•MLP in the encoder module in conventional VAE was replaced by convolutional layers to handle the position information of peaks and local features in the impedance data.•To reduce the ambiguity of ...generated data, a CBAM module is introduced into the last layer of the encoder. In the design of the channel attention module, the complex MLP design was simplified into two fully connected layers with a ReLU activation function.•The effectiveness of the proposed method in this research has been proved in handling glass curtain wall bolt failure data.
Bolt looseness has adverse influences on the stability and safety of engineering structures. Neural network algorithms can effectively monitor health conditions using impedance signals. However, impedance data of engineering structures in damaged conditions is challenging to obtain. The data would also exhibit an imbalanced distribution, yielding deterioration of the accuracy of health monitoring. In this study, we propose a data augmentation method based on a Variational Autoencoder model with a convolutional block attention module. This method addressed the issue of imbalanced data by generating new data. A Transformer model was adopted for training and fault classification. Without employing data augmentation methods, the max accuracy is 85.71%. However, experimental results demonstrate the remarkable effectiveness of this approach in enhancing and classifying imbalanced datasets, with an average accuracy of 89.35% and the highest accuracy of 94.81% after enhancement. The proposed method can be applied to health conditions identification of buildings, bridges, and trusses.
•A supervised convolutional autoencoder is proposed for multivariate fault diagnosis.•Supervised convolutional autoencoder is used to pretrain the deep network and learn the fault-relevant feature.•A ...minimum difference transformation function is introduced to the network pretraining.•Classification performance is validated on the CSTR process and the TE process.
Convolutional autoencoder (CAE) is an unsupervised feature learning method and shows excellent performance in multivariate fault diagnosis. However, CAE cannot guarantee that the extracted feature is always related to the fault type due to its unsupervised self-reconstruction in the pretraining phase.
To solve this problem, a new feature learning method, supervised convolutional autoencoder (SCAE) is proposed to pretrain the network and learn representative feature containing internal spatial information and fault information. In the SCAE, process sample and corresponding label are reconstructed by multilayer encoding-decoding the raw sample. Meanwhile, to prevent label information overfitting the network, a minimum difference transformation function is introduced into the loss function.
The obtained fault-relevant features can be obviously distinguished between different fault types. The trained pretraining network provides more appropriate predefined parameters for fine-tuning to improve the classification performance. The effectiveness of the proposed method is evaluated by the continuous stirred tank reactor (CSTR) process and the Tennessee Eastman (TE) process.
Display omitted
Display omitted
•An optimal configuration method of concentrating solar power in power systems.•A data-driven scenario generation method to describe the uncertainty in power systems.•The benefits of ...concentrating solar power are comprehensively considered.•Sensitivity factors affecting the configuration results are analyzed in the case study.
The proportion of renewable energy sources and the flexibility demands of the power grid have increased simultaneously, which has caused difficulties in renewable energy consumption and the secure operation of power systems. Concentrating solar power (CSP) can provide additional flexibility for power systems and change the uncontrollable characteristics of variable renewable energy generation. Due to the high construction cost, it is necessary to fully evaluate the configurational scheme of CSP. In this paper, we propose an optimal configuration method for CSP in multienergy power systems to fully utilize the CSP benefits. We first improve the variational autoencoder (VAE) to describe the uncertainty in power systems and generate scenarios for the configuration model. The model consists of two stages: planning and operation. The planning model determines the configuration capacity of each component of the CSP station. The operation model considers the day-ahead and real-time periods to analyze the operational cost of the power systems with CSP. By means of linearized methods, the configuration model is treated as a mixed integer linear programming (MILP) formulation to obtain a rapid solution. A case study is conducted based on the power source data of a province in northwestern China. The simulation results show that flexibility values makes CSP more competitive in the configuration process, and the configuration results are significantly affected by the coordination with other power sources. We use sensitivity analysis with different situations to explore the development prospects of CSP.
