一种基于深度迁移学习的滚动轴承早期故障在线检测方法

近年来, 深度学习技术已在滚动轴承故障检测和诊断领域取得了成功应用, 但面对不停机情况下的早期故障在线检测问题, 仍存在着早期故障特征表示不充分、误报警率高等不足. 为解决上述问题, 本文从时序异常检测的角度出发, 提出了一种基于深度迁移学习的早期故障在线检测方法. 首先, 提出一种面向多域迁移的深度自编码网络, 通过构建具有改进的最大均值差异正则项和Laplace正则项的损失函数, 在自适应提取不同域数据的公共特征表示同时, 提高正常状态和早期故障状态之间特征的差异性; 基于该特征表示, 提出一种基于时序异常模式的在线检测模型, 利用离线轴承正常状态的排列熵值构建报警阈值, 实现在线数据中异常序列的快速匹配, 同时提高在线检测结果的可靠性. 在XJTU-SY数据集上的实验结果表明, 与现有代表性早期故障检测方法相比, 本文方法具有更好的检测实时性和更低的误报警数.     

面向轴承早期故障检测的多尺度残差注意力深度领域适配模型

针对由工作环境和设备状况的差异引起的轴承早期故障检测模型可靠性差、误报警率高的问题，根据早期故障检测的特点和需求，提出一种多尺度注意力深度领域适配模型。首先，将监测信号处理成由原始信号、希尔伯特-黄变换边际谱、频谱组成的三通道数据；然后，通过在残差注意力模块中增加不同尺寸的滤波器以提取多尺度深度特征，使用卷积-反卷积操作来重构输入信息从而获得注意力信息，并且将注意力信息与多尺度特征融合构建了一种多尺度残差注意力模块，用于提取对早期故障表征能力更强的注意力特征；其次，在所提取到的注意力特征基础上，构建基于交叉熵和最大均值差异（MMD）正则化约束的损失函数来实现领域适配；最后，采用随机梯度下降算法进行网络参数优化，构建端到端的早期故障检测模型。在IEEE PHM-2012数据挑战赛数据集上的实验结果表明，与8种代表性的早期故障检测和诊断方法以及迁移学习算法相比，所提方法能够在不延迟报警时间点的前提下，分别比8种方法的平均误报警率降低了62.7%和61.3%，有效提高了早期故障检测的鲁棒性。     

面向轴承早期故障检测的多尺度残差注意力深度领域适配模型

针对由工作环境和设备状况的差异引起的轴承早期故障检测模型可靠性差、误报警率高的问题,根据早期故障检测的特点和需求,提出一种多尺度注意力深度领域适配模型。首先,将监测信号处理成由原始信号、希尔伯特-黄变换边际谱、频谱组成的三通道数据;然后,通过在残差注意力模块中增加不同尺寸的滤波器以提取多尺度深度特征,使用卷积-反卷积操作来重构输入信息从而获得注意力信息,并且将注意力信息与多尺度特征融合构建了一种多尺度残差注意力模块,用于提取对早期故障表征能力更强的注意力特征;其次,在所提取到的注意力特征基础上,构建基于交叉熵和最大均值差异（MMD）正则化约束的损失函数来实现领域适配;最后,采用随机梯度下降算法进行网络参数优化,构建端到端的早期故障检测模型。在IEEE PHM-2012数据挑战赛数据集上的实验结果表明,与8种代表性的早期故障检测和诊断方法以及迁移学习算法相比,所提方法能够在不延迟报警时间点的前提下,分别比8种方法的平均误报警率降低了62.7%和61.3%,有效提高了早期故障检测的鲁棒性。     

基于深度学习的故障检测方法

针对传统故障诊断方法中特征提取技术难度大、故障样本获取困难等问题,在深度学习计算框架下提出了一种半监督训练的故障检测方法,利用深度信念网络中的受限波茨曼机堆栈结构实现了数据高层特征的自动提取,结合支持向量数据描述方法实现了异常数据检测,只需利用正常工况的数据样本进行网络训练和模型拟合,无需故障样本数据,也无需人工干预进行信号特征提取,即能实现对故障数据进行的实时检测和判别;经采用标准轴承实验数据的三组故障数据进行验证,故障识别率达到100%,具有很强的工程应用价值。     

