Feature evaluation and extraction based on neural network in analog circuit fault diagnosis

Choosing the right characteristic parameter is the key to fault diagnosis in analog circuit. The feature evaluation and extraction methods based on neural network are presented. Parameter evaluation of circuit features is realized by training results from neural network; the superior nonlinear mapping capability is competent for extracting fault features which are normalized and compressed subsequently. The complex classification problem on fault pattern recognition in analog circuit is transferred into feature processing stage by feature extraction based on neural network effectively, which improves the diagnosis efficiency. A fault diagnosis illustration validated this method.

Data-driven fault diagnosis method for analog circuits based on robust competitive agglomeration

The data-driven fault diagnosis methods can improve the reliability of analog circuits by using the data generated from it. The data have some characteristics, such as randomness and incompleteness, which lead to the diagnostic results being sensitive to the specific values and random noise. This paper presents a data-driven fault diagnosis method for analog circuits based on the robust competitive agglomeration （RCA）, which can alleviate the incompleteness of the data by clustering with the competing process. And the robustness of the diagnostic results is enhanced by using the approach of robust statistics in RCA. A series of experiments are provided to demonstrate that RCA can classify the incomplete data with a high accuracy. The experimental results show that RCA is robust for the data needed to be classified as well as the parameters needed to be adjusted. The effectiveness of RCA in practical use is demonstrated by two analog circuits.

Improved RBF network application in analog circuit fault isolation

One kind of steepest descent incremental projection learning algorithm for improving the training of radial basis function(RBF)neural network is proposed,which is applied to analog circuit fault isolation.This algorithm simplified the structure of network through optimum output layer coefficient with incremental projection learning(IPL)algorithm,and adjusted the parameters of the neural activation function to control the network scale and improve the network approximation ability.Compared to the traditional algorithm,the improved algorithm has quicker convergence rate and higher isolation precision.Simulation results show that this improved RBF network has much better performance,which can be used in analog circuit fault isolation field.

Combinatorial Optimization Based Analog Circuit Fault Diagnosis with Back Propagation Neural Network

Electronic components' reliability has become the key of the complex system mission execution. Analog circuit is an important part of electronic components. Its fault diagnosis is far more challenging than that of digital circuit. Simulations and applications have shown that the methods based on BP neural network are effective in analog circuit fault diagnosis. Aiming at the tolerance of analog circuit,a combinatorial optimization diagnosis scheme was proposed with back propagation( BP) neural network( BPNN).The main contributions of this scheme included two parts:( 1) the random tolerance samples were added into the nominal training samples to establish new training samples,which were used to train the BP neural network based diagnosis model;( 2) the initial weights of the BP neural network were optimized by genetic algorithm( GA) to avoid local minima,and the BP neural network was tuned with Levenberg-Marquardt algorithm( LMA) in the local solution space to look for the optimum solution or approximate optimal solutions. The experimental results show preliminarily that the scheme substantially improves the whole learning process approximation and generalization ability,and effectively promotes analog circuit fault diagnosis performance based on BPNN.

Robust Fault Diagnosis of Analog Circuits with Tolerances

A method for robust analog fault diagnosis using hybrid neural networks is proposed. The primary focus of the paper is to provide robust diagnosis using a mechanism to deal with the problem of element tolerances and reduce testing time. The proposed approach is based on the fault dictionary diagnosis method and backward propagation neural network (BPNN) and the adaptive resonance theory (ART) neural network. Simulation results show that the method is robust and fast for fault diagnosis of analog circuits with tolerances.

Fault Diagnosis of Analog Circuit Based on PSO and BP Neural Network

In order to improve the speed and accuracy of analog circuit fault diagnosis,using Back Propagation Neural Network(BPNN),a new method is proposed based on Particle Swarm Optimization(PSO)to adjust weights of BP neural network.The model can not only overcome the limitations of the slow convergence and the local extreme values by basic BP algorithm,but also improve the learning ability and generalization ability with a higher precision.The response signals of analog circuit is preprocessed by Wavelet Packet Transform(WPT)as the fault feature.The simulation result shows that the proposed method has higher diagnostic accuracy and faster convergence speed,which is effective for fault location.

A Method on Analog Circuit Fault Diagnosis with Tolerance

In this paper, it is proved that the direction of the node-voltage difference vector, which is the difference between the node-voltage vector at faulty state and the one at the nominal state, is determined only by the location of the faulty clement in linear analog circuits. Considering that the direction of the node-voltage sensitivity vector is the same as the one of the node-voltage difference vector and also considering that the module of the node-voltage sensitivity vector presents the weight of the parameter of faulty element deviation relative to the voltage difference, fault dictionary is set up based on node-voltage sensitivity vectors. A decision algorithm is proposed concerned with both the location and the parameter difference of the faulty element. Single fault and multi-fault can be diagnosed while the circuit parameters deviate within the tolerance range of 10 %.

