多策略改进麻雀算法与 BiLSTM 的变压器故障诊断研究

针对变压器故障诊断精度低的问题,提出了一种多策略改进麻雀算法(MISSA)与双向长短时记忆网络(BiLSTM)的变压器故障诊断模型。基于油中溶解气体分析(DGA)技术,结合无编码比值方法提取变压器9维故障特征作为模型输入进行网络训练,输出层采用Softmax函数得到故障诊断类型;采用Logistic混沌映射、均匀分布的动态自适应权重以及动态拉普拉斯算子来对麻雀搜索算法(SSA)进行改进;在初始解集内,利用MISSA对目标超参数进行寻优,使变压器故障诊断精度最优,并结合核主成分分析(KPCA)对故障特征指标降维,加快模型收敛速度。结果表明,提出的模型诊断精度为94%与PSO-BiLSTM、GWO-BiLSTM和SSA-BiLSTM故障诊断模型相比,分别提高了11.33%、8.67%、6%,验证了本文方法能够有效地提高变压器的故障诊断性能。     

神经网络结构与算法对变压器故障诊断的影响

BP神经网络算法本质上是基于梯度下降的一种迭代学习算法,存在学习收敛速度慢、收敛精度低、易陷入局部极小、学习率难以选取、隐层数及隐层神经元个数难以确定等缺陷。为了选择出更适宜变压器DGA故障诊断的神经网络结构及算法。本文采用了常用的几种智能算法对变压器故障样本进行了诊断性能对比实验。结果得出Levenberg-Marquardt神经网络算法是收敛速度较快的算法,有动量和自适应的梯度下降法是收敛稳定性较佳的算法;网络最优结构设计过程。为用于变压器DGA故障诊断的神经网络的结构和算法提供了系统化的试验方法。     

以模糊聚类标准谱与灰色关联序诊断变压器内部故障的方法研究

通过对变压器故障和以DGA为特征量的症状之间难以量化的模糊和灰色特征的分析，采用模糊聚类分析方法获取。个聚类中心，根据聚类中心的物理和数学意义，这c个聚类中心组成变压器故障诊断的标准谱，利用灰色关联分析原理，求出待诊模式与各标准模式的关联序，实现故障诊断，进而提出了灰色关联分析和模糊聚类相结合的变压器故障诊断新方法。并经实例证明，其诊断准确率高于其它方法。     

基于重构贡献和灰关联熵的变压器诊断方法

提出了一种基于重构贡献和灰关联熵相结合的变压器故障诊断新方法.该方法在利用油中溶解气体分析数据建立主元模型后,基于故障重构的思想,计算样本各变量重构贡献率作为特征量,规格化处理来提取变压器油中溶解气体的故障特征信息.为了克服单一灰关联分析中易造成局部关联及信息损失等缺陷,采用灰关联熵方法进行变压器故障类型诊断.实例研究结果表明,该方法具有良好的故障识别能力,提高了故障诊断的准确性.     

Identification of location and size of a defect in a structural system employing active external excitation and hybrid feature vector components in HMM

For the fault diagnosis of a mechanical system, various kinds of methods have been developed so far. For a structural system having a defect, pattern recognition methods such as Hidden Markov model (HMM) and Artificial neural network (ANN) are widely used in engineering fields. A statistical model can be constructed with one of the methods using various signals that are extracted from the structural system of interest. In the present study, a HMM employing hybrid feature vector measures is proposed for the fault diagnosis of a structural system having a defect. To obtain the hybrid feature vector components, five frequency response peaks obtained with FFT and two additional components obtained with ANN are employed. For the proposed method, an active external excitation having some specific frequency components is also applied to the structure to overcome the noise effect. To verify the effectiveness of the proposed method, a numerical model of a rotating blade having a crack is employed. Acceleration signals extracted from the structural system are employed to develop the proposed model so that the location and size of the crack can be identified. Using the proposed method, the diagnostic accuracy of the identification is significantly improved even with high level of noise in the system.     

