Multi-Sensor Vibration Signal Based Three-Stage Fault Prediction for Rotating Mechanical Equipment

In order to reduce maintenance costs and avoid safety accidents, it is of great significance to carry out fault prediction to reasonably arrange maintenance plans for rotating mechanical equipment. At present, the relevant research mainly focuses on fault diagnosis and remaining useful life (RUL) predictions, which cannot provide information on the specific health condition and fault types of rotating mechanical equipment in advance. In this paper, a novel three-stage fault prediction method is presented to realize the identification of the degradation period and the type of failure simultaneously. Firstly, based on the vibration signals from multiple sensors, a convolutional neural network (CNN) and long short-term memory (LSTM) network are combined to extract the spatiotemporal features of the degradation period and fault type by means of the cross-entropy loss function. Then, to predict the degradation trend and the type of failure, the attention-bidirectional (Bi)-LSTM network is used as the regression model to predict the future trend of features. Furthermore, the predicted features are given to the support vector classification (SVC) model to identify the specific degradation period and fault type, which can eventually realize a comprehensive fault prediction. Finally, the NSF I/UCR Center for Intelligent Maintenance Systems (IMS) dataset is used to verify the feasibility and efficiency of the proposed fault prediction method.     

A New Fault Diagnosis of Rolling Bearing Based on Markov Transition Field and CNN

The rolling bearing is a crucial component of the rotating machine, and it is particularly vital to ensure its normal operation. In addition, the selection of different category features will add uncertainty and bias to the classification results. In order to decrease the interference of these factors to fault diagnosis, a new method that automatically learns the features of the data combined with Markov transition field (MTF) and convolutional neural network (CNN) is proposed in this paper, namely MTF-CNN. The MTF contributes to convert the original time series into corresponding figures, and the CNN is used to extract the deep feature information in the figure to complete the fault diagnosis. The effectiveness of the proposed method is verified by two public data sets. The experimental results show that MTF-CNN can classify different types of faults, and the highest accuracy rate can reach 100%. Likewise, the classification accuracy of this method is higher than some existing methods.     

A New Deep Dual Temporal Domain Adaptation Method for Online Detection of Bearings Early Fault

With the quick development of sensor technology in recent years, online detection of early fault without system halt has received much attention in the field of bearing prognostics and health management. While lacking representative samples of the online data, one can try to adapt the previously-learned detection rule to the online detection task instead of training a new rule merely using online data. As one may come across a change of the data distribution between offline and online working conditions, it is challenging to utilize the data from different working conditions to improve detection accuracy and robustness. To solve this problem, a new online detection method of bearing early fault is proposed in this paper based on deep transfer learning. The proposed method contains an offline stage and an online stage. In the offline stage, a new state assessment method is proposed to determine the period of the normal state and the degradation state for whole-life degradation sequences. Moreover, a new deep dual temporal domain adaptation (DTDA) model is proposed. By adopting a dual adaptation strategy on the time convolutional network and domain adversarial neural network, the DTDA model can effectively extract domain-invariant temporal feature representation. In the online stage, each sequentially-arrived data batch is directly fed into the trained DTDA model to recognize whether an early fault occurs. Furthermore, a health indicator of target bearing is also built based on the DTDA features to intuitively evaluate the detection results. Experiments are conducted on the IEEE Prognostics and Health Management (PHM) Challenge 2012 bearing dataset. The results show that, compared with nine state-of-the-art fault detection and diagnosis methods, the proposed method can get an earlier detection location and lower false alarm rate.     

