This article proposed a practical approach to isolating faults in analog circuits. The contribution of this article is twofold. First, the optimized empirical mode decomposition approach is presented based on the Hellinger distance such that there is a minimum dependency between intrinsic mode functions. Features with high distinction could be extracted by employing intrinsic mode functions in fault detection problem of analog benchmark circuits. Second, the non-dominated sorting genetic algorithm is employed to retain excellent features and speed up the execution, resulting in the high accuracy of fault detection and isolation. The number of features and mean squared error are selected as objective functions. The features from the data are also extracted using the fast Fourier and wavelet transforms for comparison. Finally, the support vector machine and artificial neural network are employed to isolate faults. Two circuits under test are simulated, and the output signals of the faulty and fault-free circuits are extracted by the Monte Carlo analysis. According to the obtained simulation results, the proposed method with a low-dimensional feature vector outperformed the previous methods, and the computational time has also reduced significantly.
VenkatasubramanianVRengaswamyVRYinK, et al. A review of process fault detection and diagnosis part I: quantitative model-based methods. Comput Chem Eng2003; 27: 293–311.
3.
VenkatasubramanianVRengaswamyVRYinK, et al. A review of process fault detection and diagnosis part II: qualitative models and search strategies. Comput Chem Eng2003; 27: 313–326.
4.
KargarSMSalahshoorKYazdanpanahMJ. Multiple model-based fault detection and diagnosis for nonlinear model predictive fault-tolerant control. Arab J Sci Eng2014; 39(10): 7433–7442.
5.
AngZHQinWAnouX, et al. Application of FBOLE a prototype expert system for fault diagnosis in nuclear power plants. Reliab Eng Sys Safety1994; 44(3): 225–235.
6.
KeehoonKBartlettE. Nuclear power plant fault diagnosis using neural networks with error estimation by series association. IEEE T Nucl Sci1996; 43(4): 2373–2388.
7.
ChristianF. Fly by wire for commercial aircraft: the Airbus experience. Int J Control1994; 59(1): 139–157.
8.
RiereBFominiqueDTraverseP. Airbus A320/A330/A340 electrical flight controls a family of fault tolerant systems. In: FTCS-23rd the twenty-third international symposium on fault-tolerant computing, vol. 60, Toulouse, 22–24 June 1993, pp.616–623. New York: IEEE.
WangHNaseokIKimS, et al. A survey of fault detection, isolation, and reconfiguration methods. IEEE T Contr Syst T2010; 18(3): 636–653.
11.
RongbinGZhangSGaoP, et al. Applicability study on fault diagnostic methods for analog electronic systems. Eng Asset Manag Syst2015; 22(5): 1233–1246.
12.
IsermannR. Supervision, fault detection and fault diagnosis methods a short introduction. Combust Eng Diag2017; 23(8): 25–47.
13.
EntonFGaynWMcGinnityTM, et al. Fault diagnosis of electronic system using intelligent techniques: a review. IEEE T Syst Man Cy C2001; 31(3): 261–289.
14.
RayZ. Principle and method of analog circuit fault diagnosis, vol. 15, no. 4. Wuhan, China: Huazhong University of Science Press, 1989, pp.575–580.
15.
LiuCHEnbaoZHLiuT, et al. Signal model based fault coding for diagnostics and prognostics of analog electronic circuits. IEEE T Ind Electron2017; 64(1): 605–614.
16.
MahoaungNIngfengQHeeY, et al. A new decision tree approach of support vector machine for analog circuit fault diagnosis. Analog Integr Circ S2016; 88: 455–463.
17.
XiaoZYingqunSHFengL. A novel neural network approach of analog fault diagnosis based on kernel discriminant analysis and particle swarm optimization. Appl Soft Comput2012; 12(2): 904–920.
18.
ChenCHDongleiRWangY, et al. A novel approach for analog fault diagnosis based on LMD decomposition and reconstruction. In: Prognostics and system health management conference (PHM-Chengdu), vol. 12, Chengdu, China, 19–21 October 2016, pp.1–5. New York: IEEE.
19.
FanniVLessandraAGiuaA, et al. A neural network diagnosis approach for analog circuits. Appl Intell1999; 17(2): 169–186.
20.
ZhangWChaolongKHeeY, et al. A novel approach for diagnosis of analog circuit fault by using GMKL-SVM and PSO. J Electron Test2016; 32(5): 531–540.
21.
XiongZHJianGTianSH, et al. A novel method of failure sample selection for electrical systems using Ant Colony Optimization (ACO). Comput Intel Neurosc2016; 3(3): 731–740.
22.
WangTPengIYangSH. A new diagnosis approach for handling tolerance in analog and mixed signal circuits by using fuzzy math. IEEE T Circuits: I2005; 52(10): 2118–2127.
23.
HouviBZewenMXiaoM, et al. Mahalanobis distance based approach for anomaly detection of analog filters using frequency features and Parzen window density estimation. J Electron Test2016; 32(6): 681–693.
24.
DorjYEnkhjargalAChenCH, et al. A Bayesian hidden Markov model based approach for anomaly detection in electronic systems. In: Aerospace conference, vol. 32, Big Sky, MT, 2–9 March 2013, pp.1–10. New York: IEEE.
25.
TadeusiewiczMHałgasS. A method for multiple soft fault diagnosis of linear analog circuits. Measurement2019; 131: 714–722.
26.
NiuYFeiJLiY, et al. A novel fault diagnosis method based on EMD, cyclostationary, SK and TPTSR. J Mech Sci Technol2020; 34(5): 1925–1935.
27.
HuangNEShenZLongSR, et al. The empirical mode decomposition and the Hubert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc Lond A Mat1998; 454(1971): 903–995.
SchoubTFriedrichGO’SullivanB (eds). Recent advances in Bhattacharyya criteria. In: Proceeding of the 21st European conference on artificial intelligence, Prague, 18–22 August 2014. Prague: IOS Press.
30.
YektaiiMBhattacharyaP. A criterion for measuring the separability of clusters and its applications to principal component analysis. Signal Image Video P2011; 1: 93–104.
31.
AbbassHASarkerRNewtonC. PDE: a Pareto-frontier differential evolution approach for multi-objective optimization problems. In: Proceedings of the 2001 congress on evolutionary computation, vol. 2, Seoul, South Korea, 27–30 May 2001, pp.971–978. New York: IEEE.
32.
DebK. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE T Evolut Comput2002; 6(2): 182–197.
33.
ShokrolahiSMKazempourATN. A novel approach for fault detection of analog circuit by using improved EEMD. Analog Integr Circ S2019; 98(3): 527–534.
