基于MHMM模拟电路早期故障诊断

MHMM模型是一种基于高斯混合密度的连续隐马尔科夫模型,具有很好的模式识别能力,对于高混叠样本优势明显。模拟电路结构复杂,早期软故障呈现多样化,故障样本混叠严重,难以辨识。针对这个特点,提出了将MHMM模型应用于模拟电路早期故障诊断的新思路。首先,通过线性判别分析(LDA)技术将由仿真电路采集的数据样本进行降维处理,产生低维观测序列,并对样本初步划分;然后,使用高斯混合模型(GMM)对观测序列逼近,并完成MHMM模型的参数训练;最后,通过实例验证,并与BP网络进行比较。结果表明,MHMM对于早期故障的检测更具有优越性。     

Diagnosis of Incipient Faults in Weak Nonlinear Analog Circuits

Aiming at the problem to diagnose incipient faults in weak nonlinear analog circuits, an approach is presented in this paper. The approach calculates the fractional Volterra correlation functions beforehand. The next step is to use the fractional Volterra correlation functions and different angle parameters of the fractional wavelet packet transform (FRWPT) to extract the fault signatures. Meanwhile, the computational complexity is analyzed. Then the variables of the fault signatures are constructed, which are used to form the observation sequences of the hidden Markov model (HMM). HMM is used to accomplish the fault diagnosis. The simulations show that the presented method can significantly improve the incipient fault diagnosis capability.     

Diagnostics of Filtered Analog Circuits with Tolerance Based on LS-SVM Using Frequency Features

Most researchers have used the optimal wavelet coefficients or wavelet energy indicators from the time-domain response of analog circuits to train support vector machines (SVMs) to diagnose faults. In this study, we have proposed two kinds of feature vectors from frequency response data of a filter system to train least squares SVM (LS-SVM) to diagnose faults. The first is defined as the conventional frequency feature vector, which includes the center frequency and the maximum frequency response. The second is a new wavelet feature vector that is composed of the mean and standard deviation of wavelet coefficients. Different feature vectors?? combination and normalization are also discussed in the paper. The results from the simulation data and the real data for two filters showed the following: (1) The proposed method has better diagnostic accuracy than the traditional methods that were based only on the optimal wavelet coefficients or wavelet energy indicators. (2) The diagnostic accuracies using the combined feature vectors were better than those using only the conventional frequency feature vectors or wavelet feature vectors. (3) The best accuracy from using the conventional frequency feature vectors was better than that from using wavelet feature vectors. The proposed method can be extended to diagnostics of other analog circuits that are determined by their frequency characteristics.     

A novel method for fault diagnosis of analog circuits based on WP and GPNN

A novel method for fault diagnosis of analog circuits with tolerance based on wavelet packet (WP) decomposition and probabilistic neural networks using genetic algorithm (GPNN) is proposed in this paper. The fault feature vectors are extracted after feasible domains on the basis of WP decomposition of responses of a circuit being solved. Then by fusing various uncertain factors into probabilistic operations, GPNN methods to diagnose faults are proposed whose parameters and structure obtained form genetic optimisations resulting in best detection of faults. Finally, simulations indicated that GPNN classifiers are correct 7% more than BPNN of the test data associated with our sample circuits.     

Soft Fault Diagnosis in Analog Circuits Based on Bispectral Models

Aiming at the problem to locate soft faults in analog circuits, a new approach based on bispectral models is proposed. First, the Volterra kernels of the circuit under test (CUT) are calculated. Then, the Volterra kernels are used to construct bispectral models. By comparison with the fault features of the constructed models, soft faults of linear and weak nonlinear components in the analog circuit are identified and the faults are located. Simulations and experiments show the effectiveness of the proposed method in analog circuits.,     

Soft Fault Feature Extraction in Nonlinear Analog Circuit Fault Diagnosis

Aiming at the problem to diagnose soft faults in nonlinear analog circuits, a novel approach to extract fault features is proposed. The approach is based on the Wigner–Ville distribution (WVD) of the subband Volterra model. First, the subband Volterra kernels of the circuit under test are cleared. Then, the subband Volterra kernels are used to obtain the WVD functions. The fault features are extracted from the WVD functions and taken as input data into the hidden Markov model (HMM). Finally, with classification of features using HMMs, the soft fault diagnosis of the nonlinear analog circuit is achieved. The simulations and experiments show that the method proposed in this paper can extract the fault features effectively and improve the fault diagnosis.     

Synthesis method for testable electrical networks using 1st order building blocks

This work presents a method for synthesizing testable continuous-time linear time-invariant electrical networks using 1st order blocks for the implementation of analog linear circuits. A functional-structural fault model for the block, and a fault dictionary are proposed together with a simple set of test vectors. The method allows, also, the fault grade evaluation for the modeled faults. The results obtained from the two application examples have shown the suitability of the approach as a design for test method for analog circuits.     