基于XRF-CNN土壤重金属Zn元素含量预测模型研究

结合X射线荧光光谱法,针对土壤中重金属元素Zn含量的预测问题,提出基于深度卷积神经网络回归预测模型。对原始土壤进行相关预处理,用粉末压片法制作土壤压片,采用X射线荧光光谱法(X-Ray-fluorescence,XRF)获取土壤光谱,相比于传统检测方式,XRF法具有检测速度快、精度高、操作简单、不破坏样品属性并且可实现多种重金属元素同时检测等优点,故将XRF与深度卷积神经网络相结合,实现对土壤中重金属Zn元素含量的精确预测。采用箱型图来剔除X射线荧光光谱中的异常数据,采用熵权法结合多元散射校正来对样品盒数据进行校正,采用Savitzky-Golay平滑去噪法以及线性本底法对光谱数据进行预处理,可以有效地解决由外界环境和人为因素产生的噪声及基线漂移等问题。针对卷积神经网络结构的特殊性,将获取的一维光谱数据向量,采用构建光谱数据矩阵的方式来进行处理,将同一浓度、同一含水率下5组平行光谱数据向量转化为二维光谱信息矩阵,以该矩阵作为深度卷积神经网络预测模型的输入,以适应卷积层的操作要求,利用深度卷积神经网络特殊的结构模式,能有效提取土壤光谱数据特征,提高了深度卷积神经网络预测模型的学习能力,降低模型的训练难度。深度卷积神经网络预测模型采用3层卷积层搭建,使用ReLU激活函数激活,采用最大池化方式,减少数据的维度,增加Dropout层,防止过拟合,使用ADAM优化器对预测模型进行优化。实验以平均相对误差(mean relative error, MRE)、损失函数(LOSS)、平均绝对误差(mean absolute error, MAE)确定了模型的最优学习率为10-3以及最优迭代次数为3000,并将深度卷积神经网络预测模型与BP预测模型、ELM预测模型、PLS预测模型进行对比,以均方误差(mean square error, MSE)、均方根误差(root mean square error, RMSE)、以及拟合系数R2来分析比较预测模型的好坏,结果表明,基于深度卷积神经网络预测模型在对土壤中重金属Zn元素含量预测方面优于BP,ELM,PLS三种预测模型,提高了预测精度。     

基于LM-BP神经网络的气阀故障诊断方法

提出一种基于LM（Levenberg-Marquardt）算法优化的 BP (Back Propagation)神经网络的多级往复式压缩机压缩机气阀故障诊断方法。以6M25-185/314氢氮气压缩机的 6级压差和6级温差作为网络的输入向量,建立可对往复式压缩机一至六级气阀故障进行在线监测及故障诊断的LM-BP神经网络模型。以100组故障数据作为网络训练样本,30组数据作为网络检测样本进行故障诊断,结果表明,LM-BP神经网络相比于变梯度BP神经网络和RBF神经网络诊断更快速稳定且准确率达到96%以上。利用Matlab软件平台建立的LM-BP 神经网络故障诊断模型,模型简单便于在工程实际中应用。     

深度卷积网络的多品种多厂商药品近红外光谱分类

近红外光谱（NIR）分析具有分析高效、样品无损、环境无污染以及可现场检测等优点,特别适合药品的快速建模分析。但NIR存在吸收强度弱以及谱带重叠等缺点,需要建立稳健可靠的化学计量学模型对其进行分析。深度卷积神经网络是深度学习方法中一个重要分支,它通过逐层抽取数据特征并进行组合、转换,形成更高层的语义特征,具有极强的建模能力,广泛应用于计算机视觉、语音识别等领域,而在药品NIR分析方面尚未见报道。基于深度卷积网络模型,对药品NIR多分类建模进行研究。针对药品NIR数据的特点,设计若干个面向多品种、多厂商药品NIR分类的一维深度卷积网络模型。模型中卷积层和池化层交叠排列用于逐层抽取NIR数据特征,输出层连接softmax分类器,对药品NIR数据进行分类概率预测。在输出层之前采用全局最大池化层,将特征图进行整体池化,形成一个特征点,用于解决全连接层存在的限制输入维度大小,参数过多的问题。同时,在网络模型中引入批处理操作和dropout机制,以防止梯度消失和减小网络过拟合的风险。在网络模型的设计过程中,通过设计不同的卷积网络层数以及不同的卷积核尺寸大小,分析其对建模效果的影响,同时分析五种经典数据预处理方法对NIR分析的影响。以我国7个厂商生产的头孢克肟片和11个厂商生产的苯妥英钠片样本NIR为实验对象, 建立药品的多品种、多厂商分类模型,该模型在二分类、多分类实验中取得了良好的分类效果。在十八分类实验中,当训练集与测试集比例为7∶3时,分类准确率为99.37±0.45,比SVM, BP, AE和ELM算法取得更优的分类性能。同时,深度卷积神经网络模型推理速度较快,优于SVM和ELM算法,但训练速度慢于二者。大量实验结果表明,深度卷积神经网络可对多品种、多厂商药品NIR数据准确、可靠地判别分类,且模型具有良好的鲁棒性和可扩展性。该方法也可推广到烟草、石化等其他领域的NIR数据分类应用中。     

