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

JPH04330524A FUZZY CONTROL DEVICE USING NEURAL NETWORK 失效
公开(公告)号：JPH04330524A
公开(公告)日：1992-11-18
申请号：JP882691
申请日：1991-01-29
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： WATABE NOBUO , KAWAMURA AKIRA , MASUOKA RYUSUKE , OOWADA YURI , ASAKAWA KAZUO , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06F9/44 , G06F15/18 , G06G7/60 , G06N3/00 , G06N99/00
摘要： PURPOSE:To effectively utilize a learning function by constituting all parts from a fuzzy control rule part up to a consequent part membership function attaining part of a neural network. CONSTITUTION:The consequent part membership function attaining part 1 is constituted of the 1st layer 2 provided with plural neuro units for inputting and distributing the adapting of each fuzzy rule and a division network 3 for outputting a value Y obtained by dividing a linear sum A which is obtained by weighting a representative value of each rule by a grade outputted from the 1st layer by the sum B of grades. Connection weight values between respective neuro units of the 1st layer and the 1st neuro unit of the division network input layer are set up to the representative values t1 to tn of output variables corresponding to respective fuzzy rules and connection weight with the 2nd neuro unit of the division network input layer is '1' in all the neuro units of the 1st layer. Only the connection weight values t1 to the between respective neuro units of the 1st layer and the 1st neuro unit of the devision network input layer are learned.

2. 发明专利

JPH04275633A CONSTRUCTION SYSTEM FOR MEMBERSHIP FUNCTION BY NEURAL NETWORK 失效
公开(公告)号：JPH04275633A
公开(公告)日：1992-10-01
申请号：JP3598591
申请日：1991-03-01
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： WATABE NOBUO , KAWAMURA AKIRA , MASUOKA RYUSUKE , OOWADA ARIMICHI , ASAKAWA KAZUO , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06F9/44 , G06F15/18 , G06N3/00 , G06N7/02 , G06N99/00
摘要： PURPOSE:To approximate a neuron characteristic function while minimizing the absolute value of the error against a membership function without performing learning by realizing the membership function in a fuzzy control with the neuron characteristic function. CONSTITUTION:The maximum gradient of the sigmoid function as a neuron characteristic function is set by obtaining the weight and threshold value with 1.3401 times of the gradient of the membership function large or small.

3. 发明专利

JPH0498356A NEURAL NETWORK WHICH CAN OUTPUT COMBINED WEIGHT 失效
公开(公告)号：JPH0498356A
公开(公告)日：1992-03-31
申请号：JP21214290
申请日：1990-08-10
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： WATABE NOBUO , KAWAMURA AKIRA , MASUOKA RYUSUKE , OOWADA YURI , ASAKAWA KAZUO , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06G7/60 , G06F15/18 , G06N3/08 , G06N99/00
摘要： PURPOSE:To learn a network that treats a combined weight as processing data by arranging a neuro circuit which has a weighting function and does not have a threshold in the front stage of a neuro unit from which a weight value is to be detected. CONSTITUTION:For outputting the combined weight value between the neuro units 5 and 6, the neuro unit 7 is arranged for outputting the weight value between the neuro units 5 and 6 and the weight value for a signal from the neuro unit in the neuro unit 6 is fixed to '1' at the time of learning. At the time of learning, the neuro unit 7 weights data from the neuro unit 5. A division part 8 composed of the neuro units is connected and the output of the neuro unit 7 is divided by the output of the neuro unit 5. Thus, combined weight can be outputted and the overall learning becomes possible.

4. 发明专利

JPH0464183A WEIGHTED MAJORITY DECISION DEVICE BY NEURAL NETWORK AND ITS MANUFACTURE 失效
公开(公告)号：JPH0464183A
公开(公告)日：1992-02-28
申请号：JP17569490
申请日：1990-07-03
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： WATABE NOBUO , KAWAMURA AKIRA , MASUOKA RYUSUKE , ASAKAWA KAZUO , OOWADA ARIMICHI , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06G7/60 , G06F15/18 , G06N3/00 , G06N99/00
摘要： PURPOSE:To perform weighted majority decision by performing relation between input variables i.e. weighing by performing learning by using a neural network. CONSTITUTION:Signals on which weight W1-Wn are multiplied, respectively are outputted from neuro units 7-1 to 7-n in an intermediate layer. Input signals X1-Xn to the neuro units 6-1 to 6-n of an input part are inputted to the intermediate layer and division parts 1-n, 5 as it is, and X1W1-XnWn are outputted from the neuro units 7-1 to 7-n in the intermediate layer, and are inputted to the division parts 1-n and 5, and weighted mean i.e. a weighted majority decision arithmetic operation is performed. The weighing can be performed by performing the learning by plural input X1-Xn and a teacher signal D for them. In such a way, it is possible to realize the weighted majority decision by the neural network.

