RESUMO
Tool wear prediction is of great significance in industrial production. Current tool wear prediction methods mainly rely on the indirect estimation of machine learning, which focuses more on estimating the current tool wear state and lacks effective quantification of random uncertainty factors. To overcome these shortcomings, this paper proposes a novel method for predicting cutting tool wear. In the offline phase, the multiple degradation features were modeled using the Brownian motion stochastic process and a SVR model was trained for mapping the features and the tool wear values. In the online phase, the Bayesian inference was used to update the random parameters of the feature degradation model, and the future trend of the features was estimated using simulation samples. The estimation results were input into the SVR model to achieve in-advance prediction of the cutting tool wear in the form of distribution densities. An experimental tool wear dataset was used to verify the effectiveness of the proposed method. The results demonstrate that the method shows superiority in prediction accuracy and stability.
RESUMO
In recent years, prognostic and health management (PHM) has played an important role in industrial engineering. Efficient remaining useful life (RUL) prediction can ensure the development of maintenance strategies and reduce industrial losses. Recently, data-driven based deep learning RUL prediction methods have attracted more attention. The convolution neural network (CNN) is a kind of deep neural network widely used in RUL prediction. It shows great potential for application in RUL prediction. A CNN is used to extract the features of time-series data according to the spatial feature method. This way of processing features without considering the time dimension will affect the prediction accuracy of the model. On the contrary, the commonly used long short-term memory (LSTM) network considers the timing of the data. However, compared with CNN, it lacks spatial data extraction capabilities. This paper proposes a double-channel hybrid prediction model based on the CNN and a bidirectional LSTM network to avoid those drawbacks. The sliding time window is used for data preprocessing, and an improved piece-wise linear function is used for model validating. The prediction model is evaluated using the C-MAPSS dataset provided by NASA. The predicted results show the proposed prediction model to have a better prediction performance compared with other state-of-the-art models.
RESUMO
Bearings are some of the most critical industrial parts and are widely used in various types of mechanical equipment. Bearing health status can have a significant impact on the overall equipment performance, and bearing failures often cause serious economic losses and even casualties. Thus, estimating the remaining useful life (RUL) of bearings in real time is of utmost importance. This paper proposes a data-driven RUL prediction method for bearings based on Bayesian theory. First, time-domain features are extracted from the bearing vibration signal and data are fused to build a health indicator (HI) and a state model of bearing degradation. Then, according to Bayesian theory, a Bayesian model of state parameters and bearing life is established. The parameters of the Bayesian model are updated and bearing RUL is predicted by the Metropolis-Hastings algorithm. The method was validated by the XJTU-SY bearing open datasets and the prediction results are compared with the existing methods. Accuracy of the proposed method was demonstrated.
RESUMO
In order to realize the remaining useful life (RUL) prediction of mechanical equipment under different operating conditions, a domain adaption residual separable convolutional neural network (DRSCN) model is proposed in this paper. In the DRSCN model, instead of the traditional convolutional layer, a residual separable convolutional module is developed to improve the feature extraction ability of the model. Moreover, a multi-kernel maximum mean discrepancy metric function and an adversarial learning mechanism are embedded in the DRSCN model to enhance its ability to resist domain shifts, thus improving the cross-domain RUL prediction accuracy of the model. The effectiveness of the DRSCN model is verified on an aircraft engine dataset. The experimental results show that the proposed model can realize high-accuracy RUL prediction.
RESUMO
Molybdenum nitride (MoNx) was perceived as carrier-selective contacts (CSCs) for crystalline silicon (c-Si) solar cells due to having proper work functions and excellent conductivities. However, the poor passivation and non-Ohmic contact at the c-Si/MoNx interface endow an inferior hole selectivity. Here, the surface, interface, and bulk structures of MoNx films are systematically investigated by X-ray scattering, surface spectroscopy, and electron microscope analysis to reveal the carrier-selective features. Surface layers with the composition of MoO2.51N0.21 form upon air exposure, which induces the overestimated work function and explains the origin of inferior hole selectivities. The c-Si/MoNx interface is confirmed to adopt long-term stability, providing guidance for designing stable CSCs. A detailed evolution of the scattering length density, domain sizes, and crystallinity in the bulk phase is presented to elucidate its superior conductivity. These multiscale structural investigations offer a clear structure-function correlation of MoNx films, providing key inspiration for developing excellent CSCs for c-Si solar cells.