基于深度学习的变压器在线故障检测

针对供配电网络中变压器故障检测和预报的不足,提出基于深度学习的变压器故障检测方法,详细介绍了变压器监测数据预处理方法及步骤,给出了深度学习网络的具体结构和学习过程,深度学习结果表明该故障检测方法的有效性和实用性。     

基于深度迁移学习的人体舞蹈姿态检测方法

常规的人体舞蹈姿态检测方法存在多姿态动作检测精度和识别率较低,因此提出基于深度迁移学习的人体舞蹈姿态检测方法。首先,利用Kinect传感器采集人体舞蹈姿态动作三维数据。其次,基于滑动窗口间接分割原理识别动作类别。再次,利用深度迁移学习建立动作识别模型,识别人体舞蹈的特定动作和非特定动作。最后,结合人体关节位置特征,检测人体舞蹈姿态动作中左手、右手、上身及全身4类局部特征信息。实验分析可知,新的方法应用后,舞蹈姿态检测的交并比值较高,显著提升了检测准确性。     

基于集成学习的无监督网络入侵检测方法

目前,网络对抗对入侵检测智能化和自主性的需求不断提高,基于深度学习的方法通过训练和学习来区分复杂攻击模式和行为,但有监督的学习方法需要专家知识和大量人工开销。针对上述问题,文章提出一种基于集成学习的无监督网络入侵检测方法,并使用基于3种不同异常检测理念的深度学习检测器,在3种不同集成逻辑下对各单检测器的检测结果进行检测判定。该方法可以综合分析时间序列数据中不同类型的异常数据,降低无监督异常检测模型由于过度拟合所造成的影响,并以一种高效的在线方式检测可能存在的网络攻击数据流。在KDD CUP 1999和CSE-CICIDS 2018数据集上进行验证,实验结果表明,与其他单一的无监督异常检测模型相比,文章提出的集成方法结合了不同无监督检测模型的优势,适用于对多种网络入侵引起的异常进行检测。     

基于无监督学习的图像风格迁移方法

近年来,深度学习作为机器学习领域的一个分支,已经展现出强大的能力,其中基于卷积神经网络的无监督学习更是逐渐流行,之前有很多关于图像到图像翻译的工作,但都需要成对输入图片数据,这无疑增加了训练数据集获取的难度。笔者旨在实现在缺少成对数据的情况下使用生成对抗网络GAN学习从源数据域Y到目标数据域Y以实现图像到图像的翻译和风格迁移,通过学习映射G:X→Y和一个相反的映射F:Y→X,使它们成对,同时加入一个循环一致性损失函数,以确保F(G(X))≈X(反之亦然),最终实现通过输入一张具有任意风格的源图片进入网络并生成指定风格的图像,实现风格迁移。在缺少成对训练数据的情况下,本文成功实现了horse2zebra数据集和vangogh2photo数据集的风格迁移。     

基于深度迁移学习的恶意代码可视化检测

随着网络技术和人工智能技术的不断发展,恶意代码对网络空间安全的威胁日益增加,对社会经济、国家安全构成严重威胁。恶意程序数量级呈指数增加大大增加了恶意代码分析的工作量,传统的恶意代码检测方式难以应对当下日益复杂的网络空间环境。本文提出了一种面向深度迁移学习的恶意代码可视化检测,基于计算机视觉技术将恶意代码进行可视化操作,并利用深度迁移学习和目标检测技术,对恶意代码相关特征片段进行检测分类。实验结果同样也表明,基于目标检测和计算机视觉技术,进行恶意代码可视化检测分析的方法在检测准确率、检测速度以及识别能力等方面较传统的恶意代码分类方法都表现出了更优异的性能。     

A tensor-based deep learning framework

This paper presents an unsupervised deep learning framework that derives spatio-temporal features for human–robot interaction. The respective models extract high-level features from low-level ones through a hierarchical network, viz. the Hierarchical Temporal Memory (HTM), providing at the same time a solution to the curse of dimensionality in shallow techniques. The presented work incorporates the tensor-based framework within the operation of the nodes and, thus, enhances the feature derivation procedure. This is due to the fact that tensors allow the preservation of the initial data format and their respective correlation and, moreover, attain more compact representations. The computational nodes form spatial and temporal groups by exploiting the multilinear algebra and subsequently express the samples according to those groups in terms of proximity. This generic framework may be applied in a diverse of visual data, while it has been examined on sequences of color and depth images, exhibiting remarkable performance.     