基于混合神经网络和注意力机制的混沌时间序列预测

为提高混沌时间序列的预测精度,提出一种基于混合神经网络和注意力机制的预测模型(Att-CNNLSTM),首先对混沌时间序列进行相空间重构和数据归一化,然后利用卷积神经网络(CNN)对时间序列的重构相空间进行空间特征提取,再将CNN提取的特征和原时间序列组合,用长短期记忆网络(LSTM)根据空间特征提取时间特征,最后通过注意力机制捕获时间序列的关键时空特征,给出最终预测结果.将该模型对Logistic,Lorenz和太阳黑子混沌时间序列进行预测实验,并与未引入注意力机制的CNN-LSTM模型、单一的CNN和LSTM网络模型、以及传统的机器学习算法最小二乘支持向量机(LSSVM)的预测性能进行比较.实验结果显示本文提出的预测模型预测误差低于其他模型,预测精度更高.     

基于卷积神经网络的焊缝缺陷图像分类研究

为有效地对焊缝缺陷进行分类,从而判断焊接质量的等级,对传统卷积神经网络进行改进,提出一种多尺度压缩激励网络模型（SINet）。将4组两两串联的3×3卷积模块与Inception模块、压缩激励模块（SE block）相结合。通过多尺度压缩激励模块（SI module）将卷积层中的特征进行多尺度融合和特征重标定以提高分类准确率,并用全局平均池化层代替全连接层减少模型参数。此外考虑到焊接缺陷数量不平衡对准确率的影响,采用深度卷积对抗生成网络（DCGAN）进行数据集的平衡处理,并在该数据集上验证模型的有效性。与传统卷积神经网络相比,该模型具有良好的性能,在测试集上准确率达到96.77%,同时模型的参数个数也明显减少。结果表明该方法对焊缝缺陷图像能进行有效地分类。     

基于极化因子神经网络的火电厂制粉系统故障诊断技术

制粉系统是火电厂的主要设备,其安全稳定运行对发电企业的经济生产具有十分重要的意义。针对制粉系统的运行特性和故障分析,提出了基于极化因子神经网络的火电厂制粉系统故障诊断方法,该方法将故障征兆相应的过程变量作为输入,将制粉系统故障类型作为输出,通过训练神经网络建立其系统故障诊断模型,其中训练过程中采用极化因子来自动调整神经网络的收敛速度,从而在满足误差目标的前提下,防止其陷入局部极小。选取实际火电厂制粉系统3个典型故障及其相对应的9个故障征兆参数进行了实验。结果表明,该方法具有良好的收敛性,完全可以满足火电厂制粉系统现场故障诊断的要求。     

基于拉曼光谱和DCGAN数据增强的珍珠粉掺伪检测研究

珍珠粉和珍珠层粉化学成分相似,但是珍珠层粉的药用价值远低于珍珠粉,并且珍珠层粉制备容易,成本底,常被不法商家用于冒充或掺入珍珠粉中流入市场,谋取利益.因此,对珍珠粉掺伪鉴别和纯度检测具有重要的意义.采用激光拉曼光谱结合深度学习研究珍珠粉掺伪快速鉴别和纯度分析.将纯珍珠粉和珍珠层粉按一定比例混合,制成珍珠粉质量百分数分别...     

