Recently, an increasing popularity of data-driven deep learning research in the field of machine fault diagnosis has been observed. Stacked denoising autoencoder (SDA), as a classic type of deep learning method, has b...
详细信息
ISBN:
(纸本)9781728156750
Recently, an increasing popularity of data-driven deep learning research in the field of machine fault diagnosis has been observed. Stacked denoising autoencoder (SDA), as a classic type of deep learning method, has been successfully used to learn effective representations for machine fault diagnosis. However, those previous studies always encounter with the inherent limitations of SDA: high computational cost, time-consuming training, and lack of scalability to high-dimensional data. Unfortunately, those limitations can restrict the applicability of those studies in real-world applications, which require timely model upgrade and fast real-time diagnosis. Besides, most previous studies concentrate on the vibration signal, and thus lack the attention towards other kinds of sensor data like acoustical signal. Therefore, to address the two problems above, inspired by the marginalized Stacked denoising autoencoder (mSDA), we adopt a variant of SDA for fast fault diagnosis on sound signal. In this way, the required stochastic gradient descent based on back propagation in traditional deep learning methods is replaced by a forward closed-form solution. Opposite to the time-consuming works which demand training thousands of parameters during optimization, this deep architecture only needs to determine a few hyper parameters in advance. To verify the effectiveness and efficiency of the proposal on sound signal, extensive empirical evaluation on a publicly available sound signal dataset of gear fault is carried on. Thorough comparisons with some state-of-the-art faulty diagnosis approaches, confirm the superiority of the proposal in high diagnostic accuracy and lower computational cost.
In transportation engineering, spatio-temporal data including traffic flow, speed, and occupancy are collected from different kinds of sensors and used by transportation engineers for analysis. However, the missing da...
详细信息
In transportation engineering, spatio-temporal data including traffic flow, speed, and occupancy are collected from different kinds of sensors and used by transportation engineers for analysis. However, the missing data influence the analysis and prediction results significantly. In this paper, denoising autoencoders are used to impute the missing traffic flow data. In our earlier research, we focused on a more general situation and used three kinds of denoising autoencoders: “Vanilla”, CNN, and Bi-LSTM, to impute the data with a general missing rate of 30%. The autoencoder models are used to train on data with a high missing rate of about 80% in this paper. We demonstrate that even under extreme loss conditions, and autoencoder models are very robust. By observing the hyper-parameter tuning process, the changing prediction accuracy is shown and in most cases, the three models maintain the original accuracy even under the worst situations. Moreover, the error patterns and trends concerning different sensor stations and different hours on weekdays and weekends are also visualized and analyzed. Finally, based on these results, we separate the data into weekdays and weekends, train and test the model respectively, and improve the accuracy of the imputation result significantly.
To improve the operation stability and reliability of energy storage stations (ESSs), it's significance to ensure high-precision battery remaining useful life (RUL) prediction. Recently, the raw capacity of batter...
详细信息
作者:
Li, JiatuUniversity of California
San Diego Halicioǧlu Data Science Institute Department of Mathematics San DiegoCA United States
Accurate medical imaging is vital for precise disease diagnosis and effective treatment. However, X-ray images may be subject to varying degrees of noise due to factors such as patient health conditions requiring redu...
详细信息
Low Probability of Intercept (LPI) radar signals play a vital role in electronic warfare by maintaining informational superiority. Classifying these LPI radar waveforms is a key capability but remains a challenging ta...
详细信息
In recent years, precision medicine has been consistently studied and employed in cancer treatment. One of the main challenges in precision medicine is accurately predicting a cancer patient's response to a specif...
详细信息
The introduction of electronic trading platforms effectively changed the organisation of traditional systemic trading from quote-driven markets into order-driven markets. Its convenience led to an exponentially increa...
