As one of the key components in mechanical systems, rotatory machine plays a significant role in safe and stable operation. Accurate prediction of the Remaining Useful Life (RUL) of rotatory machine contributes to realization of intelligent operation and maintenance for mechanical manufacturing. In order to overcome the limitations of traditional machine learning algorithms in dealing with complex nonlinear signals, a novel prediction framework for RUL of rotatory machine based on deep learning is proposed in this paper. One-dimensional convolutional neural network is utilized to extract local features from the original signal sequence. In addition, the proposed framework analyzes sensor signals and predicts RUL by combining Long Short-Term Memory (LSTM) network with attention mechanism. Multi-layer LSTM is set up to extract useful temporal features layer by layer and improve the robustness of the model, while attention mechanism is able to effectively solve the problem of information loss in the long-distance signal transmission of LSTM. Through the feature extraction of multi-layer LSTM and the strong supervision ability of attention mechanism, the RUL of rotatory machine can be accurately predicted. The experimental results show that the proposed method for RUL estimation is efficient and has higher prediction accuracy than the traditional machine learning algorithms.

No abstract

<p><strong>Abstract.</strong> On-road vehicle emissions are a major contributor to elevated air pollution levels in populous metropolitan areas. We developed a link-level emissions inventory of vehicular pollutants, called EMBEV-Link, based on multiple datasets extracted from the extensive road traffic monitoring network that covers the entire municipality of Beijing, China (16 400 km<sup>2</sup>). We employed the EMBEV-Link model under various traffic scenarios to capture the significant variability in vehicle emissions, temporally and spatially, due to the real-world traffic dynamics and the traffic restrictions implemented by the local government. The results revealed high carbon monoxide (CO) and total hydrocarbon (THC) emissions in the urban area (i.e., within the Fifth Ring Road) and during rush hours, both associated with the passenger vehicle traffic. By contrast, considerable fractions of nitrogen oxides (NO<sub>X</sub>), fine particulate matter (PM<sub>2.5</sub>) and black carbon (BC) emissions were present beyond the urban area, as heavy-duty trucks (HDTs) were not allowed to drive through the urban area during daytime. The EMBEV-Link model indicates that non-local HDTs could for 29 % and 38 % of estimated total on-road emissions of NO<sub>X</sub> and PM<sub>2.5</sub>, which were ignored in previous conventional emission inventories. We further combined the EMBEV-Link emission inventory and a computationally efficient dispersion model, RapidAir®, to simulate vehicular NO<sub>X</sub> concentrations at fine resolutions (10 m × 10 m in the entire municipality and 1 m × 1 m in the hotspots). The simulated results indicated a close agreement with ground observations and captured sharp concentration gradients from line sources to ambient areas. During the nighttime when the HDT traffic restrictions are lifted, HDTs could be responsible for approximately 10 μg m<sup>−3</sup> of NO<sub>X</sub> in the urban area. The uncertainties of conventional top-down allocation methods, which were widely used to enhance the spatial resolution of vehicle emissions, are also discussed by comparison with the EMBEV-Link emission inventory.</p>

Rolling bearings are some of the most crucial components in rotating machinery systems. Rolling bearing failure may cause substantial economic losses and even endanger operator lives. Therefore, the accurate remaining useful life (RUL) prediction of rolling bearings is of tremendous research importance. Health indicator (HI) construction is the critical step in the data-driven RUL prediction approach. However, existing HI construction methods often require extraction of time-frequency domain features using prior knowledge while artificially determining the failure threshold and do not make full use of sensor information. To address the above issues, this paper proposes an end-to-end HI construction method called a multi-scale convolutional autoencoder (MSCAE) and uses LSTM neural networks for RUL prediction. MSCAE consists of three convolutional autoencoders with different convolutional kernel sizes in parallel, which can fully exploit the global and local information of the vibration signals. First, the raw vibration data and labels are input into MSCAE, and then, MSCAE is trained by minimizing the composite loss function. After that, the vibration data of the test bearings are fed into the trained MSCAE to extract HI. Finally, RUL prediction is performed using the LSTM neural network. The superiority of the HI extracted by MSCAE was verified using the PHM2012 challenge dataset. Compared to state-of-the-art HI construction methods, RUL prediction using MSCAE-extracted HI has the highest prediction accuracy.

Purpose The current studies on remaining useful life (RUL) prediction mainly rely on convolutional neural networks (CNNs) and long short-term memories (LSTMs) and do not take full advantage of the attention mechanism, resulting in lack of prediction accuracy. To further improve the performance of the above models, this study aims to propose a novel end-to-end RUL prediction framework, called convolutional recurrent attention network (CRAN) to achieve high accuracy. Design/methodology/approach The proposed CRAN is a CNN-LSTM-based model that effectively combines the powerful feature extraction ability of CNN and sequential processing capability of LSTM. The channel attention mechanism, spatial attention mechanism and LSTM attention mechanism are incorporated in CRAN, assigning different attention coefficients to CNN and LSTM. First, features of the bearing vibration data are extracted from both time and frequency domain. Next, the training and testing set are constructed. Then, the CRAN is trained offline using the training set. Finally, online RUL estimation is performed by applying data from the testing set to the trained CRAN. Findings CNN-LSTM-based models have higher RUL prediction accuracy than CNN-based and LSTM-based models. Using a combination of max pooling and average pooling can reduce the loss of feature information, and in addition, the structure of the serial attention mechanism is superior to the parallel attention structure. Comparing the proposed CRAN with six different state-of-the-art methods, for the predicted results of two testing bearings, the proposed CRAN has an average reduction in the root mean square error of 57.07/80.25%, an average reduction in the mean absolute error of 62.27/85.87% and an average improvement in score of 12.65/6.57%. Originality/value This article provides a novel end-to-end rolling bearing RUL prediction framework, which can provide a reference for the formulation of bearing maintenance programs in the industry.