On improving training time of neural networks in mixed signal circuit fault diagnosis applications

Testing issues are becoming more and more important with the quick development of both digital and analog circuit industry. Analog-to-digital converters (ADCs) are becoming more and more widespread owing to their fundamental capacity of interfacing analog physical world to digital processing systems. In this paper, we study the use of neural networks in fault diagnosis of ADCs and compare the results with other ADC testing approaches such as histogram, FFT and sinewave curve fit test techniques. In this paper, we introduced the idea of separation of neural network’s output matrix to improve the training phase time, called ‘index-separation’ approach. Finally, we concluded that training time in this method is about 0.25 times as much as that in the normal training method. We also concluded that this approach does not affect network’s decision strength. Besides, we concluded that if the complexity of the circuit increases, this method will still be effective. Therefore, this method is a robust way for fault diagnosis of mixed signal circuits.     

Proposal of Fault Diagnosis of Analog Circuits by Combining Operation-Region Model and X–Y Zoning Method: Case Study

We propose a method of diagnosing analog circuits that is achieved by combining an operation-region model and an X–Y zoning method. The X–Y zoning method can be used to detect faults in analog circuits by using the relationship between circuit inputs and outputs. The operation-region model can be used to analyze/model circuit behaviors by utilizing changes in the operation regions of MOS transistors in a circuit. Operation regions are obtained from transistor node voltages at sampling time corresponding to a particular excitation of the input value and the corresponding output value. Since we developed a data processing method to handle data discretely, we could implement a procedure for diagnosis based on the preset test, which is a method of diagnosing digital circuits. We demonstrated the effectiveness of our method by applying it to ITC’97 benchmark circuits with hard and soft faults. We found that the diagnostic resolution is one for every fault.     

基于Takagi-Sugeno型自适应模糊神经网络的模拟电路故障诊断

该文提出了一种基于Takagi-Sugeno型自适应模糊神经网络故障诊断方法。首先通过电路仿真获得故障样本,其次利用主成分分析对故障样本进行降维处理,减少自适应模糊神经网络的输入,降低训练时间,然后采用BP算法与最小二乘法相结合的混合学习算法训练自适应模糊神经网络的连接权值和隶属度函数。仿真结果表明,此方法能够快速有效地对模拟电路的故障进行诊断和定位,表现出了很好的应用潜力,在容差模拟电路故障诊断领域具有较好的应用前景。     

基于PCA和PNN的模拟电路故障诊断

为了解决模拟电路故障识别困难的问题,提出一种基于主成分分析和概率神经网络的模拟电路故障诊断方法。该方法对采集到的模拟电路故障信息进行特征提取,将提取的故障特征归一化处理后输入概率神经网络,进行训练和故障模式的分类识别。实验结果表明,该方法是有效的,具有较高的故障诊断率。     

Fault-based ATPG for linear analog circuits with minimal size multifrequency test sets

An automatic test pattern generation (ATPG) procedure for linear analog circuits is presented in this work. A fault-based multifrequency test approach is considered. The procedure selects a minimal set of test measures and generates the minimal set of frequency tests which guarantee maximum fault coverage and, if required, maximal fault diagnosis, of circuit AC hard/soft faults. The procedure is most suitable for linear time-invariant circuits which present significant frequency-dependent fault effects.For test generation, the approach is applicable once parametric tests have determined DC behaviour. The advantage of this procedure with respect to previous works is that it guarantees a minimal size test set. For fault diagnosis, a fault dictionary containing a signature of the effects of each fault in the frequency domain is used. Fault location and fault identification can be achieved without the need of analog test points, and just in-circuit checkers with an observable go/no-go digital output are required for diagnosis.The procedure is exemplified for the case of an analog biquadratic filter. Three different self-test approaches for this circuit are considered. For each self-test strategy, a set of several test measures is possible. The procedure selects, in each case, the minimal set of test measures and the minimal set of frequency tests which guarantee maximum fault coverage and maximal diagnosis. With this, the self-test approaches are compared in terms of the fault coverage and the fault diagnosability achieved.This work is part of AMATIST ESPRIT-III Basic Research Project, funded by CEC under contract #8820.     

一种基于神经网络的模拟电路故障诊断方法

提出了一种基于模拟电路故障诊断的神经网络方法。这种方法利用小波分解、数据标准化、主成分分析对输入数据进行预处理,采用k个神经元输出的前馈神经网络结构进行有效训练。该方法检测和识别故障准确率高,系统的鲁棒性和稳定性强。     

基于小波神经网络的模拟电路故障诊断研究

文章提出了一种基于小波神经网络的模拟电路故障诊断方法。这种方法采用正弦信号作为被测电路的输入激励,在时域中对输出信号采样来构造神经网络的训练和测试样本,将自适应学习率及附加动量BP算法训练后的小波神经网络应用于容差模拟电路故障诊断中。仿真试验表明,该方法减少了故障诊断时间和提高了网络的平均诊断正确率。     

基于多分辨分析和WNN的模拟电路故障诊断

提出了一种基于多分辨分析和小波神经网络(WNN)相结合的模拟电路故障诊断方法。该方法利用了多分辨分析优异的时频特性,提取采集数据中的故障特征参数值,结合小波神经网络强大的非线性分类、学习、泛化能力及精度高、收敛速度快等特性,将得到的输入数据进行归一化处理作为小波神经网络的输入对其进行训练,并将训练的结果应用于滤波器电路故障诊断。结果表明,该方法实现了对故障模块的定位,是一种有效的模拟电路故障诊断方法。     

