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.
This paper presents electromechanical vibration characteristics in parallel misalignment of a shaft by analyzing the vibration of PMSM grinding motorized spindle. The unbalanced magnetic pull (UMP) of the PMSM grinding motorized spindle is established as electromechanical model based on the Maxwell stress tensor, which is used to the spindle to cause the electromechanical vibration and calculated under different eccentricities through FEA (Finite Element Analysis). It increases with increasing eccentricity under no load and on load and is maximum value when mixing eccentricity. Applying a Jeffcott rotor model to analyse the dynamic characteristics of the spindle with UMP excitation and mass imbalance. The number of pole-pair is 6 and the number of slots is 36 for the PMSM grinding motorized spindle, the vibrations of 1fr, 2fr and 3fr are generated and the limit cycle is more complicated at 4500rpm. Simulated results agree well with the experimental results, and it indicates the electromechanical vibration with the shaft eccentricity and the UMP is obviously on the shaft.
Three-phase unbalance control strategy is used to improve the system performance when three-phase unbalance load or fault happens. However, when the distributed generation selected as the master in the microgrid stop working, due to the loss of system voltage direction, the traditional control strategy is no longer applicable. In order to maintain the stable operation of the SST (Solid State Transformer) under passive microgrid model when threephase unbalances occur in the microgrid, the paper came up a novel balance control strategy under passive microgrid model. The control strategy is based on the voltage and current double-loop control strategy, and uses a negative sequence current module to calculation the negative sequence reference current, prevent three-phase unbalance from entering into distribution grid side and improve the control performance of the SST. The simulation results have proved the validity and efficiency of the three-phase unbalance control strategy.
This paper considers an event-triggered communication scheme for a class of networked Takagi-Sugeno (T-S) fuzzy systems with uncertainties and time delay. By the parallel distributed compensation fuzzy control rules, a new type of closed-loop nonlinear networked control systems (NCSs) with an interval time delay, uncertainties and event-triggered communication strategy is modeled as a class of networked T-S fuzzy systems. In order to deal with the integral items and convert the coupling time-varying matrix inequalities into a class of decoupling matrix inequalities, a new delay-dependent stabilization criterion is presented firstly. Secondly, some novel criteria for the asymptotic stability analysis and control synthesis of event-triggered networked T-S fuzzy systems with time delay and uncertainties are established in terms of linear matrix inequalities (LMIs). Finally, a numerical example is given to illustrate the effectiveness of the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.