Search

The low dispersion of graphene is the main obstacle restricting the application of graphene in the natural rubber (NR) composites, especially in the green tire field. The present study addresses this important issue by developing a new hybrid filler, which is made from silicon dioxide nanoparticles (NSi) decorated reduced graphene oxide (rGO), denoted as GSi. Not only can the GSi filler be directly added to NR via mechanical mixing, but also excellent rGO dispersion is obtained, which greatly enhances the properties of the composites. The properties of GSi/NR composites are compared with those obtained by directly mixing equivalent concentrations of NSi and rGO (rGO/NSi/NR composites). The heat build-up and Akron abrasion loss of GSi/NR composites are only 18.4 °C and 0.149 cm3, 10.3% and 18.8% lower than the rGO/NSi/NR composites. Moreover, the tensile strength, elongation at break and heat resistance index of GSi/NR are up to 27.5 MPa, 507% and 182.2 °C, respectively. Besides, the abrasion loss and tensile strength can be further to 0.114 cm3 and 30.7 MPa by regulating the dosage of graphene oxide in the preparation of GSi. These results demonstrate that the GSi hybrid filler has high application value for the industrial-scale manufacture of green tires. [ABSTRACT FROM AUTHOR]

In order to improve the forecast accuracy of wind power, an Improved Long Short Term Memory (ILSTM) network structure is proposed. Firstly, Variational Mode Decomposition (VMD) method is adopted to decompose wind power signal to the long-term component, the fluctuation component and the random component, which are used as the input of forecast model. Then a parameter was defined and added to the memory cell to suppress the random component to long term memory of neural network. To provide a pass for the current random component, the output gate was modified accordingly. Compared with the traditional Long Short Term Memory (LSTM), the improved LSTM can reduce the impact of random component on the patterns in long term memory cells, while maintain the current random component in the short term memory of network. As a result, the learning for the real patterns of wind power is strengthened, avoiding over-fitting and achieve a better generalized forecast model. Finally, the performance of the forecast method proposed in this paper is tested by using the wind power data from the Belgian ELIA website. • Variational Mode Decomposition method is improved to decompose wind power signal. • In improved LSTM neural network, a parameter was added to the memory cells. • ILSTM can reduce the impact of random component on the long-term memory cells. [ABSTRACT FROM AUTHOR]