Application of Improved Deep Auto-Encoder Network in Rolling Bearing Fault Diagnosis

Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive Particle Swarm Optimization (CAPSO) was proposed. On the basis of analyzing CAPSO and DAEN, the CAPSO-DAEN fault diagnosis model is built. The model uses the randomness and stability of CAPSO algorithm to optimize the connection weight of DAEN, to reduce the constraints on the weights and extract fault features adaptively. Finally, efficient and accurate fault diagnosis can be implemented with the Softmax classifier. The results of test show that the proposed method has higher diagnostic accuracy and more stable diagnosis results than those based on the DAEN, Support Vector Machine (SVM) and the Back Propagation algorithm (BP) under appropriate parameters.

Application of deep autoencoder model for structural condition monitoring

Damage detection in structures is performed via vibra-tion based structural identification. Modal information, such as fre-quencies and mode shapes, are widely used for structural dama-ge detection to indicate the health conditions of civil structures.The deep learning algorithm that works on a multiple layer neuralnetwork model termed as deep autoencoder is proposed to learnthe relationship between the modal information and structural stiff-ness parameters. This is achieved via dimension reduction of themodal information feature and a non-linear regression against thestructural stiffness parameters. Numerical tests on a symmetri-cal steel frame model are conducted to generate the data for thetraining and validation, and to demonstrate the efficiency of theproposed approach for vibration based structural damage detec-tion.

Method of Multi-Mode Sensor Data Fusion with an Adaptive Deep Coupling Convolutional Auto-Encoder

To address the difficulties in fusing multi-mode sensor data for complex industrial machinery, an adaptive deep coupling convolutional auto-encoder (ADCCAE) fusion method was proposed. First, the multi-mode features extracted synchronously by the CCAE were stacked and fed to the multi-channel convolution layers for fusion. Then, the fused data was passed to all connection layers for compression and fed to the Softmax module for classification. Finally, the coupling loss function coefficients and the network parameters were optimized through an adaptive approach using the gray wolf optimization (GWO) algorithm. Experimental comparisons showed that the proposed ADCCAE fusion model was superior to existing models for multi-mode data fusion.

一种融合AutoEncoder与CNN的混合算法用于图像特征提取

深度学习方法在图像的特征提取方面具有优势。针对传统特征提取方法需要先验知识的不足,提出一种自动编码器(Auto Encoder)与卷积神经网络(convolutional neural network,CNN)相结合的深度学习特征提取方法。该方法给Auto Encoder加入快速稀疏性控制,据此对图像训练出基本构件,并初始化CNN的卷积核;同时,给CNN加入了滤波机制,使输出特征保持稀疏性。实验结果表明,在Minist手写数字库和Yale人脸库的识别效果上,提出的特征提取方法均取得了较好的结果,实验进一步通过交叉验证T检验指出,引入滤波机制的特征提取模型优于没有采用滤波机制的模型。

基于深度SSDAE网络的刀具磨损状态识别

针对刀具磨损状态识别过程中采集数据量大、干扰信号复杂且需人为选择特征参数的问题,为提高刀具磨损状态识别模型的鲁棒性与泛化性,提出了一种数据驱动下深度堆叠稀疏降噪自编码(stacking sparse denoising auto-encoder,简称SSDAE)网络的刀具磨损状态识别方法,实现隐藏在数据中深层次的数据特征自动挖掘。首先,将原始振动信号分解为一系列固有模态分量(intrinsic mode function,简称IMF),并采用皮尔逊相关系数法选取了最优固有模态来组合一个新的信号;其次,采用SSDAE网络自适应提取特征后对刀具磨损阶段进行了状态识别,识别精度达到98%;最后,对网络模型进行实验验证,并与最常用的刀具磨损状态识别方法进行了对比。实验结果表明,所提出的方法能够很好地处理非平稳振动信号,对不同刀具磨损阶段状态的识别效果良好,并具有较好的泛化性能和可靠性。

