolutional neural networks (CNN) for sliced snapshots of filler morphologies in rubber materials are examined. The sliced snapshots are generated from the filler morphologies modeled by reverse Monte Carlo analysis from USAXS data of rubber composites obtained in the large synchrotron radiation facility SPring-8. In the present paper, we considered an image classification problem into 3 classes, which are fillers in the end-modified SBR and the non-modified SBR, and randomly placed points. We evaluated effects of area size and number of the used snapshots for training process on generalization ability for images which are independent from the training. The examined area sizes are (250 nm)2, (500 nm)2, and (1,000 nm)2. The examined numbers are 500, 2,000, and 8,000 per class. Here, the used architecture of CNNs consists of 4 convolution layers, 4 max-pooling layers and 3 fully-connected layers, where dropout on the fully-connected layers are used for the training. We found that the area sizes larger than (500 nm)2 and the number larger than 2,000 per class are required for good image classification. We also confirmed the generalization ability of this deep learning method is better than that of the support vector machine (SVM) for HOG (histogram of oriented gradient) descriptors.

    抄録全体を表示
    PDF形式でダウンロード (1190K)
特論講座
  • スチールコードとゴムの接着（4）
    －樹脂の接着への効果－
    石川 泰弘
    2018 年 91 巻 1 号 p. 9-12
    発行日: 2018年
    公開日: 2018/05/03
    DOIhttps://doi.org/10.2324/gomu.91.9
    ジャーナル フリー
    抄録を表示する抄録を非表示にする

    Compounds containing RF (resorcinol-formaldehyde) resin/HMMM (hexamethoxymethylmelamine) condensate and one-component of HMMM resins keep a high level of adhesion.

    RF resin condensate has two functions: capturing an amine that deteriorates adhesion in the brass layer (stress corrosion crack of brass) and formation of a strong resin layer at the interface by the resinification reaction.

    To have two functions, the amount of HMMM must be higher than the amount of RF resin.

    The adhesion mechanism to explain the action of hydrogen from the one-component resins in the CuxS lattice is based upon its interaction with the defects to reduce the diffusion of Cu+ ions, avoiding the possibility of overgrowth.

    抄録全体を表示
    PDF形式でダウンロード (604K)
  • ものづくりにおける安全の追求
    第4回　マテリアルリサイクルに学ぶゴム・プラスチックの劣化対策とバイオ燃料の落とし穴（そのⅠ マテリアルリサイクル）
    大武 義人
    2018 年 91 巻 1 号 p. 13-20
    発行日: 2018年
    公開日: 2018/05/03
    DOIhttps://doi.org/10.2324/gomu.91.13
    ジャーナル フリー
    抄録を表示する抄録を非表示にする

    A large amount of antioxidant is added to recycled plastic products. The amount reaches nearly ten times of the virgin. This reason is to prevent shortening of the lifetime caused by autoxidation. The recycled products contain much amount of radicals due to damage during re-molding and using, even if the physical properties are not affected.

    抄録全体を表示
    PDF形式でダウンロード (1440K)
報告
紹介
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top