5. 发明专利

JPH0464136A LEARNING METHOD FOR NEURAL UNIT WITH FULLY COUPLED RULE PART 失效
公开(公告)号：JPH0464136A
公开(公告)日：1992-02-28
申请号：JP17461090
申请日：1990-07-03
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： KAWAMURA AKIRA , ASAKAWA KAZUO , WATABE NOBUO , MASUOKA RYUSUKE , OOWADA ARIMICHI , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06G7/60 , G06F9/44 , G06F15/18 , G06N3/00 , G06N99/00
摘要： PURPOSE:To improve the efficiency of learning by learning an entire network using a system learning data after initializing a weight value and a threshold value at each of an antecedent part membership function realizing part, rule part, and consequent part membership function realizing part. CONSTITUTION:The weight value and the threshold value are initialized at each of an antecedent part membership function realizing part 10, rule part 12, and consequent part membership function realizing part 14. That is, the initial value prepared based on knowledge stored preliminarily or by using random numbers is set. Then, the entire antecedent part membership function realizing part 10, rule part 12, and consequent part membership function realizing part 14 are learned after learning the weight of the rule part 12 using the learning data prepared preliminarily. Thus, the learning to operate a control suited to an object system can be realized efficiently.

6. 发明专利

JPH0424740A LEARNING METHOD FOR PREWIRED NEURO OF RULE PART 失效
公开(公告)号：JPH0424740A
公开(公告)日：1992-01-28
申请号：JP12470490
申请日：1990-05-15
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： KAWAMURA AKIRA , ASAKAWA KAZUO , WATABE NOBUO , MASUOKA RYUSUKE , OOWADA YURI , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06G7/60 , G05B13/02 , G06F9/44 , G06F15/18 , G06N3/00 , G06N3/08 , G06N99/00
摘要： PURPOSE:To efficiently learn to adjust the weight of a rule part and that of the antecedent implementing part of a membership function by learning the weight of the rule part and subsequently the weight of the antecedent implementing part of the membership function after initializing a weight value for the rule part, the antecedent implementing part of the membership function and the consequent implementing part of a membership function. CONSTITUTION:An initial weight value to which preliminarily stored knowledge is introduced is set for each of an antecedent implementing part 10 of the membership function, a rule part 12 and a consequent implementing part 14 of the membership function. Then, the weight of the rule part 12 is learned by using a learning data and after that, the weight of the antecedent part 10 is learned. The weight value can be initialized for the rule part 12 by using a random number or by using both the preliminarily stored knowledge and the random number. Thus, it is possible to efficiently learn to adjust the weight of the rule part and that of the antecedent implementing part of the membership function.

7. 发明专利

JPH0424738A LEARNING METHOD FOR PREWIRED NEURO OF RULE PART 失效
公开(公告)号：JPH0424738A
公开(公告)日：1992-01-28
申请号：JP12470290
申请日：1990-05-15
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： KAWAMURA AKIRA , ASAKAWA KAZUO , WATABE NOBUO , MASUOKA RYUSUKE , OOWADA YURI , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06G7/60 , G05B13/02 , G06F9/44 , G06F15/18 , G06N3/00 , G06N3/08 , G06N99/00
摘要： PURPOSE:To efficiently adjust the weight of the antecedent implementing part of a membership function by learning only the antecedent implementing part of the membership function after initializing a weight value for the antecedent implementing part of the membership function, a rule part and the consequent implementing part of the membership function. CONSTITUTION:An initial weight value is set for each of an antecedent implementing part 10 of the membership function, a rule part 12 and a consequent implementing part 14 of the membership function either by introducing a preliminarily stored knowledge or by using a random number, or by using both of them. Then, only the antecedent part 10 is learned by using a preliminarily prepared system learning data. Thus, it is possible to efficiently adjust the weight of the antecedent implementing part of the membership function and to improve the efficiency of learning.

