Patent US2952871A successfully refreshed from Google Patents.
Patent EP0568017A2 successfully refreshed from Google Patents.
EP0568017A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
A method for predicting impact by using neural networks
Assignee: Takata Corp
•
Filing: 1993-04-27
•
Granted: —
•
Expires: 2013-04-27
Abstract
Abstract A method for predicting impact by using neural networks comprising steps of supplying a predetermined crash curve to a first neural network having an intermediate layer to train said first neural network by means of learning calculation and supplying a predetermined air bag deployment limit curve to a second neural network to train said second neural network, supplying data indicative of crash curve obtained by an acceleration sensing device on collision to said first and second neural networks, predicting in said first neural network a time instance at which a threshold displacement is going to reach based on the basis of the training result in said first neural network, comparing in said second neural network data indicative of crash curve on said collision and said air bag deployment limit curve to produce a decision signal of deploying the air bag according to the comparison result, calculating AND of said decision signal and said time instance in accordance with said AND, to deploy the air bag depending on the impact, and supplying an operation command signal to the air bag deployment operation means.
Inventors
- 👤 Tomoyuki Nishio
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-25 07:55
CPC Classifications
B; B60; B60R; B60R21/00; B60R21/01; B60R21/013; B60R21/0132; B60R21/01332; G; G06; G06N; G06N3/00; G06N3/02; G06N3/04; G06N3/045; G06N3/0499; G06N3/08; G06N3/082; G06N3/09; B60R2021/01204; B60R2021/01211
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
253 words
A method for predicting impact by using neural networks comprising steps of: supplying a predetermined crash curve as a first group of parallel training data to a first neural network having an intermediate layer to train said first neural network by means of learning calculation and supplying a predetermined air bag deployment limit curve as a second group of training data to a second neural network to train said second neural network; supplying data indicative of crash curve obtained by an acceleration sensing device on collision as a set of data having a predetermined time interval to said first and second neural networks; predicting in said first neural network a time instance at which a threshold displacement is going to reach in accordance with a prediction displacement output obtained on the basis of the training result in said first neural network; comparing in said second neural network data indicative of crash curve on said collision and said air bag deployment limit curve in accordance with the training result in said second neural network to produce a decision signal indicative of the pros and cons of deploying the air bag according to the comparison result; calculating AND of said decision signal and said time instance at which the threshold is going to reach to determine, in accordance with said AND, the pros and cons of operation to deploy the air bag depending on the impact; and supplying an air bag deployment operation command signal depending on said determination to air bag deployment operation means.
Claim 2
Dependent Claim
48 words
A method for predicting impact by using neural networks as claimed in Claim 1, wherein each of said first and said second neural networks comprises a two dimensional self-organizing competitive learning layer in said intermediate layer to perform learning operation in said two dimensional self-organizing competitive learning layer.
Claim 3
Dependent Claim
28 words
A method for predicting impact by using neural networks as claimed in Claim 1 or 2, wherein said learning calculation is achieved by a back propagation network architecture.
Claim 4
Dependent Claim
48 words
A method for predicting impact by using neural networks as claimed in Claim 1 or 2, wherein said first group of parallel training data is used for learning calculation by means of converting the crash curve obtained by calculation in said first neural network into a displacement data.
Claim 5
Dependent Claim
77 words
A method for predicting impact by using neural networks as claimed in Claim 4, wherein said first group of parallel training data is supplied in parallel to an input layer of said first neural network after parallel converting a subsequent displacement values within a predetermined range, and displacement values following to said subsequent displacement values are parallel converted into a desired output data to be supplied in parallel to an output layer of said first neural network.
Claim 6
Independent Claim
214 words
A system for predicting impact by using neural networks comprising: displacement prediction means where a crash curve data obtained on collision by an acceleration sensing device is supplied to, as a data set having a predetermined time interval, a first neural network having an intermediate layer already trained by means of learning calculation with supplied a predetermined crash curve as a first group of parallel training data, and predicting a time instance at which a threshold value displacement is going to reach in accordance with the training result in said first neural network; air bag deployment decision means where said crash curve data obtained on collision is supplied to a second neural network having an intermediate layer already trained by means of learning calculation with supplied a predetermined air bag deployment limit curve as a second group of training data, and identifying the pros and cons of deploying the air bag to produce a decision signal; and a logic circuit where said time instance at which the threshold value is going to reach and said decision signal are supplied to determine the pros and cons of operation to deploy the air bag in accordance with the predicted impact and to produce an air bag deployment operational command signal to air bag deployment operation means.
Claim 7
Dependent Claim
48 words
A system for predicting impact by using neural networks as claimed in Claim 6, wherein each of said first and said second neural networks comprises a two dimensional self-organizing competitive learning layer in said intermediate layer to perform learning operation in said two dimensional self-organizing competitive learning layer.
Claim 8
Dependent Claim
28 words
A system for predicting impact by using neural networks as claimed in Claim 6 or 7, wherein said learning calculation is achieved by a back propagation network architecture.
Claim 9
Dependent Claim
48 words
A system for predicting impact by using neural networks as claimed in Claim 6 or 7, wherein said first group of parallel training data is used for learning calculation by means of converting the crash curve obtained by calculation in said first neural network into a displacement data.
Claim 10
Dependent Claim
77 words
A system for predicting impact by using neural networks as claimed in Claim 9, wherein said first group of parallel training data is supplied in parallel to an input layer of said first neural network after parallel converting a subsequent displacement values within a predetermined range, and displacement values following to said subsequent displacement values are parallel converted into a desired output data to be supplied in parallel to an output layer of said first neural network.
Claim 11
Independent Claim
46 words
A system for predicting impact by using neural networks as claimed in an one of Claims 6 through 10 wherein said first and said second neural networks are coded after completion of learning to be implemented in a substrate of an air bag operation control circuit.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.