基于AutoEncoder的油气管道控制系统异常状态监测方法

压缩机控制电路的健康状态管理在管道运输中至关重要。通常油气管道压缩机系统部署地点远离城市,环境恶劣,且负荷高、工作时间长,因此故障频发。构建可靠的健康状态检测模型通常需要大量的故障样本,然而在实际数据中,故障样本相对稀缺。采用一种基于自编码器(auto encoder,AE)的单分类方法对油气管道控制系统的异常状态进行辨识。该模型仅需对系统的正常工作状态进行学习,通过编码器可实现特征的自适应提取,从而对数据进行抽象表示,并获得较好的非线性映射能力;当数据分布异常时,系统可区分其与正常信号间的差异,并进行预警。实验部分采用西部输油管道控制系统中实地获取的通信解码信号以及电源信号进行验证,并以单分类支持向量机方法作对比实验,表明了所提出方法的有效性。

Feature Enhanced Stacked Auto Encoder for Diseases Detection in Brain MRI

The detection of brain disease is an essential issue in medical and research areas.Deep learning techniques have shown promising results in detecting and diagnosing brain diseases using magnetic resonance imaging(MRI)images.These techniques involve training neural networks on large datasets of MRI images,allowing the networks to learn patterns and features indicative of different brain diseases.However,several challenges and limitations still need to be addressed further to improve the accuracy and effectiveness of these techniques.This paper implements a Feature Enhanced Stacked Auto Encoder(FESAE)model to detect brain diseases.The standard stack auto encoder’s results are trivial and not robust enough to boost the system’s accuracy.Therefore,the standard Stack Auto Encoder(SAE)is replaced with a Stacked Feature Enhanced Auto Encoder with a feature enhancement function to efficiently and effectively get non-trivial features with less activation energy froman image.The proposed model consists of four stages.First,pre-processing is performed to remove noise,and the greyscale image is converted to Red,Green,and Blue(RGB)to enhance feature details for discriminative feature extraction.Second,feature Extraction is performed to extract significant features for classification using DiscreteWavelet Transform(DWT)and Channelization.Third,classification is performed to classify MRI images into four major classes:Normal,Tumor,Brain Stroke,and Alzheimer’s.Finally,the FESAE model outperforms the state-of-theart,machine learning,and deep learning methods such as Artificial Neural Network(ANN),SAE,Random Forest(RF),and Logistic Regression(LR)by achieving a high accuracy of 98.61% on a dataset of 2000 MRI images.The proposed model has significant potential for assisting radiologists in diagnosing brain diseases more accurately and improving patient outcomes.

Fault Diagnosis for Rolling Bearings with Stacked Denoising Auto-encoder of Information Aggregation

Rolling bearings are important central components in rotating machines, whose fault diagnosis is crucial in condition-based maintenance to reduce the complexity of different kinds of faults. To classify various rolling bearing faults, a prognostic algorithm consisting of four phases was proposed. Since stacked denoising auto-encoder can be filtered, noise of large numbers of mechanical vibration signals was used for deep learning structure to extract the characteristics of the noise. Unsupervised pre-training method, which can greatly simplify the traditional manual extraction approach, was utilized to process the depth of the data automatically. Furthermore, the aggregation layer of stacked denoising auto-encoder(SDA) was proposed to get rid of gradient disappearance in deeper layers of network, mix superficial nodes’ expression with deeper layers, and avoid the insufficient express ability in deeper layers. Principal component analysis(PCA) was adopted to extract different features for classification. According to the experimental data of this method and from the comparison results, the proposed method of rolling bearing fault classification reached 97.02% of correct rate, suggesting a better performance than other algorithms.