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

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.     

Feature Vector Selection Method Using Mahalanobis Distance for Diagnostics of Analog Circuits Based on LS-SVM

Multi-fault diagnosis for analog circuits based on support vector machine (SVM) usually used a single feature vector to train all binary SVM classifier. In fact, each binary SVM classifier has different classification accuracy for different feature vectors. However, no one has discussed the optimal or near-optimal feature vector selection problem. Based on Mahalanobis distance, a near-optimal feature vector selection method has been proposed for diagnostics of analog circuits using the least squares SVM (LS-SVM). The selection problems of wavelet types, wavelet decomposition level, and normalization methods have been also discussed. Two filters with parametric faults and a nonlinear half-wave rectifier with hard and parametric faults were used as circuits under test (CUTs). The simulation results showed the following: (1) the accuracies using the feature vector with the maximum MD were better than the average accuracies using all the feature vectors, and were better than most accuracies using a single feature vector. But the computation time using the MD method was an order of magnitude larger than that using a single feature vector; (2) Most the diagnostic accuracies using the maximum MD method were near to the optimal accuracies using the exhaustive method while the computation time was reduced about 20–50?% in comparision to the exhaustive method; (3) the Haar wavelet was the best choice among Daubechie’s wavelet family for all CUTs’ diagnosis; (4) only non-normalization, all-normalization, and part-normalization methods are necessary to be considered for feature vector normalization. The proposed method can obtain a near-optimal diagnostic accuracy in a reasonable time, which is beneficial for analog IC or circuits testing and diagnosis.     

基于小波高频系数统计特征的电路故障诊断

对故障电路进行特征提取与分类是模拟电路诊断的两个重要环节。现有方法多对时域响应信号进行小波变换以提取故障特征,并用神经网络或支持向量机方法实现对故障进行分类。为提高模拟电路故障诊断率,提出一种新的特征选取方法:在模拟电路的时域响应中对其进行小波变换,并对变换得到的高频细节系数统计平均值、标准偏差、峭度、熵和偏斜度等统计特征,并建立以支持向量机为分类器的故障诊断系统。以两种常见电路为例,实验结果表明,提出方法对常见电路进行故障诊断,准确率得到提升,精度达到99%以上,优于传统单纯小波系数分析方法,适用于模拟电路的故障诊断。     

Fault detection in analogue circuits using hybrid evolutionary algorithm and neural network

With the development of analog integrated circuits technology and due to the complexity, and various types of faults that occur in analog integrated circuits, fault detection is a new idea, has been studied in recent decades. In this paper a three amplifier state variable filter is used as circuit under test (CUT) and, a hybrid neural network is proposed for soft fault diagnosis of the CUT. Genetic algorithm (GA) has the powerful ability of searching the global optimal solution, and back propagation (BP) algorithm has the feature of rapid convergence on the local optima. The hybrid of two algorithm will improve the evolving speed of neural network. GA-BP scheme adopts GA to search the optimal combination of weights in the solution space, and then uses BP algorithm to obtain the accurate optimal solution quickly. Experiment results show that the proposed GA-BP scheme is more efficient and effective than BP algorithm.     

基于随机森林算法的模拟电路故障诊断

为提高模拟电路参变故障的诊断率,提出基于多特征向量提取和随机森林(RF)算法的模拟电路故障诊断新方法。采用时域和频域特征向量组合的多维特征向量以反映不同故障特征,经RF算法进行决策,并对决策树棵数及候选特征向量个数进行优化。故障诊断实验结果表明,所提方法能较好地实现容差模拟电路故障诊断,与支持向量机(SVM)方法相比,表现出更好的分类性能;与小波(包)特征提取方法相比,简化了多维数据特征提取步骤,易于实现在线故障诊断。     

基于分数阶相关的模拟集成电路软故障诊断* Deng Yong(邓勇), Shi Yibing(师奕兵)and Zhang Wei(张伟)

针对模拟集成电路软故障诊断的难题,提出了基于分数阶相关的方法。首先,利用分数阶小波包将待测试电路(CUT)的Volterra级数进行分解,计算出分数阶相关函数。然后,用得到的分数阶相关函数构造出待测试电路的故障特征。通过对故障特征的比较,可以将待测试电路的各种软故障状态进行辨识并对故障实现定位。标准电路的仿真实验描述了这一方法并验证了该方法对模拟集成电路软故障诊断的有效性。     

基于多幅同目标图像和HMM的SAR图像目标识别

该文提出了一种基于多幅同目标图像和隐马尔可夫模型的合成孔径雷达图像目标识别方法。该方法通过小波域主成分分析提取目标图像特征向量,结合多幅不同方位角下的同目标图像的特征向量生成单幅图像的特征序列,用隐马尔可夫模型对特征序列进行识别。实验结果表明,该方法可明显提高目标的正确识别率,是一种有效的合成孔径雷达图像目标识别方法。     

