Open AccessA Method for Fault Diagnosis Based on Multidimensional Scaling (MDS) in Analog Circuits
Author(s) -
Bing Luo,
Jiebing Cui,
Kaifang He,
Qian Liu,
Yigang He
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/631/4/042037
Subject(s) - fault (geology) , stuck at fault , nonlinear system , analogue electronics , scaling , computer science , variable (mathematics) , basis (linear algebra) , state (computer science) , electronic circuit , algorithm , electronic engineering , control theory (sociology) , fault detection and isolation , mathematics , engineering , artificial intelligence , electrical engineering , geology , mathematical analysis , physics , geometry , quantum mechanics , control (management) , seismology , actuator
Considering different fault state of the circuit in the nonlinear analog circuit fault diagnosis, the output response of the circuit varies. A Method for Fault Diagnosis of Nonlinear Analog Circuits on the basis of Multidimensional Scaling (MDS) was put forward according to the variable output response. This method can transform the difference of output response under different fault states into a low-dimensional fitting composition and then distinguish the different fault types. Under the condition of single fault of the circuit, the simulation result proves that the method presented in this paper enjoys high accuracy in effectively classifying the different fault types, locating the faulty components and observing the difference among variable faults intuitively in the low-dimensional coordinate system.