Validation of Sensors has very important effects on the consequences of structural experiments and subsequent analyzing works. This article focus on the problem that if the data collected from the sensors are valid or not. It tested the validation of an specified acceleration sensor on a truss structure by using Naive Bayesian Classifier (NBC) based on one kind of machine learning technology whose theory basis is probability statistics. In the course of data analyzing, the theoretical values modified by Finite Element Modeling are taken as an criterion of testing collected data from sensors. The continuous type of data are discretized by several different discretization methods. The classifier is created by discretized training data and used to test the validation of the specified sensor. It is proved that the testing method is effective.
[1]
Sunil Vadera,et al.
Any Time Probabilistic Reasoning for Sensor Validation
,
1998,
UAI.
[2]
Pedro M. Domingos,et al.
On the Optimality of the Simple Bayesian Classifier under Zero-One Loss
,
1997,
Machine Learning.
[3]
Sunil Vadera,et al.
Real Time Intelligent Sensor Validation
,
2001
.
[4]
Zhu Jun,et al.
Recent Advances in Bayesian Machine Learning
,
2015
.
[5]
Ole J. Mengshoel,et al.
Sensor Validation using Bayesian Networks
,
2008
.
[6]
Zheng Liu,et al.
Validation of Strain Gauges for Structural Health Monitoring With Bayesian Belief Networks
,
2013,
IEEE Sensors Journal.