基于BiLSTM-DAE的多家族恶意域名检测算法

针对现有恶意域名检测算法对于家族恶意域名检测精度不高和实时性不强的问题,提出一种基于BiLSTM-DAE的恶意域名检测算法。通过利用双向长短时记忆神经网络(Bi-directional Long Short Term Memory,BiLSTM)提取域名字符组合的上下文序列特征,并结合深度自编码网络(Deep Auto-Encoder,DAE)逐层压缩感知提取类内有共性和类间有区分性的强字符构词特征并进行分类。实验结果表明,与当前主流恶意域名检测算法相比,该算法在保持检测开销较小的基础上,具有更高的检测精度。

基于MRSDAE-SOM结合HGRU的滚动轴承RUL预测

基于传统方法预测轴承剩余使用寿命(Residual Useful Life,RUL),步骤繁多,成本昂贵,且模型不具泛化性。现有的基于深度学习(Deep Learning,DL)的预测方法,由于数据量过大,经常导致模型出现过拟合现象,从而使模型精度不高。为了克服以上缺点,提出一种基于MRSDAE-SOM结合HGRU的滚动轴承RUL预测方法。首先,使用无监督式网络流形正则化堆栈去噪自编码器(Manifold Regularization Stack Denoising Auto Encoder,MRSDAE)结合自组织映射(Self-Or-ganizing Mapping,SOM)构建轴承健康因子(Health Indicator,HI)。然后,通过分层门控循环单元(Hierarchical Gated Re-current Unit,HGRU)网络建立预测模型,HGRU网络通过加入多尺度层和密集层,使其具有捕获时序特征且集成不同时间尺度注意力信息的能力。最后,通过实验验证表明,相比于其他基于数据驱动的方法,所提方法构建健康因子使用无监督方式,高效快捷且便于应用;预测模型泛化能力好,并有效防止了过拟合现象,实现了更高的预测精度。

基于VMD与改进DAE人车地震动包络信号识别算法

为解决在野外环境中使用传统模式识别方法对低信噪比(signal-noise rate, SNR)的人车地震动信号进行分类时应用不便,效果不佳的问题,提出了通过基于包络检波、变分模态分解(variational mode decomposition, VMD)和改进的深度自编码器(deep auto-encoder, DAE)的特征提取算法。首先对目标的地震动信号进行希尔伯特变换以获取信号的平滑包络线,然后进行变分模态分解得到本征模函数(intrinsic mode function, IMF)信号,并利用皮尔森相关系数对分解得到的IMF信号进行筛选,之后将相关度较高的分量加权为高信噪比的中间信号,再使用改进的深度自编码器对其进行特征提取,最后使用泛化性能好的随机森林算法充当分类器,从而实现对人车目标的识别和分类。结果表明:所提算法有效缓解了其他传统算法的部分缺陷,综合识别正确率有所提高,且更加方便应用。

城市物流竞争力分析DAE-WMA优化算法

深入分析了城市物流竞争力的研究现状,结合深度学习相关理论,以深层自编码器(Deep Auto Encoder,DAE)标准模型与标准算法为基础,提出了基于Widrow函数的深层自编码器动量更新算法(DAE-WMA)。依据城市物流竞争力分析数据量特点,选取三种UCI数据集,对基于误差函数的标准算法(DAE-ESA)、基于交叉熵的标准算法(DAE-CSA)以及DAE-WMA的模式分类能力进行仿真,仿真结果表明后者的性能优于前两者。依据物流竞争实力与竞争潜力,基于层次分析法(Analytic Hierarchy Process,AHP)通过选取7个评估维度与19个评价指标构建城市物流竞争力指标体系,利用DAE-WMA方法与社会网络分析(Social Network Analysis,SNA)方法,对我国西北五省区13个主要城市的物流竞争力进行聚类分析与实证研究,仿真结果表明DAE-WMA方法相对于SNA方法,对核心节点城市的分类结果更加合理,更有利于对问题的分析。研究结果为确定新丝绸之路经济带沿线城市物流发展策略,促进国内物流业未来的协作与发展奠定了研究基础。