在线式电力变压器故障诊断系统

电力变压器油中溶解气体的组分和含量在一定程度上反映出变压器绝缘老化或故障的程度。在线式电力变压器故障诊断系统将各气体组分的浓度转换戍相应的电信号，经数据处理后送入工作站生成色谱图，实现了变压器油中溶解气体组分、含量及产气速率的在线监测，并利用灰色关联理论进行故障诊断，及时发现并判断变压器内部存在的潜伏性故障，克服了传统三比值法故障编码与故障分类不能一一对应的缺点。实验表明，该系统和方法的故障诊断准确率达到95％。     

基于PNN的电力变压器故障诊断方法

对油中溶解气体进行深入分析后,以改良的三比值法为基础,提出一种基于概率神经网络(PNN)的变压器故障诊断方法。该方法利用PNN的强大的非线性分类能力,将故障样本空间映射到故障模式空间中,可形成一个具有较强容错能力和结构自适应能力的诊断网络系统,从而提高故障诊断的准确率。仿真结果表明,实际案例数据验证了此方法准确率高,是一种有效的故障诊断方法。     

变压器油中气体拉曼光谱检测及信号处理方法

准确检测变压器油中溶解故障特征气体是诊断变压器运行状态的重要技术手段之一。论文基于拉曼光谱和腔长调制频率锁定原理,搭建了变压器故障特征气体频率锁定腔增强拉曼光检测平台,实现了H_2、CH_4、C_2H_2、C_2H_4、C_2H_6、CO、CO_2等七种故障特征气体的同时检测;1atm时,H_2、CH_4、C_2H_2、C_2H_4、C_2H_6、CO、CO_2的最小检测浓度实验值分别达到106、25、45、73、41、170、126(ppm)。频率锁定增强腔技术使最小检测浓度提高了约68倍。运用小波模极大值法对H_2的拉曼光谱检测信号进行了去噪处理,提出了基于包络线迭代法的光谱基线校正方法,校正后的光谱荧光背景残留减少,使气体拉曼光谱检测准确度提高了约2.95%,为变压器油中溶解故障气体同时准确检测提出了一种新方法。     

基于实例的学习矢量量化神经网络诊断方法及其应用

基于CBR良好的可扩充性、可移植性和神经网络极强的分类能力,提出了基于实例的学习矢量量化神经网络诊断方法。该方法应用于机械故障诊断系统中,可以减小实例搜索空间,提高实例检索效率。论述了系统的设计方法和应用步骤。     

Defect diagnostics of SUAV gas turbine engine using hybrid SVM-artificial neural network method

A hybrid method of an artificial neural network (ANN) combined with a support vector machine (SVM) has been developed for the defect diagnostic system applied to the SUAV gas turbine engine. This method has been suggested to overcome the demerits of the general ANN with the local minima problem and low classification accuracy in case of many nonlinear data. This hybrid approach takes advantage of the reduction of learning data and converging time without any loss of estimation accuracy because the SVM classifies the defect location and reduces the learning data range. The results of test data have shown that the hybrid method is more reliable and suitable algorithm than the general ANN for the defect diagnosis of the gas turbine engine. This paper was recommended for publication in revised form by Associate Editor Tong Seop Kim Tae-Seong Roh received his B.S. and M.S. degrees in Aeronautical Engineering from Seoul National University in 1984 and 1986. He then went on to receive his Ph.D. degree from Pennsylvania State University in 1995. Dr. Roh is currently a Professor at the department of Aerospace Engineering at Inha University in Incheon, Korea. His research interests are in the area of combustion instabilities, rocket and jet propulsion, interior ballistics, and gas turbine engine defect diagnostics. Dong-Whan Choi received his B.S. degree in Aeronautical Engineering from Seoul National University in 1974. He then went on to receive his M.S. and Ph.D. degrees from University of Washington in 1978 and 1983. Dr. Choi served three years as a President of the Korea Aerospace Research Institute from 1999. He is currently a professor at the department of Aerospace Engineering at Inha University in Incheon, Korea. His research interests are in the area of turbulence, jet propulsion, and gas turbine defect diagnostics.     