Fault Detection of Analog Circuits Using Network Parameters

A new method to detect component faults in analog circuits is proposed in this paper. Network parameters like driving point impedance, transfer impedance, voltage gain and current gain are used to detect component faults in analog circuits as these network parameters are sensitive to the components of the circuit. Using montecarlo simulation each component of the circuit is varied within its tolerance limit and the minimum and the maximum values of each network parameter are found for fault free circuit. At the time of testing, the network parameters are found for the injected fault and if any one or more network parameters is exceeding its predetermined bound limits then the circuit is confirmed faulty. The proposed method is validated through second order Sallenkey band pass filter and fourth order Chebyshev low pass filter circuits. Numerical results are presented to clarify the proposed method and prove its efficiency.     

An accurate classifier based on adaptive neuro-fuzzy and features selection techniques for fault classification in analog circuits

This paper presents a new approach for faults classification in analog integrated circuits using a multiclass adaptive neuro fuzzy inference system classifier. This is carried out to assist analog circuit's faults diagnosis suffering from inaccurate faults classification on one hand, and to lessen computational burden on the other hand. This has been achieved from features number reduction. These features serving as input feature vector are extracted from the selected circuits (CUT) frequency and transient responses under both fault free and faulty conditions. The considered faults are resistors and capacitors values variations of about 50% low and high from their nominal ones. The method accuracy has been validated with three experiment circuits, the Sallen Key band-pass, the four opamp biquad high-pass and the leapfrog filters. The obtained results reveal a high level of efficiency with an accuracy average reach to 99.76%. Hence, the proposed method has shown a good performance in term of fault classification accuracy when compared with those of both the Artificial Neural Networks (ANN) approach and the fractional Fourier transform (FRFT) method based on a statistical property.     

基于小波网络和HMM的语音识别方法

利用隐马尔可夫模型(HMM)的动态时间序列建模能力及神经网络的模式分类能力,构成混合语音识别模型,同时考虑到语音信号的非平稳性,采用小波分析方法提取语音特征向量。通过时间规整方法,将所有具有可变长度的语音特征向量转换为相同维数的特征向量,从而简化了神经网络的结构。仿真结果表明,采用混合语音识别模型以及时间规整方法,不仅可提高识别率,同时大大缩减了训练时间,获得了很好的识别效果。     

模拟电路故障诊断中的特征信息提取

在运用BP神经网络进行模拟电路故障诊断过程中,代表故障特征的网络输入至关重要。分析了常见特征信息提取和故障诊断方法,提出一种基于多测试点、多特征信息原始样本集的新方法。运用这种方法构造原始故障特征集,然后作为BP神经网络的输入对网络进行训练,仿真结果表明,通过该方法构造的样本集训练出来的网络对模拟电路故障诊断的正确率优于传统方法,证明了该方法在模拟电路故障诊断中的可行性,为模拟电路的故障诊断提供了一种新方法。     

Diagnostics of Analog Circuits Based on LS-SVM Using Time-Domain Features

Most researchers use wavelet transforms to extract features from a time-domain transient response from analog circuits to train classifiers such as neural networks (NNs) and support vector machines (SVMs) for analog circuit diagnostics. In this paper, we have proposed some new feature selection methods from a time-domain transient response, and compared the diagnostic results based on a least squares SVM (LS-SVM) using different time-domain feature vectors. First, we have improved two traditional feature selection methods: (a) using the mean and standard deviation in wavelet transform features, and (b) using the mean, standard deviation, skewness, kurtosis, and entropy in statistical property features. Then, a conventional time-domain feature vector based on the impulse response properties of a control system has been proposed. The simulation experiments for a leapfrog filter and a nonlinear rectifier show that: (1) the two improved methods have better accuracy than the traditional methods; (2) the proposed conventional time-domain feature vector is effective in the diagnostics of analog circuits—over 99 % for both of the two example circuits; (3) the proposed diagnostic method can diagnose soft faults, hard faults, and multi-faults, regardless of component tolerances and nonlinearity effects.     

有序聚类方法及其在神经网络语音识别中的应用

本文提出了一种新的网络结构,我们称之为有序聚类网络。这种网络能够对语音信号进行特征提取,很好地解决神经网络语音识别中的时间规整问题。有序聚类网络从输入语音信号的特征矢量序列中撮出一组固定数目的特 矢量,然后将这组特征矢量馈入神经网络分类器进行识别。和其他的神经网络语音识别方法相比较,用这种网络进行前端处理,可以缩短后端神经网络分类器的训练和识别时间,简化经分类器的网络产高的识别率。根据该 们建立了