RESUMO
Remaining useful life prediction is of huge significance in preventing equipment malfunctions and reducing maintenance costs. Currently, machine learning algorithms have become hotspots in remaining useful life prediction due to their high flexibility and convenience. However, machine learnings require large amounts of data, and their prediction performance depends heavily on the selection of hyper-parameters. To overcome these shortcomings, a novel remaining useful life prediction method for small sample cases is proposed based on multi-support vector regression fusion. In the offline training phase, the fusion model is established, consisting of multiple support vector regression sub-models To obtain the optimal sub-model parameters, the Bayesian optimization algorithm is applied and an improved optimization target is formulated with various metrics describing regression and prediction performance. In the online prediction phase, an adaptive weight updating algorithm based on dynamic time warping is developed to measure the fitness of each sub-model and determine the corresponding weight value. The C-MAPSS engine dataset is used to test the performance of the proposed method, along with some existing machine learning methods as comparison. The proposed method only requires 30% of the training data sample to achieve high accuracy, with a root mean square error of 14.98, which is superior to other state-of-the-art methods. The results demonstrate the superiority of the proposed method.
Assuntos
Algoritmos , Aprendizado de Máquina , Teorema de Bayes , Máquina de Vetores de SuporteRESUMO
Following the publication of this paper, it was drawn to the authors' attention by an interested reader that certain of the tumours featured in Fig. 6A of the above paper were strikingly similar to those featured in Fig. 8A of an article appearing in International Journal of Oncology (Fan F-Y, Deng R, Yi H, Sun H-P, Zeng Y, He G-C and Su Y: The inhibitory effect of MEG3/miR-214/AIFM2 axis on the growth of T-cell lymphoblastic lymphoma. Int J Oncol 51: 316-326, 2017). The Editor asked the authors for an explanation to account for the appearance of strikingly similar data in their paper independently, and they responded to request that the paper be retracted from Oncology Reports. All the authors agreed that the article should be retracted. The Editor apologizes to the readership for any inconvenience caused. [the original article was published in Oncology Reports 38: 2408-2416, 2017; DOI: 10.3892/or.2017.5871].
RESUMO
Gliomas are the most common cancers in the brain, accompanied with high morbility, occurrence, disability and mortality. Long non-coding RNAs (lncRNAs) have been proposed as promoter or inhibitor in many cancer processes. Previous findings have indicated that lncRNA-maternally expressed gene 3 (MEG3) is involved in tumorigenesis of several cancers, including glioma. However, the underlying mechanism of MEG3 in glioma remains elusive. In our study, MEG3 was found downregulated in glioma tissues compared with normal brain tissues. Downregulated expression of MEG3 was also detected in two human glioma cell lines (U-251, M059J) compared with normal astrocyte cells. MEG3 was then overexpressed by ligating to a lentiviral vector. Overexpressed MEG3 inhibited the proliferation of U-251 cells, and restrained the expression of proliferation marker proteins Ki67 and proliferating cell nuclear antigen (PCNA). However, cell apoptosis rate of U-251 cells and the expression of apoptosis marker proteins (caspase-3 and caspase-9) were elevated by MEG3. Furthermore, miR-93 was predicted a direct target of lncRNA-MEG3 by bioinformatics analysis. Overexpressed MEG3 counteracted the role of miR-93 in facilitating proliferation and inhibiting apoptosis in U-251 cells. Moreover, MEG3 restained the activation of phosphatidylinositol 3 kinase/protein kinase B (PI3K/AKT) pathway by reducing cytomembrane translocation of AKT. Finally, the in vivo experiment revealed that MEG3 strongly reduced tumor growth, tumor volume and the expression of Ki67 and PCNA. lncRNA-MEG3 also inhibited the level of miR-93 and the expression of PI3K/AKT pathway related proteins in vivo. Taken together, our research indicated a MEG3-miR-93-PI3K-AKT pathway in regulating the growth of glioma, providing a promising therapy for glioma.