基于SSA-PNN的电力变压器故障诊断

为了提高变压器故障诊断的准确率,在改良三比值法的基础上,采用麻雀搜索算法优化概率神经网络构建一种新型变压器故障诊断网络模型,并设计相应的故障诊断方法。分析表明,与基于概率神经网络的变压器故障诊断方法相比,基于该网络模型的诊断方法提高了变压器故障识别与故障分类的准确率,在电力变压器的故障诊断中具有一定的实际工程意义。     

基于非线性复杂测度的往复压缩机故障诊断

往复压缩机以多源非线性冲击振动信号为主,应用传统方法难以从振动信号中提取故障特征,为此提出一种基于非线性复杂测度的往复压缩机故障诊断方法。以气阀正常、阀片有缺口、阀片断裂及弹簧损坏4种状态下往复压缩机气阀振动信号为分析数据,在小波阈值降噪处理的基础上,采用均值符号化方法计算信号的归一化Lempel-Ziv复杂度(Lempel-Zivcomplexity,LZC)指标,分别给出各状态相应的LZC特征区间,利用BP人工神经网络对各状态信号的有效值特征、功率谱能量特征及LZC特征分别进行训练和测试,结果表明LZC更能准确区分不同状态的往复压缩机气阀故障,为往复压缩机故障诊断和维修决策提供了一种有效方法。     

Semi-supervised weighted kernel clustering based on gravitational search for fault diagnosis

Supervised learning method, like support vector machine (SVM), has been widely applied in diagnosing known faults, however this kind of method fails to work correctly when new or unknown fault occurs. Traditional unsupervised kernel clustering can be used for unknown fault diagnosis, but it could not make use of the historical classification information to improve diagnosis accuracy. In this paper, a semi-supervised kernel clustering model is designed to diagnose known and unknown faults. At first, a novel semi-supervised weighted kernel clustering algorithm based on gravitational search (SWKC-GS) is proposed for clustering of dataset composed of labeled and unlabeled fault samples. The clustering model of SWKC-GS is defined based on wrong classification rate of labeled samples and fuzzy clustering index on the whole dataset. Gravitational search algorithm (GSA) is used to solve the clustering model, while centers of clusters, feature weights and parameter of kernel function are selected as optimization variables. And then, new fault samples are identified and diagnosed by calculating the weighted kernel distance between them and the fault cluster centers. If the fault samples are unknown, they will be added in historical dataset and the SWKC-GS is used to partition the mixed dataset and update the clustering results for diagnosing new fault. In experiments, the proposed method has been applied in fault diagnosis for rotatory bearing, while SWKC-GS has been compared not only with traditional clustering methods, but also with SVM and neural network, for known fault diagnosis. In addition, the proposed method has also been applied in unknown fault diagnosis. The results have shown effectiveness of the proposed method in achieving expected diagnosis accuracy for both known and unknown faults of rotatory bearing.     

基于遗传算法的旋转机械故障诊断方法融合

针对任何单一性质故障特征、单一诊断方法难以实现在整个故障状态空间上准确诊断的局限性,提出基于遗传算法的旋转机械融合诊断方法。该方法能有效利用各种不同性质故障特征和不同诊断方法,使其发挥各自的优点,从而提高诊断的准确率。针对不同特征利用遗传算法将神经网络诊断和人工免疫诊断方法融合起来,使每一个诊断方法都在其优势空间区域发挥作用,使用小波包能量特征和双谱特征对两种诊断方法训练后,用遗传算法优化诊断融合权值矩阵对旋转机械进行实例诊断结果表明,该融合诊断方法能有效地提高故障诊断的准确率,并能提高诊断系统的鲁棒性。     

A hybrid fault diagnosis approach based on mixed-domain state features for rotating machinery

