Health Indicators (HIs) have been widely used for health state assessments. In many applications, HI with physical meaning is a preferred choice to assist system health management due to its inherent nature of objecti...
详细信息
Health Indicators (HIs) have been widely used for health state assessments. In many applications, HI with physical meaning is a preferred choice to assist system health management due to its inherent nature of objectively and accurately representing the system health state. However, in many cases, the true value of HI with physical meaning is difficult to obtain due to the difficulty in measuring them, which means, the HI is hidden from the user during system operation. It results in difficulty in training HI construction methods. In light of these challenges, we propose a physics-informed autoencoder for HI construction by fusing the physics-based model with deep learning (DL) approaches. In this framework, we redefine the conventional HI construction process with autoencoders into a new paradigm: mapping the sensor readings to a degradation-represented latent space by a DL model and reconstructing the sensor readings by a physics based model. The latent variable, bridging the connection between the encoder and decoder, works as the HI and is meticulously designed with an energy-oriented perspective, thus ensuring its applicability across various systems. Furthermore, a novel training strategy is proposed for this framework to be well-trained. The superiority and effectiveness of the proposed framework are validated on the CALCE battery dataset and electromechanical actuator simulation data. In the two examples, the SOH of batteries and the energy efficiency of electromechanical actuators can both be estimated using the proposed method.
Dealing with missing data in data analysis is inevitable. Although powerful imputation methods that address this problem exist, there is still much room for improvement. In this study, we examined single imputation ba...
详细信息
Dealing with missing data in data analysis is inevitable. Although powerful imputation methods that address this problem exist, there is still much room for improvement. In this study, we examined single imputation based on deep autoencoders, motivated by the apparent success of deep learning to efficiently extract useful dataset features. We have developed a consistent framework for both training and imputation. Moreover, we benchmarked the results against state-of-the-art imputation methods on different data sizes and characteristics. The work was not limited to the one-type variable dataset;we also imputed missing data with multi-type variables, e.g., a combination of binary, categorical, and continuous attributes. To evaluate the imputation methods, we randomly corrupted the complete data, with varying degrees of corruption, and then compared the imputed and original values. In all experiments, the developed autoencoder obtained the smallest error for all ranges of initial data corruption. (C) 2019 Elsevier B.V. All rights reserved.
Fiber -reinforced polymer (FRP) composites have been widely applied in different industrial fields, thereby necessitating the employment of non-destructive testing (NDT) methods to ensure structural integrity and safe...
详细信息
Fiber -reinforced polymer (FRP) composites have been widely applied in different industrial fields, thereby necessitating the employment of non-destructive testing (NDT) methods to ensure structural integrity and safety. Active infrared thermography (AIRT) is a fast and cost-efficient NDT technique for inspecting FRP composites. However, this method is easily affected by factors such as inhomogeneous heating, leading to a low level of visualization of defects. To address this issue, this study proposes a novel method called one-dimensional deep convolutional autoencoder active infrared thermography (1D-DCAE-AIRT) to enhance the visualization of internal defects in FRP composites. This method first preprocesses the thermal image sequence acquired by AIRT inspections. Subsequently, high-level thermal features at the pixel level are extracted from the aforementioned preprocessed thermal image sequence using a designed one-dimensional deep convolutional autoencoder (1DDCAE) model. Finally, the extracted high-level thermal features are employed to generate enhanced visualization results that exhibit improved defect visibility. The results of three kinds of AIRT (eddy current pulsed thermography, flash thermography, and vibrothermography) experiments on FRP composite specimens with artificially introduced defects show that 1D-DCAE-AIRT can effectively enhance the visualization of internal defects. The enhancement effect is better than the conventional techniques of fast Fourier transform (FFT), principal component analysis (PCA), independent component analysis (ICA), and partial least -squares regression (PLSR).
In recent years, attacks on network environments continue to rapidly advance and are increasingly intelligent. Accordingly, it is evident that there are limitations in existing signature-based intrusion detection syst...
