专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

DE69032557T2 未知
公开(公告)号：DE69032557T2
公开(公告)日：1999-05-06
申请号：DE69032557
申请日：1990-03-13
申请人： HITACHI LTD
发明人： BABA KENJI , ENBUTSU ICHIRO , WATANABE SHOJI , YAHAGI HAYAO , MARUHASHI FUMIO , MATSUZAKI HARUMI , MATSUMOTO HIROSHI , NOGITA SHUNSUKE , YODA MIKIO , HARA NAOKI
IPC分类号： G06F15/18 , G05B11/32 , G05B13/02 , G05B13/04 , G05B19/02 , G05B23/02 , G06F9/44 , G06G7/60 , G06N3/00 , G06N3/08 , G06N5/04 , G06N7/02
摘要： A method for extracting as knowledge causal relationships between input variables and an output variable of a neural circuit model, said neural circuit model being of a hierarchical structure constructed of an input layer, at least one hidden layer and an output layer and having performed learning a limited number of times by determining weight factors between mutually-connected neuron element models in different layers of the input layer, hidden layer and output layer, wherein with respect to plural routes extending from a neuron element model, corresponding to a particular input variable, of the input layer to a neuron element model, corresponding to a particular output variable, of the output layer by way of the individual neuron element models of the hidden layer, a product of the weight factors for each of the routes is determined, and the products for the plural routes are summed, whereby the sum is employed as a measure for the determination of the causal relationship between the particular input variable and the particular output variable.

2. 发明专利

DE69033328T2 未知
公开(公告)号：DE69033328T2
公开(公告)日：2000-05-31
申请号：DE69033328
申请日：1990-03-13
申请人： HITACHI LTD
发明人： BABA KENJI , EMBUTSU ICHIRO , WATANABE SHOJI , YAHAGI HAYAO , MARUHASHI FUMIO C O HITACHI IN , MATSUZAKI HARUMI , MATSUMOTO HIROSHI , NOGITA SHUNSUKE , YODA MIKIO , HARA NAOKI
IPC分类号： G06F15/18 , G05B11/32 , G05B13/02 , G05B13/04 , G05B19/02 , G05B23/02 , G06F9/44 , G06G7/60 , G06N3/00 , G06N3/08 , G06N5/04 , G06N7/02
摘要： A method for extracting as knowledge causal relationships between input variables and an output variable of a neural circuit model, said neural circuit model being of a hierarchical structure constructed of an input layer, at least one hidden layer and an output layer and having performed learning a limited number of times by determining weight factors between mutually-connected neuron element models in different layers of the input layer, hidden layer and output layer, wherein with respect to plural routes extending from a neuron element model, corresponding to a particular input variable, of the input layer to a neuron element model, corresponding to a particular output variable, of the output layer by way of the individual neuron element models of the hidden layer, a product of the weight factors for each of the routes is determined, and the products for the plural routes are summed, whereby the sum is employed as a measure for the determination of the causal relationship between the particular input variable and the particular output variable.

3. 发明专利

DE3780673T2 未知
公开(公告)号：DE3780673T2
公开(公告)日：1992-12-10
申请号：DE3780673
申请日：1987-04-06
申请人： HITACHI LTD
发明人： BABA KENJI , WATANABE SHOJI , HARA NAOKI , YODA MIKIO , MORI SHUNJI , NOGITA SHUNSUKE , YAMASAWA YUZI , AKIYAMA TOSHIMITU
IPC分类号： C02F1/52 , C02F1/68 , G01N33/18
摘要： An injection control system of a flocculating agent comprises: a flocculating pool (15) into which the inflow liquid flocculating agent (11) is injected and which forms flocs of suspended matters in the liquid; flocculating agent injection means (12) for injecting the flocculating agent into the flocculating pool (15); floc image pickup means (18) for photographing a state of the flocs in the flocculating pool (15) and for converting luminance data of the flocs into an electric signal; image recognizing means (30) for recognizing the shape of floc by binarizing the image signal derived from the floc image pickup means (18) on the basis of a luminance level of each pixel; flocculation state deciding means (80) for calculating a characteristic amount of a diameter distribution of the flocs on the basis of the floc shapes recognized by the image recognizing means (30); and injection amount control means (100) for controlling an amount of the flocculating agent which is injected from the flocculating agent injection means (12) on the basis of the characteristic amount.