基于SDAE-BP的联合收割机作业故障监测

为了解决联合收割机作业故障的非线性特征信号难以提取的问题,该研究提出了一种基于堆叠去噪自动编码器(Stack Denoising Auto Encoder,SDAE)和BP神经网络(Back Propagation,BP)融合的联合收割机作业故障监测及诊断的方法(SDAE-BP)。以转速传感器采集联合收割机脱粒滚筒转速、籽粒搅龙转速、喂入搅龙转速、杂余搅龙转速、风机转速、输送链耙转速、割刀频率以及逐稿器振动频率,并将采集的数据集作为系统的输入。利用SDAE提取输入信号的深层次特征,并由BP神经网络辨识收割机作业状态,实现联合收割机故障监测。在SDAE-BP模型训练过程中,去噪自动编码器(Denoising Auto Encode,DAE)依次经带有不同分布中心噪声的原始数据进行训练,然后将其堆叠,并通过误差反向传播算法对模型参数进行优化,以提升模型识别故障性能和泛化能力。试验结果表明,对于2018年联合收割机田间试验数据,模型的故障诊断准确率达到99.00%,与SDAE和BP神经网络相比,分别提高了1.5和4.5个百分点。将SDAE-BP故障诊断模型用2019年的试验数据进行更新,并用2018年和2019年试验数据进行测试,结果表明,更新后的模型对2018年试验数据的故障识别准确率为99.25%,对2019年试验数据的故障识别准确率为98.74%,更新后模型在2019试验数据集上的故障识别准确率较未更新模型提高了6.52个百分点。该文所建模型能够准确识别联合收割机的故障类型,且具有较好的鲁棒性,对旋转型机械故障监测及预警具有参考价值。

基于GMM工况辨识和DAE的风机齿轮箱状态监测

针对大型风电机组运行工况多变、数据量大的特点,提出一种将高斯混合模型(GMM)与深度自编码网络(DAE)相结合的风电机组齿轮箱状态监测方法。首先,基于GMM对风电机组运行工况进行辨识;然后,在各个子工况空间下,基于DAE建立正常运行状态下的齿轮箱油池温度模型,得到多工况阈值;最后,对DAE模型的重构误差进行分析,结合多工况阈值构建健康指数,实现风电机组齿轮箱的状态监测。以某台2 MW风电机组为实例进行验证,结果表明,该方法能够提前7天预警齿轮箱油池温度过高的故障;相对于基于DAE状态监测方法,在不影响在线监测时效性的情况下,该文所提方法能够提前约8 h预警潜在故障。

基于稀疏理论的DAE在公路事故伤亡预测应用

准确实现公路事故伤亡人数预测,对于把握我国未来交通安全形势、实现运输系统优化具有重要意义。将基于稀疏理论的深度自动编码器(Deep Auto-encoder)引入公路事故伤亡人数预测,利用公路事故伤亡人数2000—2015年历史数据构建伤亡人数预测模型,得到死亡及受伤人数平均误差率分别为1.69%、1.53%;采用伤亡人数的影响指标汽车保有量、国内生产总值、公路总里程、人均道路面积的同时段历史数据构建预测模型,得到死伤人数平均误差率分别为1.76%、2.13%;对比发现将DAE运用到公路事故伤亡人数预测精度较高,且采用伤亡人数时间序列数据较影响指标预测精度更高,故使用前者对2016—2020年数据进行预测,得出未来我国公路事故死亡人数将在一定时间内保持平稳,而受伤人数将会明显下降。

基于SDAE_SVDD的通信辐射源个体开集识别方法

针对现有通信辐射源个体识别研究在遇到开集问题时识别性能不高的问题,提出了一种基于堆栈去噪自编码器和支持向量描述(Support Vector Data Description,SVDD)的开集识别方法。该方法通过堆栈去噪自编码器实现降噪和特征压缩提取,将特征输入SVDD进行通信辐射源个体开集识别实验。结果表明,在不同开放度下,该方法可以将未知通信辐射源个体和已知通信辐射源个体以高准确率区分出来,进而将开集识别转为闭集识别。同时,对已知通信辐射源个体识别有很好的识别准确率和抗噪声能力。

