Analog Circuit Fault Diagnosis under Parameter Variations Based on Type-2 Fuzzy Logic Systems

In order to handle noisy measurement data, an interval type-2 fuzzy logic system (T2FLS) is proposed. In this paper, the evolution of soft fault diagnosis for analog circuits is explored based on a type-2 fuzzy logic system (T2FLS) which can handle measurement uncertainties. In order to evaluate the values of the faulty components accurately, a type-2 fuzzy rule base is adopted to describe the behavior of the circuit under test (CUT) both in fault and fault-free circumstances and to estimate the faulty element values when the measurement data are corrupted by white Gaussian noise. From the experimental results, we can find that the advocated interval type-2 fuzzy logic system has succeeded in evaluating crisp values of the faulty elements and the performance is better than that of previous work. Furthermore, to validate the capability of the proposed approach, the T2FLS is applied to extract the component values of the integrated circuit electromagnetic (ICEM) modeling.