4. 发明专利

DE69217746D1 未知
公开(公告)号：DE69217746D1
公开(公告)日：1997-04-10
申请号：DE69217746
申请日：1992-06-22
申请人： HITACHI LTD
发明人： ENBUTSU ICHIRO , BABA KENZI , HARA NAOKI , YODA MIKIO , WATANABE SHOJI , YAHAGI HAYAO
IPC分类号： G05B13/02 , G06F9/44 , G06F15/18 , G06N3/00 , G06N3/04 , G06N5/04 , G06N7/02
摘要： In order to speed up, and simplify, automated learning of rules by a neural network making use of fuzzy logic, data (120) from a system is analyzed by a teaching data creation means (140). This groups the data into clusters and then selects a representative data item from each group for subsequent analysis. The selected data items are passed to a rule extraction means (180). This investigates relationships between the data items, to derive rules, but eliminates rules which have only an insignificant effect on the system. The result are candidate rules which are stored in a first rule base (200). The candidate rules are then compared with rules in a second rule base (240) to check for duplication and/or contradiction. Only those rules which are not duplicated and not contradictory are stored in the second rule base (240). Hence, when fuzzy inference is used to control the system on the basis of rules in the second rule base (240), only valid rules which provide a significant effect on the system are used.

5. 发明专利

DE69217746T2 未知
公开(公告)号：DE69217746T2
公开(公告)日：1997-10-23
申请号：DE69217746
申请日：1992-06-22
申请人： HITACHI LTD
发明人： ENBUTSU ICHIRO , BABA KENZI , HARA NAOKI , YODA MIKIO , WATANABE SHOJI , YAHAGI HAYAO
IPC分类号： G05B13/02 , G06F9/44 , G06F15/18 , G06N3/00 , G06N3/04 , G06N5/04 , G06N7/02
摘要： In order to speed up, and simplify, automated learning of rules by a neural network making use of fuzzy logic, data (120) from a system is analyzed by a teaching data creation means (140). This groups the data into clusters and then selects a representative data item from each group for subsequent analysis. The selected data items are passed to a rule extraction means (180). This investigates relationships between the data items, to derive rules, but eliminates rules which have only an insignificant effect on the system. The result are candidate rules which are stored in a first rule base (200). The candidate rules are then compared with rules in a second rule base (240) to check for duplication and/or contradiction. Only those rules which are not duplicated and not contradictory are stored in the second rule base (240). Hence, when fuzzy inference is used to control the system on the basis of rules in the second rule base (240), only valid rules which provide a significant effect on the system are used.

6. 发明专利

DE69033328D1 未知
公开(公告)号：DE69033328D1
公开(公告)日：1999-11-18
申请号：DE69033328
申请日：1990-03-13
申请人： HITACHI LTD
发明人： BABA KENJI , EMBUTSU ICHIRO , WATANABE SHOJI , YAHAGI HAYAO , MARUHASHI FUMIO C O HITACHI IN , MATSUZAKI HARUMI , MATSUMOTO HIROSHI , NOGITA SHUNSUKE , YODA MIKIO , HARA NAOKI
IPC分类号： G06F15/18 , G05B11/32 , G05B13/02 , G05B13/04 , G05B19/02 , G05B23/02 , G06F9/44 , G06G7/60 , G06N3/00 , G06N3/08 , G06N5/04 , G06N7/02
摘要： A method for extracting as knowledge causal relationships between input variables and an output variable of a neural circuit model, said neural circuit model being of a hierarchical structure constructed of an input layer, at least one hidden layer and an output layer and having performed learning a limited number of times by determining weight factors between mutually-connected neuron element models in different layers of the input layer, hidden layer and output layer, wherein with respect to plural routes extending from a neuron element model, corresponding to a particular input variable, of the input layer to a neuron element model, corresponding to a particular output variable, of the output layer by way of the individual neuron element models of the hidden layer, a product of the weight factors for each of the routes is determined, and the products for the plural routes are summed, whereby the sum is employed as a measure for the determination of the causal relationship between the particular input variable and the particular output variable.