Method for Analog Circuit Soft-Fault Diagnosis and Parameter Identification Based on Indictor of Phase Deviation and Spectral Radius

The soft fault induced by parameter variation is one of the most challenging problems in the domain of fault diagnosis for analog circuits.A new fault location and parameter prediction approach for soft-faults diagnosis in analog circuits is presented in this paper.The proposed method extracts the original signals from the output terminals of the circuits under test（CUT） by a data acquisition board.Firstly,the phase deviation value between fault-free and faulty conditions is obtained by fitting the sampling sequence with a sine curve.Secondly,the sampling sequence is organized into a square matrix and the spectral radius of this matrix is obtained.Thirdly,the smallest error of the spectral radius and the corresponding component value are obtained through comparing the spectral radius and phase deviation value with the trend curves of them,respectively,which are calculated from the simulation data.Finally,the fault location is completed by using the smallest error,and the corresponding component value is the parameter identification result.Both simulated and experimental results show the effectiveness of the proposed approach.It is particularly suitable for the fault location and parameter identification for analog integrated circuits.

Research method of circuit fault diagnosis based on FCM

Using fuzzy C cluster mean (FCM), fuzzy theory and neural network, a fault diagnosis method was proposed, which was based on fuzzy C-means clustering algorithm of neural network that was applied in non-linear analog circuits and in diagnoses the ARNIC 429 reception circuit of aviation aircraft avionics. The C cluster algorithm can make the amount of the fuzzy rule automatically and can create an initial fuzzy rule database of fault diagnosis. A type of fuzzy neural network and a fault tree were generated. The algorithm avoids the disadvantage that gets into the part of optimum circumstance. A validate application was implemented, which proves that the method is effective. Therefore, the method is superior to the traditional methods in fault diagnosis, and the efficiency is heavily improved.

THE EFFECTIVE RANGE OF K-FAULT DIAGNOSIS OF-LINEAR CIRCUITS

In view of K-fault testability,the topological construction of a practical circuitis far from ideal.In order to improve the testability of a circuit,we may increase the numberof accessible nodes or use the multi-excitation method.Effectiveness of these methods and thefeasibility of choosing accessible nodes are discussed in detail.The conditions for multi-excitationtestability are presented.

基于FSSA-ELM的模拟电路故障诊断方法

在大规模电路中,模拟电路的故障率高达80%。针对模拟电路故障诊断方法准确率低、耗时长的问题,提出了一种分数阶麻雀搜索算法结合极限学习机(FSSA-ELM)的模拟电路故障诊断方法。利用核主成分分析与局部线性嵌入(KPCA-LLE)联合方式对电路故障数据进行特征提取,通过分数阶与麻雀搜索算法(SSA)相融合,对极限学习机(ELM)的权重和阈值进行寻优,将提取后的特征数据输入到FSSA-ELM模型中进行训练和测试。T型反馈网络反相比例运算电路诊断实例表明,FSSA-ELM的故障诊断用时相较于SSA-ELM缩短了891 s,单故障诊断准确率可达972%,比SSA-ELM和ELM分别提高了19%和28%;双故障诊断准确率可达95%,分别提高了04%和10%。该故障诊断方法准确率高、耗时短,具有较强的模拟电路故障检测能力。

基于IHHO-BP神经网络的模拟电路故障诊断

针对模拟电路故障类型多、故障状态不稳定以及故障数据冗余,使得模拟电路故障诊断困难的问题,提出利用改进哈里斯鹰算法(improved Harris Hawks optimization, IHHO)优化反向传播(back propagation, BP)神经网络,实现模拟电路故障特征选择与诊断。首先,将非线性自适应因子、柯西变异和随机差分扰动引入哈里斯鹰算法,实现收敛速度和精度的提升;其次,采用IHHO对模拟电路的单一故障和组合故障仿真数据进行特征选择,完成数据预处理;最后,采用IHHO-BP算法,对预处理后的故障数据进行训练和测试,实现模拟电路故障诊断。诊断结果表明,所提方法的诊断精度相较于其他算法提升了5.5%。

