Open AccessData-Driven Sensor Fault Diagnosis for Fighter under Harsh Conditions
Author(s) -
Qi Wang,
Fuyang Chen,
Li Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1631/1/012176
Subject(s) - principal component analysis , support vector machine , classifier (uml) , computer science , pattern recognition (psychology) , fault (geology) , wavelet packet decomposition , grasp , artificial intelligence , wavelet transform , real time computing , data mining , algorithm , wavelet , seismology , programming language , geology
This paper presents a multi-classification fault diagnosis scheme for the sensor of fighter. It is difficult to diagnose sensor faults for fighter under harsh conditions like hyper maneuver because the states change rapidly and the data of fault-free and faulty sensor are similar to each other. The rapidly changing states means that values of sensor faults may be small compared with states variation. Similar data may raise the difficulty to find the separating plane. Wavelet packet decomposition can transform the raw dataset to fault features by computing the energy values of each frequency band. And principal component analysis (PCA) can grasp the main features and reduce computational complexity by transform a group of dependent parameters into a group of independent parameters via orthogonal transformation. A support vector machine (SVM) trains fault features to achieve a multi-classifier via one-versus-rest method. The classifier can obtain fault diagnosis results by inputting features of new data. Numerical simulation results illustrate the effectiveness and accuracy of the proposed fault diagnosis scheme.