7. 发明专利

DE69032557D1 未知
公开(公告)号：DE69032557D1
公开(公告)日：1998-09-17
申请号：DE69032557
申请日：1990-03-13
申请人： HITACHI LTD
发明人： BABA KENJI , ENBUTSU ICHIRO , WATANABE SHOJI , YAHAGI HAYAO , MARUHASHI FUMIO , MATSUZAKI HARUMI , MATSUMOTO HIROSHI , NOGITA SHUNSUKE , YODA MIKIO , HARA NAOKI
IPC分类号： G06F15/18 , G05B11/32 , G05B13/02 , G05B13/04 , G05B19/02 , G05B23/02 , G06F9/44 , G06G7/60 , G06N3/00 , G06N3/08 , G06N5/04 , G06N7/02
摘要： A method for extracting as knowledge causal relationships between input variables and an output variable of a neural circuit model, said neural circuit model being of a hierarchical structure constructed of an input layer, at least one hidden layer and an output layer and having performed learning a limited number of times by determining weight factors between mutually-connected neuron element models in different layers of the input layer, hidden layer and output layer, wherein with respect to plural routes extending from a neuron element model, corresponding to a particular input variable, of the input layer to a neuron element model, corresponding to a particular output variable, of the output layer by way of the individual neuron element models of the hidden layer, a product of the weight factors for each of the routes is determined, and the products for the plural routes are summed, whereby the sum is employed as a measure for the determination of the causal relationship between the particular input variable and the particular output variable.

8. 发明专利

DE3780673D1 未知
公开(公告)号：DE3780673D1
公开(公告)日：1992-09-03
申请号：DE3780673
申请日：1987-04-06
申请人： HITACHI LTD
发明人： BABA KENJI , WATANABE SHOJI , HARA NAOKI , YODA MIKIO , MORI SHUNJI , NOGITA SHUNSUKE , YAMASAWA YUZI , AKIYAMA TOSHIMITU
IPC分类号： C02F1/52 , C02F1/68 , G01N33/18
摘要： An injection control system of a flocculating agent comprises: a flocculating pool (15) into which the inflow liquid flocculating agent (11) is injected and which forms flocs of suspended matters in the liquid; flocculating agent injection means (12) for injecting the flocculating agent into the flocculating pool (15); floc image pickup means (18) for photographing a state of the flocs in the flocculating pool (15) and for converting luminance data of the flocs into an electric signal; image recognizing means (30) for recognizing the shape of floc by binarizing the image signal derived from the floc image pickup means (18) on the basis of a luminance level of each pixel; flocculation state deciding means (80) for calculating a characteristic amount of a diameter distribution of the flocs on the basis of the floc shapes recognized by the image recognizing means (30); and injection amount control means (100) for controlling an amount of the flocculating agent which is injected from the flocculating agent injection means (12) on the basis of the characteristic amount.

