利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

9 条记录 (耗时 0.016 秒)

    Neural network system adapted for non-linear processing
    1.
    发明公开
    Neural network system adapted for non-linear processing 失效
    适用于非线性加工的神经网络系统

    公开(公告)号：EP0488150A3

    公开(公告)日：1994-06-08

    申请号：EP91120155.6

    申请日：1991-11-26

    申请人： HITACHI, LTD. ,  Hitachi Engineering Co., Ltd.

    发明人： Inoue, Haruki ,  Nakamura, Kenichi ,  Oshima, Keiji ,  Yahiro, Masakazu ,  Koide, Minoru ,  Abe, Noboru

    IPC分类号： G06F15/80

    CPC分类号： G06N3/08 ,  G06N3/0436 ,  G06N7/046 ,  Y10S706/90

    摘要： A neural network system includes a qualitative evaluation section (2), a neural network section (5), a quantifying section (3) and a display section (32). The qualitative evaluation section (2) qualitatively analyzes an unknown data supplied thereto, and normalizes the result of analysis within a predetermined range. The neural network section (5) having a neural network (6) with plural neurons computes the network output data from the normalized unknown data produced by the qualitative evaluation section (2). Each neuron is connected to plural of neurons through synapses, each of which is assigned with a weight coefficient. Each neuron is adapted to output an output function value assigned thereto associated with the total sum of the products of the output from the neurons connected thereto and the synapse weight coefficient. The quantifying section (3) quantifies the network output data to produce desired data. The desired data thus produced is displayed on the display section.

    Process control method and control system
    2.
    发明公开
    Process control method and control system 失效
    过程控制方法与控制系统

    公开(公告)号：EP0337423A3

    公开(公告)日：1990-08-16

    申请号：EP89106504.7

    申请日：1989-04-12

    申请人： HITACHI, LTD. ,  Hitachi Engineering Co., Ltd.

    发明人： Inoue, Haruki ,  Funabashi, Motohisa ,  Yahiro, Masakazu ,  Tanaka, Fumiki

    IPC分类号： G05B13/02

    CPC分类号： G06N7/04 ,  G05B13/0275 ,  Y10S706/90 ,  Y10S706/906

    摘要： The feature of this invention is that in the various process control systems of plant the actions of the process are grasped as a qualitative model to which the fuzzy theory is applied to infer and control. The process control system chiefly comprises differentiation means (2) for determining the amounts of displacement of different process amounts with respect to time, qualitative fuzzy inference means (3) for making inference of qualitative process actions, and centroid arithmetic means (4) for converting the qualitative values of the inferred control target process amounts into the amount of control by a constant amount. The conventional linear control and fuzzy control system have a difficulty in the control of the process of which the local factors are suddenly changed to greatly affect the actions of the process. This invention is able to satisfactorily follow this sudden change and thus make high-precision control.

    Neural network system adapted for non-linear processing
    4.
    发明公开
    Neural network system adapted for non-linear processing 失效
    神经元Netzwerk，angepasstfürnicht-lineare Verarbeitung。

    公开(公告)号：EP0488150A2

    公开(公告)日：1992-06-03

    申请号：EP91120155.6

    申请日：1991-11-26

    申请人： HITACHI, LTD. ,  Hitachi Engineering Co., Ltd.

    发明人： Inoue, Haruki ,  Nakamura, Kenichi ,  Oshima, Keiji ,  Yahiro, Masakazu ,  Koide, Minoru ,  Abe, Noboru

    IPC分类号： G06F15/80

    CPC分类号： G06N3/08 ,  G06N3/0436 ,  G06N7/046 ,  Y10S706/90

    摘要： A neural network system includes a qualitative evaluation section (2), a neural network section (5), a quantifying section (3) and a display section (32). The qualitative evaluation section (2) qualitatively analyzes an unknown data supplied thereto, and normalizes the result of analysis within a predetermined range. The neural network section (5) having a neural network (6) with plural neurons computes the network output data from the normalized unknown data produced by the qualitative evaluation section (2). Each neuron is connected to plural of neurons through synapses, each of which is assigned with a weight coefficient. Each neuron is adapted to output an output function value assigned thereto associated with the total sum of the products of the output from the neurons connected thereto and the synapse weight coefficient. The quantifying section (3) quantifies the network output data to produce desired data. The desired data thus produced is displayed on the display section.

