公开(公告)号：US07070368B2

公开(公告)日：2006-07-04

申请号：US10255693

申请日：2002-09-27

申请人： Shinji Murakami ,  Kazuya Hattori ,  Yoshihiko Yamada ,  Tadashi Otani ,  Atsushi Saito

发明人： Shinji Murakami ,  Kazuya Hattori ,  Yoshihiko Yamada ,  Tadashi Otani ,  Atsushi Saito

IPC分类号： B23Q15/00

CPC分类号： G05B19/416 ,  B23Q15/013 ,  G05B2219/36278 ,  G05B2219/36283 ,  G05B2219/36288 ,  Y10T409/300896 ,  Y10T409/30112 ,  Y10T409/303808

摘要： A machining feed rate for machining a workpiece portion to be machined by a machining tool based upon a machining program is set by reading a data of the workpiece portion, by sectionalizing the workpiece portion in an area corresponding to a workpiece shape of the workpiece portion, and by determining a shape change point based upon a workpiece shape of the workpiece portion. The machining feed rate is set for each area and for each shape change point with reference to a predetermined parameter corresponding to an attribute of the each sectionalized area and corresponding to an attribute of the each determined shape change point.

公开(公告)号：US5333238A

公开(公告)日：1994-07-26

申请号：US936635

申请日：1992-08-28

申请人： Yukinori Kakazu ,  Takao Yoneda ,  Tomonari Kato ,  Kazuya Hattori

发明人： Yukinori Kakazu ,  Takao Yoneda ,  Tomonari Kato ,  Kazuya Hattori

IPC分类号： G06F15/18 ,  G06G7/60 ,  G06N3/04 ,  G06N3/10 ,  G06N99/00

CPC分类号： G06N3/10 ,  G06N3/04

摘要： An apparatus for checking the input-output characteristic of a neural network which has an input layer, an intermediate layer and an output layer. Plural nodes of the input layer are related to plural nodes of the intermediate layer with plural connection weights while the plural nodes of the intermediate layer are also related to plural nodes of the output layer with plural connection weights. One of the nodes of the input layer is selected as a variable input element while the rest of the nodes are regarded as fixed input elements. A variable data input to the variable input element is varied within a predetermined variation range, while data input to the fixed input elements are fixed, so as to detect how the components of output data from the output layer change. The detected changes of the components of the output data are displayed as the input-output characteristic of the neural network.

摘要翻译： 一种用于检查具有输入层，中间层和输出层的神经网络的输入 - 输出特性的装置。 输入层的多个节点与具有多个连接权重的中间层的多个节点相关，而中间层的多个节点也与具有多个连接权重的输出层的多个节点相关。 选择输入层的一个节点作为可变输入元素，而将其余节点视为固定输入元素。 输入到可变输入元件的可变数据在预定变化范围内变化，而输入到固定输入元件的数据是固定的，以便检测来自输出层的输出数据的分量如何变化。 检测到的输出数据的分量的变化被显示为神经网络的输入 - 输出特性。

公开(公告)号：US08540598B2

公开(公告)日：2013-09-24

申请号：US13074648

申请日：2011-03-29

申请人： Mayuko Wakida ,  Motoyasu Yamamori ,  Atsushi Ando ,  Kazuya Hattori ,  Hiromichi Ota ,  Yoshinobu Kato ,  Koji Nagumo ,  Tomohiro Honda

发明人： Mayuko Wakida ,  Motoyasu Yamamori ,  Atsushi Ando ,  Kazuya Hattori ,  Hiromichi Ota ,  Yoshinobu Kato ,  Koji Nagumo ,  Tomohiro Honda

IPC分类号： F16H23/00

CPC分类号： F16H1/32 ,  F16H2001/324 ,  F16H2001/325

摘要： A speed change gear includes: an internal gear member; an eccentric member; an oscillating member; a pair of first and second rotating members; and a pin that is supported at both ends by insertion holes of the first and second rotating members. The insertion hole and the insertion hole have the same diameter. The outside diameter of the other side end portion of the pin is smaller than the outside diameter of one side end portion of the pin such that the one side end portion is press-fitted in the corresponding insertion hole and the other side end portion is supported by the corresponding insertion hole.

摘要翻译： 变速齿轮包括：内齿轮构件; 偏心构件 摆动构件; 一对第一和第二旋转构件; 以及通过第一和第二旋转构件的插入孔在两端支撑的销。 插入孔和插入孔具有相同的直径。 销的另一侧端部的外径小于销的一个侧端部的外径，使得一侧端部压配合在相应的插入孔中，另一侧端部被支撑 通过相应的插孔。

公开(公告)号：US5355434A

公开(公告)日：1994-10-11

申请号：US931324

申请日：1992-08-18

申请人： Takao Yoneda ,  Tomonari Kato ,  Kazuya Hattori ,  Masashi Yamanaka ,  Shiho Hattori

发明人： Takao Yoneda ,  Tomonari Kato ,  Kazuya Hattori ,  Masashi Yamanaka ,  Shiho Hattori

IPC分类号： G06N3/08 ,  G06N3/10 ,  G06F15/18

CPC分类号： G06N3/10 ,  G06N3/08

摘要： An apparatus for carrying out learning operation of a neural network which has an input layer, an intermediate layer and an output layer. Plural nodes of the input layer are related to plural nodes of the intermediate layer with plural connection weights, while the plural nodes of the intermediate layer are also related to plural nodes of the output layer with plural connection weights. Although input data composed of plural components and teaching data composed of plural components are used in learning operation, some of the components are ineffective for the purpose of learning operation. During error calculation between output data from the neural network and the teaching data, the apparatus judges whether each of the components of the teaching data is effective or ineffective, and output errors corresponding to the ineffective components are regarded as zero. The connection weights are thereafter corrected based upon the calculated errors. The apparatus further comprises means for adding new input data and teaching data into a data base, and means for calculating a degree of heterogeneousness of the new teaching data. The new input data and teaching data are added to the data base only when the degree of heterogeneousness is smaller than a predetermined value.

摘要翻译： 一种用于执行具有输入层，中间层和输出层的神经网络的学习操作的装置。 输入层的多个节点与具有多个连接权重的中间层的多个节点相关，而中间层的多个节点也与具有多个连接权重的输出层的多个节点相关。 虽然在学习操作中使用由多个分量组成的输入数据和由多个分量组成的教学数据，但是为了学习操作的目的，一些组件是无效的。 在神经网络的输出数据与教学数据的误差计算期间，设备判断教学数据的各个成分是否有效或无效，与无效分量相对应的输出误差为零。 然后根据计算的误差校正连接权重。 该装置还包括用于将新的输入数据和教学数据添加到数据库中的装置，以及用于计算新教学数据的异质程度的装置。 仅当异质度小于预定值时，才将新的输入数据和教学数据添加到数据库。