8. 发明专利

JPH0424736A LEARNING METHOD FOR PREWIRED NEURO OF RULE PART 失效
公开(公告)号：JPH0424736A
公开(公告)日：1992-01-28
申请号：JP12470790
申请日：1990-05-15
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： KAWAMURA AKIRA , ASAKAWA KAZUO , WATABE NOBUO , MASUOKA RYUSUKE , OOWADA YURI , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06G7/60 , G05B13/02 , G06F9/44 , G06F15/18 , G06N3/00 , G06N3/08 , G06N99/00
摘要： PURPOSE:To adjust the optimal weight of the consequent implementing part of a membership function by learning the weight of the consequent implementing part of the membership function after learning the weight of either the antecedent implementing part of a membership function or a rule part, or the weight of both of them. CONSTITUTION:An initial weight value to which preliminarily stored knowledge is introduced is set for each of an antecedent implementing part 10 of the membership function, a rule part 12 and a consequent implementing part 14 of the membership function. Then, the weight of either the antecedent part 10 or the rule part 12, or the weight of both of them is learned and finally the weight of the consequent part 14 is learned. The weight value can be initialized for the antecedent part 10 and the rule part 12 by using a random number or by using both the preliminarily stored knowledge and the random number. Thus, it is possible to adjust the optimal weight of the consequent implementing part of the membership function and to learn efficiently the control which is suitable to an objective system.

9. 发明专利

JPH0421060A SEQUENTIAL LEARNING SYSTEM FOR GROUP UNIT OF COUPLING IN NEURAL NETWORK 失效
公开(公告)号：JPH0421060A
公开(公告)日：1992-01-24
申请号：JP12290390
申请日：1990-05-15
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： WATABE NOBUO , KAWAMURA AKIRA , MASUOKA RYUSUKE , OOWADA YURI , ASAKAWA KAZUO , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06G7/60 , G06F15/18 , G06N3/08 , G06N99/00 , G11C11/54
摘要： PURPOSE:To prevent the breakdown of knowledge reflected at the time of setting an initial value of weight by converting a neural network of complete coupling to a network having a certain special structures by setting a group of coupling as a unit, adjusting the degree of learning at every coupling group and determining the sequence of leading. CONSTITUTION:A neural network learning means 4 sets a learning adjustment constant outputted by a learning adjustment constant output means 3 to all couplings in a neural network, and controls learning of the neural network. In accordance with the storage contents of a learning coupling group storage means 5, that is, the designation of a coupling group learned in each learning phase, a learning phase control means 6 allows the learning adjustment constant output means 3 to output, for instance, '1', and '0' to an in-group coupling or an inter-group coupling learned in each learning phase, and to all the coupling except the above coupling, respectively, and also, controls learning of each learning phase. In such a way, it can be prevented that knowledge reflected at the time of setting an initial value of weight is broken down.

10. 发明专利

JPH03271809A FUZZY CONTROLLER 失效
公开(公告)号：JPH03271809A
公开(公告)日：1991-12-03
申请号：JP7116990
申请日：1990-03-20
申请人： FUJITSU LTD , FUJI FACOM CORP
发明人： OOWADA ARIMICHI , WATABE NOBUO , KAWAMURA AKIRA , MASUOKA RYUSUKE , ASAKAWA KAZUO , MATSUOKA SHIGENORI , OKADA HIROYUKI
IPC分类号： G06F15/18 , G05B13/02 , G06F9/44 , G06N3/00 , G06N7/02 , G06N99/00
摘要： PURPOSE:To easily change an arithmetic function to an OR operation used from conventionally, while realizing an arithmetic function of an algebraic sum as a consequent part operation by constituting a consequent part arithmetic means of a hierarchical network structure part to which a value by which an algebraic sum value of an input signal value is outputted as an internal state value of an internal coupling from an output layer is set. CONSTITUTION:A hierarchical network structure part 20 operates to calculate an algebraic sum value of an input signal value inputted to an input layer and to output it to an inference value calculating part 19 in accordance with a data converting function prescribed by a hierarchical network structure which said part has by itself and an internal state value allocated to an internal coupling of its hierarchical network structure. In such a way, when an application value of each fuzzy control rule to the same consequent part membership function is inputted as an input signal from an antecedent part arithmetic part 17, a consequent part arithmetic part 18 calculates an algebraic sum value of its input signal value which is inputted and processes it to determine as an application value to its consequent part membership function. Accordingly, the arithmetic contents can be changed freely.

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