详细信息
ISBN:
(纸本)9781450393768
The introduction of electronic trading platforms effectively changed the organisation of traditional systemic trading from quote-driven markets into order-driven markets. Its convenience led to an exponentially increasing amount of financial data, which is however hard to use for the prediction of future prices, due to the low signal-to-noise ratio and the non-stationarity of financial time series. Simpler classification tasks - where the goal is to predict the directions of future price movement via supervised learning algorithms need sufficiently reliable labels to generalise well. Labelling financial data is however less well defined than in other domains: did the price go up because of noise or a signal? The existing labelling methods have limited countermeasures against the noise, as well as limited effects in improving learning algorithms. This work takes inspiration from image classification in trading [6] and the success of self-supervised learning in computer vision (e.g., [16]). We investigate the idea of applying these techniques to financial time series to reduce the noise exposure and hence generate correct labels. We look at label generation as the pretext task of a self-supervised learning approach and compare the naive (and noisy) labels, commonly used in the literature, with the labels generated by a denoising autoencoder for the same downstream classification task. Our results demonstrate that these denoised labels improve the performances of the downstream learning algorithm, for both small and large datasets, while preserving the market trends. These findings suggest that with our proposed techniques, self-supervised learning constitutes a powerful framework for generating "better" financial labels that are useful for studying the underlying patterns of the market.
In the prediction of bearing fault remaining useful life (RUL), the identification and feature extraction of early bearing faults are very important. In order to improve the accuracy of early fault RUL prediction, a b...
详细信息
In the prediction of bearing fault remaining useful life (RUL), the identification and feature extraction of early bearing faults are very important. In order to improve the accuracy of early fault RUL prediction, a bearing fault RUL prediction model based on weighted variable loss degradation characteristics is proposed. The model is composed of a stack denoising autoencoder (SDAE) module guided by variable loss, a signal-to-noise feature adaptive weighting module and a long-short term memory (LSTM) degradation characteristics extraction and regression output module. Firstly, this model improves the ability of SDAE model to extract weak fault features by ascending dimension learning and variable loss function. Then, an adaptive weighting matrix is generated according to the test signal to modulate the weight vector of SDAE. Finally, the hidden layer features of SDAE were input into LSTM model to extract the bearing state degradation features and realize the RUL prediction of bearing faults. The experimental results show that the proposed model can accurately predict the RUL of the test data in the early fault stage and the fault development stage. The proposed model can give early fault warning to the bearing state.
Wind turbine gearbox fault feature extraction is difficult due to strong background noise. To address this issue, a noise reduction method combining comprehensive learning particle swarm optimization-variational mode ...
详细信息
Wind turbine gearbox fault feature extraction is difficult due to strong background noise. To address this issue, a noise reduction method combining comprehensive learning particle swarm optimization-variational mode decomposition (CLPSO-VMD) and deep residual denoising self-attention autoencoder (DRDSAE) is proposed. Firstly, the proposed CLPSO-VMD algorithm is used to decompose the noisy wind turbine gearbox vibration signals. Subsequently, the intrinsic mode functions highly correlated with the original signals are selected through the Spearman correlation coefficient and utilized for signal reconstruction, thereby filtering out high-frequency noise outside the fault frequency band in the frequency domain characterization. Secondly, the improved DRDSAE is utilized to learn the latent representations of data in the first-level denoised signal, further reducing the residual noise within the fault frequency band while retaining important signal features. Finally, the envelope spectrum highlights the weak feature of the wind turbine gearbox vibration signal. Experimental results demonstrate the effectiveness of the proposed method in denoising wind turbine gearbox vibration signals under strong noise.
The precise estimation of the state of health (SoH) in Lithium-ion batteries (LiBs) relies heavily on a reliable health indicator (HI). Conventional indicators are often constructed by directly concatenating features ...
详细信息
The precise estimation of the state of health (SoH) in Lithium-ion batteries (LiBs) relies heavily on a reliable health indicator (HI). Conventional indicators are often constructed by directly concatenating features from multiple sources. It overlooks significant non-linear and correlative information inherent in raw signals. To address this limitation, this paper introduces an innovative approach for SoH estimation in LiBs. Deep features extracted from signals of various sensors are obtained using denoising auto-encoders (DAEs). Then the dominant invariant subspaces (DIS) are calculated through the non-linear transformation of multi-source features on the Grassmann manifold. It can preserve essential and robust characteristics. The health indicator quantifies the geodesic distance of DIS using a projection metric. It provides a more comprehensive inclusion of nonlinear and correlation information. Consequently, this indicator offers heightened precision in discerning differences in health states. Validation of the proposed method is conducted using the NASA dataset. The result demonstrates its effectiveness on the SoH assessment and superiority to the state-of-the-art method.
暂无评论