Source Ranging Using Ensemble Convolutional Networks in the Direct Zone of Deep Water

Using deep convolutional neural networks as primary learners and a deep neural network as meta-learner, source ranging is solved as a regression problem with the ensemble learning method. Simulated acoustic data from the acoustic propagation model are used as the training data. Real data from an experiment in the South China Sea are used as the test data to demonstrate the performance. The results indicate that in the direct zone of deep water, signals received by a very deep receiver can be used to estimate the range of underwater sound source.Within 30 km, the mean absolute error of the range predictions is 1.0 km and the mean absolute percentage error is 7.9%.     

基于信息融合的模拟电路故障的特征提取与融合方法

在模拟电路故障诊断中,故障特征的提取是一个非常重要的环节,其提取结果的好坏将直接影响最终的诊断正确率。对现有文献研究发现,每种特征提取方法单独使用时都有一定的局限性,为了能够更加充分的提取模拟电路故障特征,提出了小波包分析与主元分析并行应用的方法,并将两种方法提取的特征向量依据不同规则进行了三种类型的融合,方便对比实验。为获取最优小波特征,提出了特征偏离度,并以此为标准选择最优小波基。最后,通过设计一种改进的神经网络分类器模型,将融合后的三种特征向量送入其中进行仿真验证,得出最终诊断结果。结果表明,该方法能够有效克服单一特征提取方法提取不充分的缺点,提高故障诊断的正确率,并且融合因子 适中时诊断正确率最高。     

基于AdaBoost与GABP的模拟电路软故障诊断方法

针对容差模拟电路软故障诊断精度较低的问题,提出了一种基于AdaBoost与GABP的组合分类器诊断方法;首先,在Pspice中对故障模式进行Monte-Carlo分析,并利用波形有效点提取法提取故障特征,在此基础上,做归一化处理构建神经网络的原始样本;其次,利用GA算法与L-M算法组合优化BP网络构建GABP分类器;最后,利用AdaBoost算法对GABP单分类器进行迭代提升,构建AdaBoost-GABP组合分类器;诊断实例的结果表明,该方法比传统的单分类器诊断方法具有更高的诊断精度、更低的绝对误差,能够克服单分类器容易陷入局部最优,诊断结论不可信的缺陷。     

Fusion Domain-Adaptation CNN Driven by Images and Vibration Signals for Fault Diagnosis of Gearbox Cross-Working Conditions

The vibration signal of gearboxes contains abundant fault information, which can be used for condition monitoring. However, vibration signal is ineffective for some non-structural failures. In order to resolve this dilemma, infrared thermal images are introduced to combine with vibration signals via fusion domain-adaptation convolutional neural network (FDACNN), which can diagnose both structural and non-structural failures under various working conditions. First, the measured raw signals are converted into frequency and squared envelope spectrum to characterize the health states of the gearbox. Second, the sequences of the frequency and squared envelope spectrum are arranged into two-dimensional format, which are combined with infrared thermal images to form fusion data. Finally, the adversarial network is introduced to realize the state recognition of structural and non-structural faults in the unlabeled target domain. An experiment of gearbox test rigs was used for effectiveness validation by measuring both vibration and infrared thermal images. The results suggest that the proposed FDACNN method performs best in cross-domain fault diagnosis of gearboxes via multi-source heterogeneous data compared with the other four methods.     