    摘要翻译： 神经网络系统包括定性评估部分（2），神经网络部分（5），量化部分（3）和显示部分（32）。 定性评价部（2）定性地分析提供给其的未知数据，并将分析结果归一化在预定范围内。 具有具有多个神经元的神经网络（6）的神经网络部分（5）从由定性评估部分（2）产生的归一化未知数据计算网络输出数据。 每个神经元通过突触连接到多个神经元，每个神经元被赋予权重系数。 每个神经元适于输出与其相关联的输出功能值，其与从其连接的神经元的输出的产物和突触加权系数的总和相关联。 量化部分（3）量化网络输出数据以产生期望的数据。 由此产生的期望数据显示在显示部分上。

    Process control method and control system
    6.
    发明公开
    Process control method and control system 失效
    Prozessregelungsverfahren und Regelungssystem。

    公开(公告)号：EP0337423A2

    公开(公告)日：1989-10-18

    申请号：EP89106504.7

    申请日：1989-04-12

    申请人： HITACHI, LTD. ,  Hitachi Engineering Co., Ltd.

    发明人： Inoue, Haruki ,  Funabashi, Motohisa ,  Yahiro, Masakazu ,  Tanaka, Fumiki

    IPC分类号： G05B13/02

    CPC分类号： G06N7/04 ,  G05B13/0275 ,  Y10S706/90 ,  Y10S706/906

    摘要： The feature of this invention is that in the various process control systems of plant the actions of the process are grasped as a qualitative model to which the fuzzy theory is applied to infer and control. The process control system chiefly comprises differentiation means (2) for determining the amounts of displacement of different process amounts with respect to time, qualitative fuzzy inference means (3) for making inference of qualitative process actions, and centroid arithmetic means (4) for converting the qualitative values of the inferred control target process amounts into the amount of control by a constant amount. The conventional linear control and fuzzy control system have a difficulty in the control of the process of which the local factors are suddenly changed to greatly affect the actions of the process. This invention is able to satisfactorily follow this sudden change and thus make high-precision control.

    摘要翻译： 本发明的特征在于，在植物的各种过程控制系统中，该过程的动作被理解为将模糊理论应用于推理和控制的定性模型。 过程控制系统主要包括用于确定不同处理量相对于时间的位移量的微分装置（2），用于进行定性过程动作推理的定性模糊推理装置（3）和用于转换的质心算术装置（4） 推断的控制目标过程的定性值以恒定量计入控制量。 传统的线性控制和模糊控制系统难以控制局部因素突然变化的过程，极大地影响了过程的动作。 本发明能够令人满意地跟随这种突然变化，从而进行高精度的控制。

    Train control system
    8.
    发明公开
    Train control system 失效
    列车控制系统

    公开(公告)号：EP0615891A1

    公开(公告)日：1994-09-21

    申请号：EP94301815.0

    申请日：1994-03-15

    申请人： HITACHI, LTD.

    发明人： Murata, Satoru ,  Kawabata, Atsushi ,  Miura, Shuuichi ,  Tashiro, Korefumi ,  Morooka, Yasuo ,  Yahiro, Masakazu ,  Katahira, Masaki ,  Kera, Kazuo

    IPC分类号： B61L1/00 ,  B61L27/00 ,  B61L3/00

    CPC分类号： B61L27/0027 ,  B61L27/0022

    摘要： A train control system includes an equipment for issuing, to a train under control based on a predetermined train schedule, an operational target to be attained in terms of the aimed position, aimed time and aimed speed. Once a target is issued, a possible run region of the train is determined, and another target may be set within the possible run region such that the train is not subjected to the ATC-baed speed limitation or the like, thereby minimizing the cause of delay of the train operation.

    摘要翻译： 列车控制系统包括用于根据预定的列车时刻表向控制列车发出关于目标位置，目标时间和目标速度所达到的操作目标的设备。 一旦发布了目标，就确定列车的可能运行区域，并且可以在可能的运行区域内设置另一个目标，使得列车不经受ATC-限速等，从而使得 列车运行延误。