The fault diagnosis of hydraulic servo system attracts more attention in complex system prognostics and health management. As the precondition of most fault diagnosis methods, feature extraction could efficiently draw...
详细信息
ISBN:
(纸本)9781728176871
The fault diagnosis of hydraulic servo system attracts more attention in complex system prognostics and health management. As the precondition of most fault diagnosis methods, feature extraction could efficiently draw information from the initial data and supply more evidence to the following results. However, traditional time-frequency analysis largely depend on artificial selection and optimization, which are generally limited by the quality of input data and working environment. Thus this paper proposes a stacked deep learning based model to represent robust feature information in terms of the advantage of cognitive computing and pattern classification theory, which is shown to be suitable for certain applications with inevitable ambient noise and working condition fluctuations. To effectively realize feature reconstruction, a stacked denoising autoencoder (SDA) in which multiple encoders are established and trained is used. The employed deep neural network is trained layer by layer to extract high-level features, where the sparsity representation is applied to map the original inputs to better high-level features. Considering better robustness of the learnt features to avoid external interferences, the original input neural parameters of each autoencoder are denoised by randomly assigning some units to be zero. The modified denoisingautoencoders are then stacked to initialize the deep hierarchical architecture instead of the original. High-level feature representations of the monitoring data samples are obtained based on unsupervised self-learning, and are set as the inputs of a top fault pattern classifier for final training, followed by a fine-tuning process. Validation data arc collected to facilitate the comparison and evaluation of the fault diagnosis results of the SDA models, of which the denoising proportion is different for each. Experiments show an obvious advantage of the SDA model based on the self-learning of the robustness features for fault patte
In semiconductor manufacturing systems, defects on wafer maps tend to cluster and then these spatial patterns provide important process information for helping operators in finding out root-causes of abnormal processe...
详细信息
In semiconductor manufacturing systems, defects on wafer maps tend to cluster and then these spatial patterns provide important process information for helping operators in finding out root-causes of abnormal processes. Promptly recognizing wafer map defects is an effective way to increase manufacturing process stability and then to improve yields. Deep learning has been widely applied and obtained many successes in image and visual analysis. This paper proposes an effective deep learning method, enhanced stacked denoising autoencoder (ESDAE) with manifold regularization for wafer map pattern recognition (WMPR) in manufacturing processes. This study will concentrate on developing a deep learning model to learn effective discriminative features from wafer maps through a deep network architecture for WMPR improvement. An indication based on ESDAE is developed for detecting map defects online. An ESDAE-based classifier is finally developed to implement recognition of wafer map defects. The most motivation for developing deep learning and manifold regularization techniques is to achieve higher accuracy and applicability than that of some regular recognizers. The effectiveness of the proposed method has been demonstrated by experimental results from a real-world wafer map dataset (WM-811K).
In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used me...
详细信息
In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.
Bearing fault diagnosis is an inevitable process in the maintenance of rotary machines. Multiple combined defects in bearings are more difficult to detect because of the complexity in components of acquired acoustic e...
详细信息
ISBN:
(纸本)9789811303418;9789811303401
Bearing fault diagnosis is an inevitable process in the maintenance of rotary machines. Multiple combined defects in bearings are more difficult to detect because of the complexity in components of acquired acoustic emission signals. To address this issue, this paper proposes a deep learning method that can effectively detect the combined defects in bearings. The proposed deep neural network (DNN) is based on the stacked denoising autoencoder (SDAE). In this study, the proposed method trains single faulty data while it efficiently classifies multiple combined faults. Experimental results indicate that the proposed method achieves an average accuracy of 91% although it only has single mode fault information.
Web-based anomalies remains a serious security threat on the Internet. This paper proposes the use of Sum Rule and Xgboost to combine the outputs related to various stacked denoising autoencoders (SDAEs) in order to d...
详细信息
ISBN:
(纸本)9781450372459
Web-based anomalies remains a serious security threat on the Internet. This paper proposes the use of Sum Rule and Xgboost to combine the outputs related to various stacked denoising autoencoders (SDAEs) in order to detect abnormal HTTP queries. Sum Rule and Xgboost inherit the distinct advantage of SDAE that does not require handcrafted features to be extracted. Furthermore, these methods can cope with the changing web vulnerabilities, where malicious code is added into different parts of the request header and body. Experiments were carried out on the DVWA dataset and the dataset that obtained from a real-world application. Sum Rule and Xgboost demonstrate to achieve higher F1-score as compared to the state-of-the-art Regularized Deep autoencoders, Isolation Forest, C4.5 decision tree and Long Short-term Memory network.
Planetary gear train plays a critical role in the helicopter transmission system. Fault diagnosis of the planetary gear train has long been a research topic in the health monitoring and maintenance of the helicopter. ...
