Fault diagnosis in LED illuminating circuits based on cloud model

For gaining effective features to realize fault diagnosis in the LED illuminating circuits, a method of fault diagnosis in analog circuits based on cloud model is proposed. In this paper, the analog circuit with a sinusoidal input is simulated and its output is sampled to extract sequences of each layer of wavelet coefficients as the initial fault feature vectors. Then, the backward cloud algorithm of cloud model is applied to obtain corresponding digital features of the wavelet coefficients, which include the Expected value Ex, the Entropy En and the Hyper entropy He as new fault feature vectors, named fault cloud feature vectors. Finally, Fault cloud feature vectors are used to BP neural networks to classify fault and realize the fault diagnosis in analog circuits. The simulation result on the LED illuminating circuits shows that this method is feasible and has many powerful virtues, such as diagnosing and locating faults quickly and exactly.