To make further improvement in the diagnosis accuracy and efficiency, a mixed-domain state features data based hybrid fault diagnosis approach, which systematically blends both the statistical analysis approach and the artificial intelligence technology, is proposed in this work for rolling element bearings. For simplifying the fault diagnosis problems, the execution of the proposed method is divided into three steps, i.e., fault preliminary detection, fault type recognition and fault degree identification. In the first step, a preliminary judgment about the health status of the equipment can be evaluated by the statistical analysis method based on the permutation entropy theory. If fault exists, the following two processes based on the artificial intelligence approach are performed to further recognize the fault type and then identify the fault degree. For the two subsequent steps, mixed-domain state features containing time-domain, frequency-domain and multi-scale features are extracted to represent the fault peculiarity under different working conditions. As a powerful time-frequency analysis method, the fast EEMD method was employed to obtain multi-scale features. Furthermore, due to the information redundancy and the submergence of original feature space, a novel manifold learning method (modified LGPCA) is introduced to realize the low-dimensional representations for high-dimensional feature space. Finally, two cases with 12 working conditions respectively have been employed to evaluate the performance of the proposed method, where vibration signals were measured from an experimental bench of rolling element bearing. The analysis results showed the effectiveness and the superiority of the proposed method of which the diagnosis thought is more suitable for practical application.     

基于大量故障实例的故障诊断系统设计

一些具有组分结构的系统（如机载火力控制系统）相当复杂,要想获得全套系统精确的故障诊断数学模型是非常困难的。利用维修人员在基层级和中继级获得的大量故障实例,采用神经网络和专家系统技术,则可以设计出一种基于症状知识的故障诊断系统。该故障诊断系统主要由知识库、专家规则诊断单元和神经网络诊断单元组成,其神经网络诊断单元随着故障实例训练的增加而不断成熟,专家规则诊断单元则可以通过神经网络对故障实例的训练与仿真来完善和扩充,具有很强的自学习功能和专家规则不能包容的新故障诊断能力。     

Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network

In rotary complex machines, collapse of a component may inexplicably occur usually accompanied by a noise or a disturbance emanating from other sources. Rolling bearings constitute a vital part in many rotational machines and the vibration generated by a faulty bearing easily affects the neighboring components. Continuous monitoring, fault diagnosis and predictive maintenance, is a crucial task to reduce the degree of damage and stopping time for a rotating machine. Analysis of fault-related vibration signal is a usual method for accurate diagnosis. Among the resonant demodulation techniques, a well-known resolution often used for fault diagnosis is envelope analysis. But, usually this method may not be adequate enough to indicate satisfactory results. It may require some auxiliary additional techniques. This study suggests some methods to extract features using envelope analysis accompanied by Hilbert Transform and Fast Fourier Transform. The proposed artificial neural network (ANN) based fault estimation algorithm was verified with experimental tests and promising results. Every test was initiated with a reference ANN architecture to avoid inappropriate classification during the evaluation of fitness value. Later, ANN model was modified using a genetic algorithm providing, an optimal skillful fast-reacting network architecture with improved classification results.     

基于免疫算法优化最小二乘支持向量机的压器故障诊断

由于支持向量机中的参数会显著影响着支持向量机分类的精确度,建立了一种基于免疫算法优化最小二乘支持向量机的电力变压器故障诊断模型;该模型以变压器油中主要溶解气体作为向量机的输入,以变压器故障类型作为其相应的输出,选用径向基核、使用免疫算法得到优化参数,充分发挥向量机较高泛化能力的优势.实例验证表明,这种方法能提高变压器的故障诊断准确率,反映了其有效性和正确性.     

时频分析和深度学习相结合的滚动轴承故障诊断

滚动轴承大量使用在旋转机械中,轴承的工况严重影响着机械设备的正常运行。为了提高轴承故障的诊断精度,本文提出了一种时频分析和深度学习相结合的滚动轴承诊断方法。首先,分析了十种不同时频分析方法;其次,建立了深度学习的滚动轴承故障诊断模型,并利用迁移学习克服训练样本数量少的问题,通过对比分析,常数Q变换(Constant Q transform, CQT)的准确率可达100%;最后,利用实验数据对所提方法的有效性和可靠性进行验证,分别评估了在不同负载和噪声情况下的识别精度,并与文献中的方法对比,证明所提方法在不同工作环境条件下都有较好的鲁棒性和较高的识别精度。     

变压器故障的诊断研究

阐述了变压器在线故障诊断的意义,对故障类型和诊断方法做了详细的介绍,系统阐述了基于神经网络的变压器诊断理论,对尽早发现潜伏性故障及提高运行维护水平,具有重要的意义。