Apparatus for detecting vibrations of a test object using a competitive learning neural network in determining frequency characteristics generated
First Claim
1. A nondestructive inspection apparatus comprising:
- a sensor unit for detecting vibrations transmitted through a test object from a vibration generator;
a signal input unit for extracting a target signal from an electric signal outputted from the sensor unit;
an amount of characteristics extracting unit for extracting multiple frequency components from the target signal as an amount of characteristics; and
a decision unit having a competitive learning neural network for determining whether the amount of the characteristics belongs to a category, wherein the competitive learning neural network has been trained by using training samples belonging to the category representing an internal state of the test object,wherein distributions of membership degrees of the training samples are set in the decision unit, the distributions being set with respect to neurons excited by the training samples based on samples and weight vectors of the excited neurons, andwherein the decision unit determines that the amount of characteristics belongs to the category, if one of the excited neurons is excited by the amount of characteristics and the distance between the amount of characteristics and a weight vector each of one or more of the excited neurons, corresponds to a membership degree equal to or higher than a threshold determined by the distributions.
3 Assignments
0 Petitions
Accused Products
Abstract
A nondestructive inspection apparatus includes a sensor unit for detecting vibrations transmitted through a test object from a vibration generator and a signal input unit for extracting a target signal from an electric signal outputted from the sensor unit. An amount of characteristics extracting unit is also included for extracting multiple frequency components from the test signal as an amount of characteristics. Further, a decision unit has a competitive learning neural network for determining whether the amount of the characteristics belongs to a category, wherein the competitive learning neural network has been trained by using training samples belong to the category representing an internal state of the test object, wherein distributions of membership degrees of the training samples are set in the decision unit.
21 Citations
4 Claims
-
1. A nondestructive inspection apparatus comprising:
-
a sensor unit for detecting vibrations transmitted through a test object from a vibration generator; a signal input unit for extracting a target signal from an electric signal outputted from the sensor unit; an amount of characteristics extracting unit for extracting multiple frequency components from the target signal as an amount of characteristics; and a decision unit having a competitive learning neural network for determining whether the amount of the characteristics belongs to a category, wherein the competitive learning neural network has been trained by using training samples belonging to the category representing an internal state of the test object, wherein distributions of membership degrees of the training samples are set in the decision unit, the distributions being set with respect to neurons excited by the training samples based on samples and weight vectors of the excited neurons, and wherein the decision unit determines that the amount of characteristics belongs to the category, if one of the excited neurons is excited by the amount of characteristics and the distance between the amount of characteristics and a weight vector each of one or more of the excited neurons, corresponds to a membership degree equal to or higher than a threshold determined by the distributions. - View Dependent Claims (2, 3, 4)
-
Specification