详细信息
In recent years, attacks on network environments continue to rapidly advance and are increasingly intelligent. Accordingly, it is evident that there are limitations in existing signature-based intrusion detection systems. In particular, for novel attacks such as Advanced Persistent Threat (APT), signature patterns have problems with poor generalization performance. Furthermore, in a network environment, attack samples are rarely collected compared to normal samples, creating the problem of imbalanced data. Anomaly detection using an autoencoder has been widely studied in this environment, and learning is through semi-supervised learning methods to overcome these problems. This approach is based on the assumption that reconstruction errors for samples that are not used for training will be large, but an autoencoder is often over-generalized and this assumption is often broken. In this paper, we propose a network intrusion detection method using a memory-augmented deep auto-encoder (MemAE) that can solve the over-generalization problem of autoencoders. The MemAE model is trained to reconstruct the input of an abnormal sample that is close to a normal sample, which solves the generalization problem for such abnormal samples. Experiments were conducted on the NSL-KDD, UNSW-NB15, and CICIDS 2017 datasets, and it was confirmed that the proposed method is better than other one-class models.
Predictive and condition-based maintenance is given more and more attention to further optimize the utilization of manufacturing and production equipment. Utilizing acoustic signals for equipment monitoring and condit...
详细信息
Predictive and condition-based maintenance is given more and more attention to further optimize the utilization of manufacturing and production equipment. Utilizing acoustic signals for equipment monitoring and condition-based maintenance has been proven effective in many applications. Many manufacturing and production setups consist of multiple alike machines (e.g. within injection moulding) where it would be beneficial to use the same monitoring setup and configuration on all machines. Based on an industrial application within injection moulding (using five different injection moulds), a methodology is proposed utilizing acoustic signals from injection moulds combined with generative Gaussian or autoencoder modeling. To improve the generalization ability of generative modeling to moulds not seen at training time, a simple yet effective model adaptation is proposed, which only requires a few faultless moulding cycles at runtime/test time. The best results are obtained using the Gaussian model, where area under the curve values close to one are achieved when employing a model adapted to the specific mould at test time to detect abnormal situations like mechanical-defective moulds (loose latch lock) and the need for lubrication. The proposed framework is light in terms of computation and makes the setup implementation practically feasible in a real industrial context with multiple similar machines.
Early detection, early diagnosis and classification of the cancer type facilitates faster disease management of patients. Cervical cancer is fourth most pervasive cancer type which affects life of many people worldwid...
详细信息
Early detection, early diagnosis and classification of the cancer type facilitates faster disease management of patients. Cervical cancer is fourth most pervasive cancer type which affects life of many people worldwide. The intent of this study is to automate cancer diagnosis and classification through deep learning techniques to ensure patients health condition progress timely. For this research, Herlev dataset was utilized which contains 917 benchmarked pap smear cells of cervical with 26 attributes and two target variables for training and testing phase. We have adopted combination of convolutional network with variational autoencoder for data classification. The usage of variational autoencoder reduces the dimensionality of data for further processing with involvement of softmax layer for training. The results have been obtained over 917 cancerous image type pap smear cells, where 70% (642) allocated for training and remaining 30% (275) considered for test data set. The proposed architecture achieved variational accuracy of 99.2% with 2*2 filter size and 99.4% with 3*3 filter size using different epochs. The proposed hybrid variational convolutional autoencoder approach applied first time for cervical cancer diagnosis and performed better than traditional machine learning methods.
Non-destructive testing & evaluation techniques play an essential role in ensuring safety of materials in operation at various industry sectors. Pulse compressed favourable thermal wave imaging is one of the widel...