•Different degrees of sparsity constraints are imposed adaptively in deep learning networks by temperature scaling techniques.•By considering the distribution of ground objects, it has good ...generalization in the real scene.•The framework is a new spatial level constraint method and can be transferred to other convolutional autoencoder-based methods.
Hyperspectral unmixing is a key technology in the development of remote sensing applications. However, since both endmembers and abundances are unknown, unmixing is a non-convex problem with a large solution space. To solve this, existing methods usually impose the same strength of sparsity constraint. However, this often does not hold in practice. Because the abundances of purer regions are generally sparse, while the abundances distribution of more mixed regions should be smoother. Temperature scaling is a technique of introducing a temperature parameter T into softmax activation function to adjust the sparsity of the output. Inspired by this, we propose a temperature scaling unmixing (TSU) framework based on convolutional autoencoder (CAE). In this framework, sparse constraints of different intensities are applied to diverse regions by considering spatial similarity of ground objects distribution while preserving the ability of CAE to extract spatial features. What is more, equal-frequency binning is adopted to guide the division of regions by similarity matrix to realize the automatic temperature parameter setting. In addition, a CAE network is designed under the TSU framework in this paper, called TSUCAE. The TSUCAE method exhibits superior accuracy compared to state-of-the-art approaches, as demonstrated through extensive comparative experiments. Furthermore, the TSU framework can be transferred to other CAE-based unmixing methods directly while keeping the network structure of these methods unchanged. Sufficient ablation experiments also prove that the transfer of framework can improve the performance of unmixing. The code is publicly available at https://github.com/UPCGIT/TSUCAE.
The performance of subspace clustering is affected by data representation. Data representation for subspace clustering maps data from the original space into another space with the property of better ...separability. Many data representation methods have been developed in recent years. Typical among them are low-rank representation (LRR) and an autoencoder. LRR is a linear representation method that captures the global structure of data with low-rank constraint. Alternatively, an autoencoder nonlinearly maps data into a latent space using a neural network by minimizing the difference between the reconstruction and input. To combine the advantages of an LRR (globality) and autoencoder (self-supervision based locality), we propose a novel data representation method for subspace clustering. The proposed method, called low-rank constrained autoencoder (LRAE), forces the latent representation of the neural network to be of low rank, and the low-rank constraint is computed as a prior from the input space. One major advantage of the LRAE is that the learned data representation not only maintains the local features of the data, but also preserves the underlying low-rank global structure. Extensive experiments on several datasets for subspace clustering were conducted. They demonstrated that the proposed LRAE substantially outperformed state-of-the-art subspace clustering methods.
•Introduce the CFS clustering model for feature selection.•Using the SDAE for life prediction at early life stage.•Extracting the original features using discharge capacity and temperature only.
...Accurate life prediction of lithium-ion batteries is important to help assess battery quality in advance, improve long-term battery planning, and subsequently guarantee the safety and reliability of battery operations. In this study, a deep learning-based stacked denoising autoencoder (SDAE) method is proposed to directly predict battery life by extracting various battery features. In general, the SDAE contains autoencoders and uses a deep network architecture to learn the complex nonlinear input-output relationship in a layer-by-layer fashion. Many features enabling the life prediction of lithium-ion batteries are extracted from discharge temperature and voltage curves. As redundancies in these features may result in poor prediction accuracy, a clustering by fast search (CFS) method is adopted to filter and select essential features. The CFS selects effective features by aggregating the types of battery features into clusters. All selected features are then fed into the SDAE to predict battery life cycle. Key hyperparameters are investigated, such as the number of iterations, the learning rate, and the denoising rate of the SDAE network. Experimental results show that the proposed selected-features-based deep learning method can provide more accurate and efficient battery life predictions with less fluctuation than the method without feature selection.