紧致型小波网络在模拟电路故障诊断中的应用

提出了一种新的基于紧致型小波神经网络的模拟电路故障诊断方法。该法首先利用小波包变换对故障信号进行预处理,减少了紧致型小波神经网络的输入数目,简化了紧致型小波神经网络结构,然后对紧致型小波神经网络进行训练和测试。仿真试验表明,该方法比普通BP神经网络方法训练速度更快,诊断准确率更高,容错能力强,非常适用于模拟电路故障诊断。     

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。     

Fault diagnosis and its prediction in wireless sensor networks using regressional learning to achieve fault tolerance

Due to the wide range of critical applications and resource constraints, sensor node gives unexpected responses, which leads to various kind of faults in sensor node and failure in wireless sensor networks. Many research studies focus only on fault diagnosis, and comparatively limited studies have been conducted on fault diagnosis along with fault tolerance in sensor networks. This paper reports a complete study on both 2 aspects and presents a fault tolerance approach using regressional learning with fault diagnosis in wireless sensor networks. The proposed method diagnose the different types of faulty nodes such as hard permanent, soft permanent, intermittent, and transient faults with better detection accuracy. The proposed method follows a fault tolerance phase where faulty sensor node values would be predicted by using the data sensed by the fault free neighbors. The experimental evaluation of the fault tolerance module shows promising results with R² of more than 0.99. For the periodic fault such as intermittent fault, the proposed method also predict the possible occurrence time and its duration of the faulty node, so that fault tolerance can be achieved at that particular time period for better performance of the network.     

A fully automatic one-scan adaptive zooming algorithm for color images

We present an interpolation algorithm for adaptive color image zooming. The algorithm produces the magnified image in one scan of the input image, and is fully automatic since does not involve any a priori fixed threshold. Given any integer zooming factor n, each pixel of the input image generates an n×n block of pixels in the zoomed image. For the currently visited pixel of the input image, the pixels of its associated block are first assigned tentative values, which are then adaptively updated before building the next block. The method is suggested for RGB images, but can equally be employed in other color spaces. Peak signal to noise ratio (PSNR) and Structural SIMilarity (SSIM) are used to evaluate the performance of the algorithm.     

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.     

基于支持向量机的变压器故障诊断

针对变压器故障诊断中缺少实际典型故障样本的问题,提出了支持向量机（SVMs）变压器故障诊断方法。该方法采用K均值聚类（KMC）对变压器油中5种特征气体样本进行预选取作为特征向量,输入到多分类支持向量机中进行训练,建立SVMs诊断模型,实现对故障样本的诊断分类。实例分析表明,KMC算法浓缩了故障信息,有效地解决了确定模型参数时耗时巨大的问题。该方法在有限样本情况下,能够达到较高的故障正判率,满足变压器故障自动诊断的目的。     

Multiple Soft Fault Diagnosis of Nonlinear Circuits Using the Continuation Method

This paper offers a method for multiple soft fault diagnosis of nonlinear static circuits. The method enables us to locate the faulty elements and evaluate their parameters. It exploits a set of n nonlinear algebraic type diagnostic equations in n unknown variables and is oriented on finding multiple solutions of these equations. As a result, the method is capable of finding, in systematic manner, different sets of the parameters which satisfy the diagnostic test, rather than one specific set. For this purpose the continuation (homotopy) approach is applied and an efficient procedure for tracing a homotopy path is developed. The proposed method is especially useful at the pre-production stage, where corrections of the technological process are possible and the diagnostic time is not crucial. To illustrate the proposed approach two numerical examples are given.     

基于小波神经网络和相位差的模拟电路故障诊断

根据模拟电路中存在噪声的问题,提出利用相位差来进行故障诊断。通过正常模式和故障模式下相位差和幅值差的特征提取,建立故障字典。然后利用小波神经网络对故障电路建模,基于该网络学习收敛快,对网络输入不太敏感的特点,实现故障诊断。通过实例证明,该方法不但诊断准确,而且很切合实际模拟电路。     

一种基于小波预处理的模拟电路故障诊断方法

文中提出了一种基于小波预处理的模拟电路故障诊断方法。由于小波分析具有数据压缩和特征提取的特性,我们利用小波变换对电路脉冲信号进行多尺度分解,提取特征向量输入神经网络进行训练。实验表明,该办法可以有效地减少神经网络的训练时间,提高模拟电路故障诊断的准确率。     

Extension of the bond graph causality inversion method for fault detection and isolation

Controlled systems can be subjected to faults that may affect the performance of the system, and unable its objectives to be achieved. Fault detection and isolation algorithms are then used to study these faults. The bond graph tool can be used for modeling purposes and then its structural, and causal properties can be exploited for automatic generation of analytical redundancy relations (ARRs) through a procedure named causality inversion method, which are used for diagnosis applications. These ARRs are mathematical constraints that are used to verify the coherence between the process measurements and the system model. This paper proposes an extension of the causality inversion method by different versions of the same ARR. The goal is to increase the number of isolable faults. Moreover, structural conditions are given in order to avoid the generation of redundant ARRs. To validate the obtained structural procedure, a fault is imposed in a traction of an omnidirectional mobile robot.     

A test points selection method for analog fault dictionary techniques

The problem of test point selection is important in the area of fault diagnosis and circuit testing. In this paper, the problem of near optimum test points set selection for analog fault dictionary is considered. This problem is formulated as a depth-first graph search problem. So the test points selection progress is transformed to a graph node expanding progress. The graph node construction method and node expanding procedure are given also. The proposed graph search method guarantee a maximum information increase of S _opt by adding a test point to S _opt each time, where S _opt is the desired test points set used on the path from current node to root node. So a global minimum test points set can be more likely achieved than other methods. The results of statistical experiments indicate that the proposed method more accurately finds the global minimum set of test points without increasing time complexity; therefore, it is a good solution to minimize the size of test points set.     

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。