详细信息
Non-destructive testing & evaluation techniques play an essential role in ensuring safety of materials in operation at various industry sectors. Pulse compressed favourable thermal wave imaging is one of the widely used non-destructive testing techniques due to its excellent noise rejection capabilities. However, the high dimensional thermal imaging data needs to be encoded into lossless compressed form to highlight the hidden defects inside the materials. This paper proposes a novel constrained and regularized autoencoder based thermography approach for sub-surface defect detection in a mild steel specimen. Certain properties such as non-correlation of encoded data, weight orthogonality, and weights with unit norm length have been highlighted which are non-existent in linear autoencoders but are responsible for better defect detection inside the materials inspected by frequency modulated thermal wave imaging. Novel constraints are formulated for autoencoder cost function to incorporate these significant properties. The proposed approach is able to provide better defect detection, in terms of signal to noise ratio of defects, than linear autoencoder as well as traditional principal component thermography approach. Also, non-correlation of encoded data is found to be the most significant factor in achieving better defect detection followed by properties ensuring weight orthogonality and weights with unit norm length.
autoencoder can learn the structure of data adaptively and represent data efficiently. These properties make autoencoder not only suit huge volume and variety of data well but also overcome expensive designing cost an...
详细信息
autoencoder can learn the structure of data adaptively and represent data efficiently. These properties make autoencoder not only suit huge volume and variety of data well but also overcome expensive designing cost and poor generalization. Moreover, using autoencoder in deep learning to implement feature extraction could draw better classification accuracy. However, there exist poor robustness and overfitting problems when utilizing autoencoder. In order to extract useful features, meanwhile improve robustness and overcome overfitting, we studied denoising sparse autoencoder through adding corrupting operation and sparsity constraint to traditional autoencoder. The results suggest that different autoencoders mentioned in this paper have some close relation and the model we researched can extract interesting features which can reconstruct original data well. In addition, all results show a promising approach to utilizing the proposed autoencoder to build deep models.
An increasing number of deep autoencoder-based algorithms for intelligent condition monitoring and anomaly detection have been reported in recent years to improve wind turbine reliability. However, most existing studi...
详细信息
An increasing number of deep autoencoder-based algorithms for intelligent condition monitoring and anomaly detection have been reported in recent years to improve wind turbine reliability. However, most existing studies have only focused on the precise modeling of normal data in an unsupervised manner;few studies have utilized the information of fault instances in the learning process, which results in suboptimal detection performance and low robustness. To this end, we first developed a deep autoencoder enhanced by fault instances, that is, a triplet-convolutional deep autoencoder (triplet-Conv DAE), jointly integrating a convolutional autoencoder and deep metric learning. Aided by fault instances, triplet-Conv DAE can not only capture normal operation data patterns but also acquire discriminative deep embedding features. Moreover, to overcome the difficulty of scarce fault instances, we adopted an improved generative adversarial network-based data augmentation method to generate high-quality synthetic fault instances. Finally, we validated the performance of the proposed anomaly detection method using a multitude of performance measures. The experimental results show that our method is superior to three other state-of-the-art methods. In addition, the proposed augmentation method can efficiently improve the performance of the triplet-Conv DAE when fault instances are insufficient. & COPY;2023 ISA. Published by Elsevier Ltd. All rights reserved.
The classification of hyperspectral images (HSI) into categories that correlate to various land cover sorts such as water bodies, agriculture and urban areas, has gained significant attention in research due to its wi...
详细信息
The classification of hyperspectral images (HSI) into categories that correlate to various land cover sorts such as water bodies, agriculture and urban areas, has gained significant attention in research due to its wide range of applications in fields, such as remote sensing, computer vision, and more. Supervised deep learning networks have demonstrated exceptional performance in HSI classification, capitalizing on their capacity for end-to-end optimization and leveraging their strong potential for nonlinear modeling. However, labelling HSIs, on the other hand, necessitates extensive domain knowledge and is a time-consuming and labour-intensive exercise. To address this issue, the proposed work introduces a novel semi-supervised network constructed with an autoencoder, Siamese action, and attention layers that achieves excellent classification accuracy with labelled limited samples. The proposed convolutional autoencoder is trained using the mass amount of unlabelled data to learn the refinement representation referred to as 3D-CAE. The added Siamese network improves the feature separability between different categories and attention layers improve classification by focusing on discriminative information and neglecting the unimportant bands. The efficacy of the proposed model's performance was assessed by training and testing on both same-domain as well as cross-domain data and found to achieve 91.3 and 93.6 for Indian Pines and Salinas, respectively.
暂无评论