Accurate and timely traffic flow forecasting is critical for the successful deployment of intelligent transportation systems. However, it is quite challenging to develop an efficient and robust ...forecasting model due to the inherent randomness and large variations of traffic flow. Recently, the stacked autoencoder has been proven promising for traffic flow forecasting but still exists some drawbacks in certain conditions. In this paper, a training samples replication strategy is introduced to train a series of stacked autoencoders and an adaptive boosting scheme is proposed to ensemble the trained stacked autoencoders to improve the accuracy of traffic flow forecasting. Furthermore, sufficient experiments have been conducted to demonstrate the superior performance of the proposal.
•Proposes a novel resampling method based on a deep generative model to deal with the imbalanced regression data sets.•Improves the effect of undersampling and reduces the number of normal samples ...without losing informative samples by the proposed undersampling method.•Improves the quality of new rare regression samples, can better capture and learn information from rare samples by introducing the boosting mechanism and deep generative model.
Resampling is the most commonly used method for dealing with imbalanced data, in addition to modifying the algorithm mechanism, it can, for example, generate new minority samples or reduce majority samples to adjust the data distribution. However, to date, related research has predominantly focused on solving the classification problem, while the issue of imbalanced regression data has rarely been discussed. In real-world applications, predicting regression data is a common and valuable issue in decision making, especially in regard to those rare samples with extremely high or low values, such as those encountered in the fields of signal processing, finance, or meteorology. This study therefore divided its regression data into rare samples and normal samples, with self-defined relevance functions and, in addition, proposed a boosting resampling method based on a conditional variational autoencoder. The experimental results showed that when using the proposed resampling method was employed, the prediction performance of the whole testing data set was slightly increased, while the performance for the rare samples was significantly improved.
This paper presents a novel method based on modified Paris model with particle filtering (PF) framework to prognosis fatigue multi-cracks in metal structures. Since conventional Paris model is only ...applicable for the single crack, modified Paris model is proposed by introducing the mutual interaction between multiple cracks into stress intensity factor (SIF) expression and utilized to portray multiple fatigue crack growth process. To accurately monitor multi-cracks lengths, Lamb waves are periodically acquired during the fatigue growth of multiple cracks and fed into a deep autoencoder (DAE) network to automatically track response signals variations. Online monitoring model of multi-cracks lengths is then constructed by fitting the mapping relationship between the deep damage feature extracted by the bottleneck layer of DAE network and crack length. PF framework is further adopted to strategically fusing the prediction results of modified Paris model and real-time measurements of online monitoring model to reduce the uncertainties of material parameters and obtain more reliable prognosis results of multi-cracks lengths. The proposed method is demonstrated on center-hole metal specimens with two fatigue cracks. Experimental results show that the proposed method can accurately prognosis two fatigue cracks lengths, in which modified Paris model could more accurately describe multiple fatigue crack growth than conventional Paris model, and online monitoring model based on deep damage feature could more accurately track the fatigue crack length than artificial damage feature.
Semantic communications have emerged as a new paradigm for improving communication efficiency by transmitting the semantic information of a source message that is most relevant to a desired task at ...the receiver. Most existing approaches typically utilize neural networks (NNs) to design end-to-end semantic communication systems, where NN-based semantic encoders output continuously distributed signals to be sent directly to the channel in an analog fashion. In this work, we propose a joint coding-modulation (JCM) framework for digital semantic communications by using variational autoencoder (VAE). Our approach learns the transition probability from source data to discrete constellation symbols, thereby avoiding the non-differentiability problem of digital modulation. Meanwhile, by jointly designing the coding and modulation process together, we can match the obtained modulation strategy with the operating channel condition. We also derive a matching loss function with information-theoretic meaning for end-to-end training. Experiments on image semantic communication validate the superiority of our proposed JCM framework over the state-of-the-art quantization-based digital semantic coding-modulation methods across a wide range of channel conditions, transmission rates, and modulation orders. Furthermore, its performance gap to analog semantic communication reduces as the modulation order increases while enjoying the hardware implementation convenience.