基于WRF数值模式的SDAE-SVR风速预测模型研究

风速预测是风力预报中的核心与基础,采用天气研究和预报(Weather Research and Forecasting,WRF)模式进行风力预报往往存在风速预测误差较大的问题.为了提高风速预测精度,提出了一种基于深度学习和支持向量回归(Support Vector Regression,SVR)相结合的风速预测模型.该模型以WRF模式预报输出的多种气象变量为基础,结合气象自动观测站传感器的实测风速,引入堆栈降噪自动编码(Stacked De-noising Auto-Encoder,SDAE)深度网络来学习样本数据中隐含的深度特征,然后将该深度网络最后一层输出的深度特征置入回归器SVR中,利用SVR良好的回归预测性能对WRF模式预报的未来1 h风速进行预测订正.结果表明:所建立的SDAE-SVR风速预测模型具有较高的风速预测精度,在对典型日的WRF模式预报未来1 h风速的预测订正中,其平均百分比误差与均方根误差仅为8.28%与0.8066m·s^-1.

基于改进的DAEN在TE过程故障诊断中的应用研究

现代化工生产过程中故障情况十分复杂,具有非线性、多种类、少标签问题,传统方法很难建立准确的诊断模型。基于深度自编码网络(DAEN),提出了一种新型智能故障诊断方法,并且添加Softmax分类器,构建了深度自编码网络诊断模型。该模型采取稀疏理论进行了改进,解决故障数据少,与正常数据不平衡问题。并且所提方法采取大量无标签样本作为训练集,进行预训练,优化模型参数,并以少量有标签样本作为测试集,进行微调。通过田纳西-伊斯曼(TE)过程仿真数据实验结果表明,相比较支持向量机(SVM)、K最近邻(KNN)等学习方法,DAEN与Softmax回归结合,得到更高的故障诊断正确率;而相比传统的DAEN诊断方法、以及基于反向传播神经网络(BPNN)的传统机器学习故障诊断方法,本文改进的DAEN诊断方法诊断精度得到明显提高。

Fault diagnosis for distillation process based on CNN–DAE

Distillation is the most widely used operation for liquid mixture separation in the chemical industry. It is of great importance to detect and diagnose faults in distillation process. Due to the strong feedback and coupling of processes in a distillation column, it is difficult to use deep auto-encoders(DAEs) alone to achieve good results in detecting and diagnosing faults, in terms of accuracy and efficiency. This paper proposes a hybrid fault-diagnosis model based on convolutional neural networks(CNNs) and DAEs, by integrating the powerful capability of CNN in feature extraction and of DAE in classification. A case study was carried out with the distillation process of depropanization. It is shown that the proposed hybrid model is of good performance compared to other models, in terms of the accuracy of fault detection in such a process. Also, with the increase of structural layers of the CNN–DAE model, the diagnostic accuracy will be improved, with an optimal accuracy of 92.2%.

Bridge the Gap Between Full-Reference and No-Reference:A Totally Full-Reference Induced Blind Image Quality Assessment via Deep Neural Networks

Blind image quality assessment(BIQA)is of fundamental importance in low-level computer vision community.Increasing interest has been drawn in exploiting deep neural networks for BIQA.Despite of the notable success achieved,there is a broad consensus that training deep convolutional neural networks(DCNN)heavily relies on massive annotated data.Unfortunately,BIQA is typically a small sample problem,resulting the generalization ability of BIQA severely restricted.In order to improve the accuracy and generalization ability of BIQA metrics,this work proposed a totally opinion-unaware BIQA in which no subjective annotations are involved in the training stage.Multiple full-reference image quality assessment(FR-IQA)metrics are employed to label the distorted image as a substitution of subjective quality annotation.A deep neural network(DNN)is trained to blindly predict the multiple FR-IQA score in absence of corresponding pristine image.In the end,a selfsupervised FR-IQA score aggregator implemented by adversarial auto-encoder pools the predictions of multiple FR-IQA scores into the final quality predicting score.Even though none of subjective scores are involved in the training stage,experimental results indicate that our proposed full reference induced BIQA framework is as competitive as state-of-the-art BIQA metrics.