基于BP神经网络的变速箱故障诊断方法研究

针对变速箱的工作时间不能真实反映实际健康状况的问题,通过提取变速箱的振动信号作为状态参数,建立了基于BP神经网络的变速箱故障诊断模型。该模型首先提取振动信号中对故障反映灵敏的成分作为特征值,获得BP神经网络的训练数据,并通过对比确定最优的隐含层节点数,确定BP神经网络的结构参数。模型训练结束后,以验证数据为例进行故障诊断研究,并对诊断结果进行评估。评估结果表明,该模型准确度高,具有较好的应用和推广价值。     

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.     

基于邻域粗糙集和并行神经网络的故障诊断

针对目前使用神经网络诊断故障时出现的输入向量选择困难、网络结构复杂、对并发故障诊断效果不好等问题,提出了基于邻域粗糙集和并行神经网络的故障诊断方法。先利用邻域粗糙集对初始征兆进行约简,留下有价值的征兆作为神经网络的输入向量,然后针对每种故障类型设计一个神经网络。用多个训练好的神经网络来并行诊断故障,综合每个神经网络的结果给出最终的诊断结论。用转子实验台的实验数据对这种故障诊断方法进行验证,结果显示该方法能优化神经网络结构,且神经网络具有训练速度快、诊断正确率高的特点。     

深度学习在超声检测缺陷识别中的应用与发展*

深度学习（Deep Learning）是目前最强大的机器学习算法之一,其中卷积神经网络（Convolutional Neural Network, CNN）模型具有自动学习特征的能力,在图像处理领域较其他深度学习模型有较大的性能优势。本文先简述了深度学习的发展史,然后综述了深度学习在超声检测缺陷识别中的应用与发展,从早期浅层神经网络到现在深度学习的应用现状,并借鉴医学影像识别和射线图像识别领域的方法,分析了卷积神经网络对超声图像缺陷识别的适用性。最后,探讨归纳了目前在超声检测图像识别中使用CNN存在的一些问题,及其主要应对策略的研究方向。     

ECG Signal Classification Using Deep Learning Techniques Based on the PTB-XL Dataset

The analysis and processing of ECG signals are a key approach in the diagnosis of cardiovascular diseases. The main field of work in this area is classification, which is increasingly supported by machine learning-based algorithms. In this work, a deep neural network was developed for the automatic classification of primary ECG signals. The research was carried out on the data contained in a PTB-XL database. Three neural network architectures were proposed: the first based on the convolutional network, the second on SincNet, and the third on the convolutional network, but with additional entropy-based features. The dataset was divided into training, validation, and test sets in proportions of 70%, 15%, and 15%, respectively. The studies were conducted for 2, 5, and 20 classes of disease entities. The convolutional network with entropy features obtained the best classification result. The convolutional network without entropy-based features obtained a slightly less successful result, but had the highest computational efficiency, due to the significantly lower number of neurons.     

Comparisons of MFDFA,EMD and WT by Neural Network,Mahalanobis Distance and SVM in Fault Diagnosis of Gearboxes

A method for gearbox fault diagnosis consists of feature extraction and fault identification. Many methods for feature extraction have been devised for exposing nature of vibration data of a defective gearbox. In addition, features extracted from gearbox vibration data are identified by various classifiers. However, existing literatures leave much to be desired in assessing performance of different combinatorial methods for gearbox fault diagnosis. To this end, this paper evaluated performance of several typical combinatorial methods for gearbox fault diagnosis by associating each of multifractal detrended fluctuation analysis (MFDFA), empirical mode decomposition (EMD) and wavelet transform (WT) with each of neural network (NN), Mahalanobis distance decision rules (MDDR) and support vector machine (SVM). Following this, performance of different combinatorial methods was compared using a group of gearbox vibration data containing slightly different fault patterns. The results indicate that MFDFA performs better in feature extraction of gearbox vibration data and SVM does the same in fault identification. Naturally, the method associating MFDFA with SVM shows huge potential for fault diagnosis of gearboxes. As a result, this paper can provide some useful information on construction of a method for gearbox fault diagnosis.