A Combined Method for Analog Circuit Fault Diagnosis Based on Dependence Matrices and Intelligent Classifiers

Shi, Junyou; Deng, Yi; Wang, Zili; He, Qingjie

doi:10.1109/tim.2019.2905307

Cited by 24 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because that the parameter value of analog element is continuous real number, the faulty parameter p could be any positive real number, p∈ ℝ . Hence, some specific soft faults [4,5], such as ±50% parameter shifting [4], are considered. Although these methods can diagnose some specific soft faults, the continuous character of analog parameter still not be handled.…”

Section: A Fault Locationmentioning

confidence: 99%

Genetic Algorithm Based Faulty Parameter Identification for Linear Analog Circuit

Yang

2020

IEEE Access

View full text Add to dashboard Cite

Faulty parameter identification is vital to prediction of remaining useful life of circuit under test (CUT). Based on the transfer function of the CUT, we use measured faulty response to reversely deduce the possible faulty parameters. It is known that the response is the function of the analog parameters. Usually, the number of independent response is much fewer than that of the analog component. The underdetermined equations have infinite solutions. In other words, there are lots of combinations of analog parameters that can generate the same faulty response. Hence, it is more valuable to deduce the possible fault parameter range within which all faults can generate the same measured response. The deduction is accomplished by using genetic algorithm. The length of chromosome equals to the number of analog component. Each gene represents a component's parameter value. Based on the gene values and the transfer function, each individual has a simulated response. Our target is to find all possible individuals viz., parameter combinations, which minimize the difference between the simulated and measured faulty response. In the final solutions, it is easy to find the minimal and maximum fault parameters, viz., extreme points. The possible faulty parameter rage is determined by these two extreme points because that the transfer function and parameters of analog element are continuous. The effectiveness of the proposed method is examined by using filter circuit examples.

show abstract

Section: A Fault Locationmentioning

confidence: 99%

Genetic Algorithm Based Faulty Parameter Identification for Linear Analog Circuit

Yang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Two well-known metrics in PHM studies, i.e., scoring function and root mean squared error (RMSE), formulated by (10) and (11), respectively, are used in this study to evaluate the performance of the proposed method. (10) where N is the total number of the samples, and (11) where g and gi denote the sum of the score and the score of the i th sample.…”

Section: B Health State Estimation 1) Assessment Metricsmentioning

confidence: 99%

“…Broadly, PHM includes fault diagnosis and prognostics. Analog circuit fault diagnosis pinpoints the faulty components and, sometimes, provides correction solutions [10][11][12]. In comparison, circuit fault prognosis estimates the circuit performance in the future and possible failures.…”

Section: Introductionmentioning

confidence: 99%

Circuit Health State Estimation via An Integrated Deep Neural Network

2020

International Journal of Circuits, Systems and Signal Processing

View full text Add to dashboard Cite

accelerating the industry to become more integrated and intricated. It is almost inevitable for a system to encounter failures during its whole life span. Thus, it is imperative to monitor the operating system from a system-level perspective to avoid potential catastrophes. Intuitively, inclusive prior knowledge is required for prognostics and health management (PHM). However, due to time-varying parameters and external conditions, the system is usually too complex to neatly fit into a prior-built model. This paper presents a novel pragmatic method, encompassing the convolutional autoencoder (CAE) and long short-term memory recurrent neural network (LSTM-RNN), to track the health state of a circuit. Briefly, the proposed method can be divided into two steps. First, degradation characteristics are extracted by using the time-domain features and CAE to prepare for the later health state estimation step. Then, the LSTM-RNN is used to finish the predictive process, i.e., to map the extracted abstract features to the health state. In addition, the degradation of a practical circuit considering the angular distance is discussed to quantify the health state of the circuit system. Furthermore, a case study based on that prognostics scheme is conducted to verify the proposed method. The comparison with other existing popular methods indicates the superiority of the proposed methodology.

show abstract

“…Analog circuit fault diagnosis problem is considered to be a classification problem, and researchers are actively exploring ways to develop many effective fault diagnosis methods for analog circuits. For example, experts applied the intelligence technology including expert system methods, fuzzy theory, artificial neural network, and support vector machines to build the multiclassification models to diagnose the analog faults [ 6 , 7 , 8 ]. Song et al used the RMS specification to measure the sensitivity of the output response of the circuit under test obtained by multiresolution analysis and used the neural network as a classifier for fault diagnosis [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

A Fault Diagnosis Method of Modular Analog Circuit Based on SVDD and D–S Evidence Theory

Sun

Yang

Jiang

et al. 2021

Sensors

View full text Add to dashboard Cite

In the actual fault diagnosis process of an analog circuit, there is often a problem due to the lack of fault samples, leading to the low-accuracy of diagnostic models. Therefore, using positive samples that are easy to obtain to establish diagnostic models became a research hotspot in the field of analog circuit fault diagnosis. This paper proposes a method based on Support Vector Data Description (SVDD) and Dempster–Shafer evidence theory (D–S evidence theory) for fault diagnosis of modular analog circuit. Firstly, the principle of circuit module partition is proposed to divide the analog circuit under test, and the output port of each module is selected as test point. Secondly, the paper extracts the feature of the time-domain and frequency-domain output signals of the circuit module through Principal Component Analysis (PCA). Thirdly, four state detection models based on SVDD are established to judge the working state of each circuit module, including TSG, TSP, FSG, and FSP state detection model. Finally, the D–S theory is introduced to integrate the test results of each model for locating fault circuit module. To verify the effectiveness of the proposed method, the dual bandpass filter circuit is selected for simulation and hardware experiment. The results show that the proposed method can locate the analog fault effectively and has a higher diagnosis accuracy.

show abstract

A Combined Method for Analog Circuit Fault Diagnosis Based on Dependence Matrices and Intelligent Classifiers

Cited by 24 publications

References 40 publications

Genetic Algorithm Based Faulty Parameter Identification for Linear Analog Circuit

Genetic Algorithm Based Faulty Parameter Identification for Linear Analog Circuit

Circuit Health State Estimation via An Integrated Deep Neural Network

A Fault Diagnosis Method of Modular Analog Circuit Based on SVDD and D–S Evidence Theory

Contact Info

Product

Resources

About