Search

This paper presents a methodology for predicting the remaining usability of rolling bearings. The method combines a fully adaptive ensemble empirical modal decomposition of noise (CEEMDAN), convolutional neural network (CNN), and attention bidirectional long short-term memory network (ABiLSTM). Firstly, a finite number of intrinsic mode functions (IMFs) are obtained from breaking down the initial vibration signals using CEEMDAN. The IMFs are further screened by combining the correlation criterion and the craggy criterion. Then, time-frequency domain features, which are extracted from the screened IMFs, are reconstructed into a feature set. The SPT is recognized through some features, like the root mean square (RMS), variance, and kurtosis. Secondly, the deterioration character of rolling bearings was extracted using CNN and used to train the ABiLSTM network. Based on the output of the ABiLSTM network, it forecasts how long rolling bearings will last during use. Finally, the XJTU-SY rolling bearing dataset validated the validity of the suggested rolling bearing remaining life prediction method. We compare our algorithm with other algorithms, such as GRU, LSTM, and CNN–BiLSTM, in which the accuracy of MAE, MSE, RMSE, MAPE, and R2_score is significantly improved. Thus, the results of the validation experiments demonstrate that our proposed algorithm has excellent prediction accuracy. [ABSTRACT FROM AUTHOR]

Aiming at the waste of resources caused by the bearing reaching the service time and still meeting the service conditions, a bearing remaining service life prediction method based on CNN-LSTM is proposed. Firstly, a high-speed railway traction motor bearing which has completed service but is still healthy is selected as the research object, the test platform is built and the bearing vibration signal is collected; secondly, a network model of CNN-LSTM is established; then, the collected vibration signal is input into the network model after Fourier transform, and its deep features are mined; finally, the remaining service life is predicted through the prediction module. The results show that the predicted value obtained by the proposed method is closer to the true value, which can well reflect the performance degradation trend of the bearing in operation.

To implement Prognostics Health Management (PHM) for hydraulic pumps, it is very important to study the faults of hydraulic pumps to ensure the stability and reliability of the whole life cycle. The research on fault diagnosis has been very active, but there is a lack of systematic analysis and summary of the developed methods. To make up for this gap, this paper systematically summarizes the relevant methods from the two aspects of fault diagnosis and health management. In addition, in order to further facilitate researchers and practitioners, statistical and comparative analysis of the reviewed methods is carried out, and a future development direction is prospected. [ABSTRACT FROM AUTHOR]

To implement Prognostics Health Management (PHM) for hydraulic pumps, it is very important to study the faults of hydraulic pumps to ensure the stability and reliability of the whole life cycle. The research on fault diagnosis has been very active, but there is a lack of systematic analysis and summary of the developed methods. To make up for this gap, this paper systematically summarizes the relevant methods from the two aspects of fault diagnosis and health management. In addition, in order to further facilitate researchers and practitioners, statistical and comparative analysis of the reviewed methods is carried out, and a future development direction is prospected.

Concrete highway bridge remaining service life has been at the forefront of bridge owners' concerns for several years in terms of growing bridge maintenance needs. Distresses in concrete bridge components occur due to physical, chemical, and mechanical factors that manifest as observable symptoms of deterioration. Deterioration models realistically link the observable defects to the several explanatory variables affecting the deterioration that aid in the planning of appropriate corrective actions. Only a limited number of explanatory variables have been considered in the published literature in the development of bridge component deterioration models. This study investigates the effect of multiple relevant explanatory variables affecting the bridge component condition including aging, loads and environmental conditions, and design characteristics using a multivariate regression analysis approach. Deterioration models for both superstructure and substructure of reinforced and prestressed concrete bridges are developed and validated in the present study. The proposed models will aid the bridge engineers to predict the concrete bridge component conditions based on bridge characteristics for planning preventive maintenance. [ABSTRACT FROM AUTHOR]

The state-of-the art paper provides an extensive literature review on the work pertaining to structural health monitoring (SHM) systems used to investigate the structural integrity of highway bridges. The focus of this review is on identifying the SHM research efforts that include damage detection, structural capacity evaluation, and remaining service life estimates on such structures. These efforts have spanned a broad range of data processing methods devoted to tracking changes in structural characteristics for damage detection, codified frameworks enabling structural capacity estimating, and reliability analysis to predict remaining life. Our findings are that a large number of studies considered damage detection by data processing methods, whereas a relatively small number of studies were devoted to the estimation of structural capacities and the remaining service life of bridges. We conclude that the critical gaps include a lack of validated SHM systems that use ambient data to examine design code-based structural integrity and remaining life of highway bridges. [ABSTRACT FROM AUTHOR]

In the domain of rolling bearing condition monitor and fault prognosis, to solve the key problem of rolling bearing degenerate feature extraction, a new approach based on generalized mathematical morphological particle is proposed in the paper, the new approach, which is founded on the mathematical morphological particle analysis, introduces corrosion and dilation operators in morphological calculation and takes the calculated generalized mathematical morphological particle as feature indicator, therefore, the performance degenerate degree could be reflected in quantity. The effectiveness of this approach is test and verified with simulation and actual signal. On this basis, in order to describe the whole tendency and random fluctuating feature for rolling bearings, grey Markov model is applied in the remaining service life prediction for rolling bearing, A method of remaining service life prediction based on generalized mathematical morphological particle and grey Markov model is proposed thereby. Rolling bearing fatigued life testing was proceeded with Hangzhou Bearing Test & Research Center, the approach is proved effective with the collecting bearing inner race whole life data in fatigued life testing. [ABSTRACT FROM AUTHOR]

Prediction of the remaining service life (RSL) of pavement is a challenging task for road maintenance and transportation engineering. The prediction of the RSL estimates the time that a major repair or reconstruction becomes essential. The conventional approach to predict RSL involves using non-destructive tests. These tests, in addition to being costly, interfere with traffic flow and compromise operational safety. In this paper, surface distresses of pavement are used to estimate the RSL to address the aforementioned challenges. To implement the proposed theory, 105 flexible pavement segments are considered. For each pavement segment, the type, severity, and extent of surface damage and the pavement condition index (PCI) were determined. The pavement RSL was then estimated using non-destructive tests include falling weight deflectometer (FWD) and ground-penetrating radar (GPR). After completing the dataset, the modeling was conducted to predict RSL using three techniques include support vector regression (SVR), support vector regression optimized by the fruit fly optimization algorithm (SVR-FOA), and gene expression programming (GEP). All three techniques estimated the RSL of the pavement by selecting the PCI as input. The correlation coefficient (CC), Nash–Sutcliffe efficiency (NSE), scattered index (SI), and Willmott's index of agreement (WI) criteria were used to examine the performance of the three techniques adopted in this study. In the end, it was found that GEP with values of 0.874, 0.598, 0.601, and 0.807 for CC, SI, NSE, and WI criteria, respectively, had the highest accuracy in predicting the RSL of pavement. [ABSTRACT FROM AUTHOR]