基于IWOA-ELM的模拟电路故障诊断方法

针对模拟电路故障诊断中非线性和高维度输出信号带来的诊断困难问题,提出一种基于改进鲸鱼算法(IWOA)优化极限学习机(ELM)的模拟电路故障诊断方法。首先,采用主成分分析(PCA)法对初始故障电路特征进行降维;其次,在鲸鱼算法的基础上引入Tent映射来初始化种群,并且加入了非线性时变因子、自适应权重以及随机差分变异策略;再利用改进后的鲸鱼算法对ELM进行优化;最后将降维后的故障特征向量输入ELM中得到故障诊断结果。通过Sallen-Key带通滤波器电路以及CSTV滤波器电路仿真测试实例表明:IWOA优化ELM的故障诊断方法具有更优的故障诊断性能,故障诊断准确率高达99.41%。

基于INGO-Transformer的模拟电路元件故障预测

针对模拟电路元件易受外部环境影响发生故障、故障特征提取困难、无法准确预测及诊断元件故障等问题,基于Transformer模型提出改进INGO-Transformer方法。采用小波包分解(WPD)对原始数据进行特征提取,使用特征向量之间的三角距离来表征模拟电路中元件的退化状态,使用INGO优化Transformer的训练超参数构建预测模型。以Sallen-Key带通滤波电路与镜像电流源电路为预测实验对象进行故障预测实验,采用MAE与MSE作为故障预测模型评价指标,两组实验电路10次实验平均MAE、MSE结果分别为4.2162e-04、4.1906e-07和0.0017、1.9625e-05。仿真结果表明,所提方法在模拟电路单一元件故障预测中具有较高的准确性与较强的泛化能力。

基于优化矩阵扰动分析的模拟电路故障诊断

在现有的模拟电路故障诊断算法中,人工智能故障诊断算法训练数据量大、训练时间长,且难以实现参数辨识。传统电路分析方法所需测试点多,计算复杂。基于此,提出了一种基于优化矩阵扰动分析的模拟电路故障诊断算法。首先,采用拉普拉斯(Laplace)算子卷积被测电路的输出响应矩阵,从而增强矩阵元素与电路元件参数之间的扰动规律。其次,选取矩阵的迹和谱半径作为故障特征,并利用这种扰动规律建立矩阵模型。然后,利用改进的诊断算法,在Sallen_Key带通滤波器电路和跳蛙低通滤波器电路上进行实例验证。结果表明,所提方法在仅使用一个测点的情况下,可实现故障元件的参数辨识。其故障诊断率达100%,参数辨识误差控制在1%内,且计算时间控制在毫秒级别。因此该方法容易实现在线测试,且适用于要求高定位准确率、高精度参数辨识的场合。

适配器匹配下的大规模模拟电路故障红外图像检测系统设计

为了提升模拟电路故障检测效果,精准定位确定电路故障区域,设计了适配器匹配下的大规模模拟电路故障红外图像检测系统。通过三维精密电动平台,确定大规模模拟电路的红外成像范围;通过定位标志刻画电路红外图像边缘;利用适配器统一匹配待测电路输入输出接口信号;通过三维精密电动平台、定位标志与适配器,共同控制热像仪,扫描待测电路,获取电路红外图像;利用图像存储卡存储扫描获取的电路红外图像;通过红外图像预处理模块,滤波处理红外图像;大规模模拟电路故障诊断模块利用互信息配准法,配准图像存储卡内的电路红外图像,通过差分检测法初步确定电路故障区域,利用热序列检测法精准检测电路故障元件;利用互联网络实现整个系统的通信。实验证明:该系统可有效采集并预处理电路红外图像,提升红外图像清晰度;该系统可有效初步确定电路故障区域,精准诊断电路故障元件。

基于深度学习的模拟电路故障诊断方法研究

本文重点研究基于深度学习的模拟电路故障诊断方法。基于传统故障诊断方法的分析以及深度学习技术在其他领域的成功应用,提出了一种基于深度学习的模拟电路故障诊断方法。通过构建合适的数据集、设计合适的神经网络模型以及优化训练算法,实现对模拟电路故障的准确诊断。该方法能够有效提高故障诊断的准确性和效率,具有广阔的应用前景。

RBF神经网络在船舶模拟电路故障诊断中的应用

针对船舶模拟电路元件复杂交互,故障信号在大量的正常信号中难以凸显,故障特征提取识别难度较大的问题,提出基于RBF神经网络的船舶模拟电路故障诊断方法。由基于小波包的船舶模拟电路故障特征提取方法,以小波分解重构的方式,捕捉电路频带能量变化特征;使用基于状态转移算法优化RBF神经网络的故障诊断模型,由状态转移算法优化RBF神经网络参数,构建用于诊断电路故障的RBF神经网络模型后,学习所提取故障特征与类型之间关系,诊断新输入的船舶模拟电路输出信号故障类型。实验测试结果显示,此方法在有效捕捉船舶模拟电路故障频带能量变化特征后,对多种船舶模拟电路故障的诊断结果均未出现明显错误。