详细信息
ISBN:
(纸本)9781728108612
Planetary gear train plays a critical role in the helicopter transmission system. Fault diagnosis of the planetary gear train has long been a research topic in the health monitoring and maintenance of the helicopter. However, due to the intricate kinematics and severe operating conditions, the vibration signals of the planetary gear train are highly complex, dominated by various coupling disturbances and ambient noise. Aiming to address these challenges, an integrated health state identification scheme (IHSIS) is proposed for fault diagnosis of helicopter planetary gear train. Firstly, IHSIS utilizes multiple sensors to collecting vibration signals for sufficient fault information under multi-mode faults and fluctuating working conditions. Secondly, stackeddenoising automatic encoder (SDAE) is adopted to explore deep features from frequency spectrum of each individual sensor. Finally, deep features derived from measured signals of all sensors are fused together and input to a softmax classifier for fault diagnosis. The superiority of IHSIS is validated by analyzing results of a few comparative experiments conducted on a helicopter main-rotor testbed with intentionally created localized gear faults of a planetary gear train under different noise levels.
Deep learning has attracted much attention because of its ability to extract complex features automatically. Unsupervised pre-training plays an important role in the process of deep learning, but the monitoring inform...
详细信息
ISBN:
(纸本)9789811089718;9789811089701
Deep learning has attracted much attention because of its ability to extract complex features automatically. Unsupervised pre-training plays an important role in the process of deep learning, but the monitoring information provided by the sample of labeling is still very important for feature extraction. When the regression forecasting problem with a small amount of data is processed, the advantage of unsupervised learning is not obvious. In this paper, the pre-training phase of the stacked denoising autoencoder was changed from unsupervised learning to supervised learning, which can improve the accuracy of the small sample prediction problem. Through experiments on UCI regression datasets, the results show that the improved stacked denoising autoencoder is better than the traditional stacked denoising autoencoder.
This paper proposed an intelligent algorithm based approach for fault location in a high voltage direct current (HVDC) transmission system. To obtain post-fault signals, the point-to-point HVDC transmission lines, inc...
详细信息
ISBN:
(纸本)9781728116754
This paper proposed an intelligent algorithm based approach for fault location in a high voltage direct current (HVDC) transmission system. To obtain post-fault signals, the point-to-point HVDC transmission lines, including overhead lines and cables, are modeled on PSCAD/EMTDC. The data set is split into two parts used for training and testing, separately. The proposed method uses stacked denoising autoencoder (SDAE), which takes the raw training data as the input of network and can directly obtain fault locations. SDAE with unsupervised learning is utilized to extract representative features automatically from raw data in pre-training. Then labeled data is applied to network for fine-tuning in a supervised manner. The testing data is used for the evaluation of the proposed method. The simulation results indicate that the SDAE based method performs well in fault location and has robustness against noises, ground resistances, and system parameters.
Most deep learning models such as stackedautoencoder (SAE) and stacked denoising autoencoder (SDAE) are used for fault diagnosis with a data label. These models are applied to extract the useful features with several...
详细信息
Most deep learning models such as stackedautoencoder (SAE) and stacked denoising autoencoder (SDAE) are used for fault diagnosis with a data label. These models are applied to extract the useful features with several hidden layers, then a classifier is used to complete the fault diagnosis. However, these fault diagnosis classification methods are only suitable for tagged datasets. Actually, many datasets are untagged in practical engineering. The clustering method can classify data without a label. Therefore, a method based on the SDAE and Gath-Geva (GG) clustering algorithm for roller bearing fault diagnosis without a data label is proposed in this study. First, SDAE is selected to extract the useful feature and reduce the dimension of the vibration signal to two or three dimensions direct without principal component analysis (PCA) of the final hidden layer. Then GG is deployed to identify the different faults. To demonstrate that the feature extraction performance of the SDAE is better than that of the SAE and EEMD with the FE model, the PCA is selected to reduce the dimension of eigenvectors obtained from several previously hidden layers, except for the final hidden layer. Compared with SAE and ensemble empirical mode decomposition (EEMD)-fuzzy entropy (FE) models, the results show that as the number of the hidden layers increases, all the fault samples under different conditions are separated better by using SDAE rather than those feature extraction models mentioned. In addition, three evaluation indicators such as PC, CE, and classification accuracy are used to assess the performance of the method presented. Finally, the results show that the clustering effect of the method presented, and its classification accuracy are superior to those of the other combination models, including the SAE-fuzzy C-means (FCM)/Gustafson-Kessel (GK)/GG and EEMD-fuzzy entropy FE-PCA-FCM/GK/GG. (C) 2018 Elsevier B.V. All rights reserved.
Modern industrial processes have become increasingly complicated, consequently, the nonlinearity of data collected from these systems continues to increase. However, the feature extraction methods of existing process ...
详细信息
Modern industrial processes have become increasingly complicated, consequently, the nonlinearity of data collected from these systems continues to increase. However, the feature extraction methods of existing process monitoring are not capable of extracting crucial features from these highly nonlinear data, which affects the performance of monitoring. In this paper, a novel nonlinear process monitoring method based on stacked denoising autoencoder (SDAE) and k-nearest neighbor (kNN) rule is proposed. Specifically, stacked denoising autoencoder is utilized to model the nonlinear process data and automatically extract crucial features. The original nonlinear space is then mapped to the feature space and the residual space via SDAE. Two new statistics in the above spaces are constructed by introducing the kNN rule with their corresponding control limits determined by kernel density estimation. Case studies on a nonlinear numerical system and the Tennessee Eastman benchmark process verify the effectiveness of the proposed method. (C) 2018 Elsevier Ltd. All rights reserved.
暂无评论