Stability-based system for bearing fault early detection

This paper presents a new and straightforward system for bearing fault detection. The system computes the stability of two vibration signals by using the direct matching points (DMP) of an elastic and non-linear align function. It is able to find discriminant properties in the stability of fault-free and faulty bearing vibration signals from the early and late stages of the fault in critical bearing parts. Because training data constitutes one of the critical challenges in most expert and intelligent systems, one of the novelties of the proposed stability-based system is that it requires neither training nor fine-tuning. A significant impact on the robustness of the system is demonstrated using two publicly available vibration signal databases under several load conditions, with real faults, during multiple machine working states. Experimental results validate the use of the proposed stability-based system for predictive maintenance in bearings.     

A reinforcement ensemble deep transfer learning network for rolling bearing fault diagnosis with Multi-source domains

Fault diagnosis with transfer learning has achieved great attention. However, existing methods mostly focused on single-source-single-target sceneries. In some cases, there may exist multiple source domains. Therefore, a reinforcement ensemble deep transfer learning network (REDTLN) is proposed for fault diagnosis with multi-source domains. Firstly, various new kernel maximum mean discrepancies (kMMDs) are used to construct multiple deep transfer learning networks (DTLNs) for single-source-single-target domain adaptation. The differences of kernel functions and source domains can help the DTLNs learn diverse transferable features. Secondly, a new unified metric is designed based on kMMD and diversity measures for unsupervised ensemble learning. Finally, using the unified metric as the reward, a reinforcement learning method is firstly explored to generate an effective combination rule for multi-domain-multi-model reinforcement ensemble. The proposed method is verified with experiment datasets, and the results empirically show its effectiveness and superiority compared with other methods.     

Unsupervised deep learning system for local anomaly event detection in crowded scenes

Multimedia Tools and Applications - Anomaly detection in video surveillance is a significant research subject because of its immense use in real-time applications. These days, open spots like...     

A deep feature enhanced reinforcement learning method for rolling bearing fault diagnosis

Fault diagnosis of rolling bearing is crucial for safety of large rotating machinery. However, in practical engineering, the fault modes of rolling bearings are usually compound faults and contain a large amount of noise, which increases the difficulty of fault diagnosis. Therefore, a deep feature enhanced reinforcement learning method is proposed for the fault diagnosis of rolling bearing. Firstly, to improve robustness, the neural network is modified by the Elu activation function. Secondly, attention model is used to improve the feature enhanced ability and acquire essential global information. Finally, deep Q network is established to accurately diagnosis the fault modes. Sufficient experiments are conducted on the rolling bearing dataset. Test result shows that the proposed method is superior to other intelligent diagnosis methods.     

A multi-view attention-based deep learning system for online deviant content detection

With the exponential growth of user-generated content, policies and guidelines are not always enforced in social media, resulting in the prevalence of deviant content violating policies and guidelines. The adverse effects of deviant content are devastating and far-reaching. However, the detection of deviant content from sparse and imbalanced textual data is challenging, as a large number of stakeholders are involved with different stands and the subtle linguistic cues are highly dependent on complex context. To address this problem, we propose a multi-view attention-based deep learning system, which combines random subspace and binary particle swarm optimization (RS-BPSO) to distill content of interest (candidates) from imbalanced data, and applies the context and view attention mechanisms in convolutional neural network (dubbed as SSCNN) for the extraction of structural and semantic features. We evaluate the proposed approach on a large-scale dataset collected from Facebook, and find that RS-BPSO is able to detect whether the content is associated with marijuana with an accuracy of 87.55%, and SSCNN outperforms baselines with an accuracy of 94.50%.

     

无监督深度学习彩色图像识别方法

针对彩色图像分类识别的重要性,提出了一种结合图像特征数据和深度信任网络(DBN)的彩色图像识别方法。首先,构造符合人类视觉特性的图像色彩数据场;其次,以小波变换描述图像的多尺度特征;最后,通过无监督训练深度信任网络实现对图像的识别。实验结果表明,所提方法与Adaboost、支持向量机(SVM)方法比较,分类准确率分别提高约3.7%和2.8%,可有效提高图像识别效果。     

Unsupervised deep learning approach for network intrusion detection combining convolutional autoencoder and one-class SVM

Applied Intelligence - With the rapid advancement in network technologies, the need for cybersecurity has gained increasing momentum in recent years. As a primary defense mechanism, an intrusion...