9. 发明专利

JP2010063954A Liquid treatment apparatus 有权
标题翻译：液体处理设备
公开(公告)号：JP2010063954A
公开(公告)日：2010-03-25
申请号：JP2008230400
申请日：2008-09-09
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： SUMIKURA MISAKI , HIDAKA MASATAKA , TAKEMOTO TAKESHI , WATANABE SHOJI , ENBUTSU ICHIRO , NOBUTOMO YOSHIHIRO , TADOKORO HIDEYUKI , HARA NAOKI
IPC分类号： C02F1/78 , C02F1/24 , C02F1/32 , C02F1/50 , C02F1/76
摘要： PROBLEM TO BE SOLVED: To reduce operating cost for the whole processes by separating objects into objects to be removed suitable for an ozone treatment process and objects to be removed suitable for a sterilization process and achieving target water quality by the processes. SOLUTION: A liquid treatment apparatus includes an ozone generator 3 for injecting ozone gas which reacts with water to be treated in an ozone contact tank 2, a colorimeter 8 in a passage connected to the ozone contact tank 2, a chlorine injector 11 for injecting a chlorine agent into an ultraviolet irradiation tank 6 equipped with an ultraviolet lamp and connected to the passage or into the passage, and an input means 10 for performing input into a controller 9 controlling the ozone generator 3, the ultraviolet lamp, or the chlorine injector 11. The output of the ozone generator 3 is controlled from a deviation between the target value of a first water quality item from the input means 10 and a value of the first water quality item measured by a water quality measuring meter. The output of the ultraviolet lamp or the injection rate of the chlorine agent of the chlorine injector 11 is controlled from the target value of a second water quality item from the input means 10 by a relationship between the first water quality item and ultraviolet irradiation or a relationship between the first water quality item and the injection rate of the chlorine agent. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：通过将物体分离成适合于臭氧处理过程的待去除物体和适于灭菌过程的待去除物体并通过该过程实现目标水质来降低整个过程的操作成本。解决方案：液体处理装置包括臭氧发生器3，其用于在臭氧接触罐2中喷射与待处理的水反应的臭氧气体，连接到臭氧接触罐2的通道中的色度计8，氯喷射器11 用于将氯剂注入装有紫外线灯并连接到通道或通道的紫外线照射罐6中，以及输入装置10，用于输入到控制臭氧发生器3，紫外线灯或氯喷射器11.臭氧发生器3的输出由来自输入装置10的第一水质物品的目标值与由水质量测量计测量的第一水质物品的值之间的偏差控制。通过第一水质项目和紫外线照射之间的关系，从输入装置10的第二水质项目的目标值控制氯注射器11的氯剂的输出或氯气喷射量的输出，或第一个水质项目与氯剂的喷射率之间的关系。版权所有（C）2010，JPO＆INPIT

10. 发明专利

JP2009233622A Water treatment device 审中-公开
标题翻译：水处理设备
公开(公告)号：JP2009233622A
公开(公告)日：2009-10-15
申请号：JP2008085588
申请日：2008-03-28
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： YAMANOI ICHIRO , ENBUTSU ICHIRO , KAGEYAMA KOJI , HARA NAOKI , WATANABE SHOJI , TAKEMOTO TAKESHI
IPC分类号： B01D65/08 , B01D65/02 , C02F1/44 , C02F3/12
CPC分类号： Y02W10/15
摘要： PROBLEM TO BE SOLVED: To suppress the formation of an instable main stream part by minute turbulence to obtain an excellent cleaning effect of a membrane element. SOLUTION: In a biological treatment tank 1 filled with an active sludge mixture liquid 11, a membrane unit 2 composed of a plurality of membrane elements 21 having a filtration action is immersed, and an aeration tube 4 is provided below it. Air supplied from an aeration blower 5 is discharged as bubbles 12 from the aeration tube 4, and the discharged bubbles 12 form an elevating flow, pass through a flow speed adjuster 3 and flow into the inter-membrane flow path 22 of the membrane unit 2. A recessed part in an inverse chevron shape or a chevron shape is provided on the upper side or lower side of the flow speed adjuster 3, and the flow path resistance of a center part is small. Thus, a flow speed at the center part of the inter-membrane flow path 22 becomes high, and a stable main stream part is formed at the center part of the inter-membrane flow path 22. Since the bubbles 12 of the stable main stream part act on the membrane elements 21, the deposition of active sludge is prevented, and the formation of the instable main stream part is suppressed. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：为了通过微小的湍流抑制不稳定主流部分的形成，以获得优异的膜元件清洁效果。解决方案：在填充有活性污泥混合液11的生物处理槽1中，浸渍由具有过滤作用的多个膜元件21构成的膜单元2，在其下方设置曝气管4。从曝气鼓风机5供给的空气从曝气管4排出为气泡12，排出的气泡12形成升降流，通过流量调节器3流入膜单元2的膜间流路22 在流速调节器3的上侧或下侧设置有倒V形或V形形状的凹部，中心部的流路阻力小。因此，膜间流路22的中央部的流速变高，在膜间流路22的中心部形成稳定的主流部。由于稳定主流的气泡12 部分作用在膜元件21上，防止了活性污泥的沉积，并且抑制了不稳定主流部分的形成。版权所有（C）2010，JPO＆INPIT

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式