For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
Radio Frequency (RF) analog circuit faults often occur in broadband, high voltage and high temperature environment, so the detection of faults location and prediction of faults occurring time are important research subject.As GMM-HMM (Gaussian Mixture-Hidden Markov Model) algorithm has strong capability for sequential data processing, it is proposed in this paper a fault diagnosis method based on GMM-HMM and has been successfully applied to the fault diagnosis of low noise amplifier circuit based on ATF54143 transistor. Through multiple testing datasets, the experimental results have verified the feasibility of proposed method, the fault model has 100% accuracy for open circuit and short circuit fault diagnosis of the radio frequency circuit.
Inspec keywords: radiofrequency amplifiers; Gaussian processes; low noise amplifiers; wideband amplifiers; mixture models; fault location; hidden Markov models; fault diagnosis; transistor circuits
Subjects: Markov processes; Amplifiers