Fault dictionary based switched current circuit fault diagnosis using entropy as a preprocessor

Abstract

A novel method based on a fault dictionary that uses entropy as a preprocessor to diagnose faulty behavior in switched current (SI) circuit is presented in the paper. The proposed method uses a data acquisition board to extract the original signal form the output terminals of the circuit-under-tests. These original data are fed to the preprocessors for feature extraction and finds out the entropies of the signals which are a quantitative measure of the information contained in the signals. The proposed method has the capability to detect and identify faulty transistors in SI circuit by analyzing its output signals with high accuracy. Using entropy of signals to preprocess the circuit response drastically reduces the size of fault dictionary, minimizing fault detect time and simplifying fault dictionary architecture. The result from our examples showed that entropies of the signals fall on different range when the faulty transistors ' Transconductance G m value varying within their tolerances of 5 or 10%, thus we can identify the faulty transistors correctly when the response do not overlap. The average accuracy of fault recognition achieved is more than 95% although there are some overlapping data when tolerance is considered. The method can classify not only parametric faults but also catastrophic faults. It is applicable to analog circuits as well as SI ones. A low-pass and a band-pass SI filter and a Clock feedthrough cancellation circuit have been used as test beached to verify the effectiveness of the proposed method. A comparison of our work with Yuan et al. (IEEE Trans Instrum Meas 59(3):586-595, 2010), which used entropy and kurtosis as preprocessors, reveals that our method requiring one feature parameter reduces the computation and fault diagnosis time.

A new swarm-SVM-based fault diagnosis approach for switched current circuit by using kurtosis and entropy as a preprocessor

“…Going through all the rows of this table shows that our system only misclassifies the test data associated with the Mg;fault classes. The method in [12] cannot distinguish two groups including Mg; and Mj:, Mg: and Mj; for the sixth-order Chebyshev low-pass filter, and has 95 % correct classification for the filter. Obviously, the method proposed in this paper has successfully classified the two ambiguity groups except Mg: and a higher correct fault recognition rate.…”

“…A novel method based on a fault dictionary that uses entropy as a unique parameter to diagnose faulty behavior in SI circuit is presented in Ref. [12], but fault classes are indistinguishable when the ambiguity groups of entropy are overlapped.…”

Diagnóstico de falhas em máquinas rotativas utilizando Random Forest

“…A entropia H pode ser definida como uma medida capaz de aferir quão imprevisívelé uma variável aleatória [4], [8]. Esta medida pode ser calculada através da equação abaixo:…”

“…Há casos em que o procedimento da inspeção visual das características dos sinais de vibração no domínio da frequênciá e suficiente para identificar falhas. No entantoé necessário que este processo de realização de diagnóstico seja feito de maneira rápida e automática, por isso utilizam-se os algoritmos de classificação, dentre eles destacam-se para o reconhecimento de padrões com múltiplas classes o Random Forest e as Redes Neurais Artificiais [2], [4], [3].…”

A Novel Fault Diagnostic Method Based on Node-Voltage Vector Ambiguity Sets

“…These technologies were reviewed in [5] and [6]. References [7]- [10] have added several new methods, which have been applied successfully to numerous projects [11]. The concept of fault ambiguity sets is widely used in engineering, particularly in test node optimization, because it can easily program auto-test systems [3]- [5], [13].…”