Search

Sunspots have a significant impact on human activities. In this study, we aimed to improve solar activity prediction accuracy. To predict the sunspot number based on different aspects, such as extracted features and relationships among data, we developed a hybrid model that includes a one-dimensional convolutional neural network (1D-CNN) for extracting the features of sunspots and bidirectional long short-term memory (BiLSTM) embedded with a multi-head attention mechanism (MHAM) to learn the inner relationships among data and finally predict the sunspot number. We evaluated our model and several existing models according to different evaluation indicators, such as mean absolute error (MAE) and root mean square error (RMSE). Compared with the informer, stacked LSTM, XGBoost-DL, and EMD-LSTM-AM models, the RMSE and MAE of our results were more than 42.5% and 65.1% lower, respectively. The experimental results demonstrate that our model has higher accuracy than other methods. [ABSTRACT FROM AUTHOR]

In the context of predicting the remaining useful life (RUL) of rolling bearings, many models often encounter challenges in identifying the starting point of the degradation stage, and the accuracy of predictions is not high. Accordingly, this paper proposes a technique that utilizes particle swarm optimization (PSO) in combination with the fusing of a one-dimensional convolutional neural network (CNN) and a multihead self-attention (MHSA) bidirectional long short-term memory (BiLSTM) network called PSO-CNN-BiLSTM-MHSA. Initially, the original signals undergo correlation signal processing to calculate the features, such as standard deviation, variance, and kurtosis, to help identify the beginning location of the rolling bearing degradation stage. A new dataset is constructed with similar degradation trend features. Subsequently, the particle swarm optimization (PSO) algorithm is employed to find the optimal values of important hyperparameters in the model. Then, a convolutional neural network (CNN) is utilized to extract the deterioration features of rolling bearings in order to predict their remaining lifespan. The degradation features are inputted into the BiLSTM-MHSA network to facilitate the learning process and estimate the remaining lifespan of rolling bearings. Finally, the degradation features are converted to the remaining usable life (RUL) via the fully connected layer. The XJTU-SY rolling bearing accelerated life experimental dataset was used to verify the effectiveness of the proposed method by k-fold cross-validation. After comparing our model to the CNN-LSTM network model and other models, we found that our model can achieve reductions in mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) of 9.27%, 6.76%, and 2.35%, respectively. Therefore, the experimental results demonstrate the model's accuracy in forecasting remaining lifetime and support its ability to forecast breakdowns. [ABSTRACT FROM AUTHOR]

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]

Using intumescent flame retardant (IFR) composed of ammonium polyphosphate (APP) and pentaerythritol (PER) as the main flame retardant, the organic montmorillonite (OMMT) as the synergistic flame retardant, and the thermoplastic polyurethane elastomer (TPU) as the polymer charring agent, the flame retardant modification of polybutylene succinate (PBS) was carried out by melt blending. The effect of the distribution of IFR and OMMT on the flame retardancy of PBS/TPU blends was investigated. The PBS/TPU/IFR/OMMT flame retardant composites were tested and characterized by limiting oxygen index (LOI), vertical combustion, thermogravimetric analysis, melt viscosity analysis and scanning electron microscopy (SEM). The results show that OMMT and IFR has a good synergistic flame retardant effect. The flame retardant effect of PBS/TPU/IFR blends can be improved when the mass fraction of OMMT is 1%. The distribution position of IFR and OMMT has a significant impact on the flame retardance of PBS/TPU/IFR/OMMT blends. When IFR and OMMT are directly distributed in PBS phase, the flame retardancy of the blend is the best. LOI is 32. 7% and the vertical combustion reaches UL 94 V-0 level, which is significantly better than that of the flame retardancy for the other three distribution systems. [ABSTRACT FROM AUTHOR]

Studied here in the paper is the influence by the heat treatment process on the residual austenite content and the mechanical properties of the expandable casing. As a result, it is revealed that compared with the heat treatment process of quenching + hi-temperature annealing, employment of the heat treatment process of quenching + critical section normalization + hi-temperature annealing is capable of bringing about more residual austenite structure, and thus proper residual austenite content gets the comprehensive mechanical properties of the steel improved, the strength ratio reduced, the plasticity and toughness of the expandable casing enhanced, and the uniform elongation increased from 12% up to 23% so as to meet the requirement for the expansion. [ABSTRACT FROM AUTHOR]

Abstract: The electrical properties of different metal–cadmium–zinc–telluride (CdZnTe) contacts produced by sputtering deposition method are investigated. The results of current–voltage and SEM analyses show that Au is the most suitable electrical contact material, which forms nearly ideal Ohmicity contact with high resistivity p-CdZnTe:In crystals and a 0.95±0.02eV barrier height with low resistivity ones. Passivation treatment can decrease the leakage current. XPS analyses show that Au atoms diffused into CdZnTe:In during annealing, meanwhile Cd and Te atoms diffuse into the Au contact. Diffused Au atoms do not form any compound with any element in CdZnTe:In crystal, but subsitute Cd sites or occupy Cd vacancies as acceptors. Thus, a heavy p-type doping layer is formed, and M–p+–p Ohmic contact is obtained. [Copyright &y& Elsevier]