In the context of human-robot and robot-robot interactions, the better cooperation can be achieved by predicting the other party’s subsequent actions based on the current action of the other party. The time duration for adjustment is not sufficient provided by short term forecasting models to robots. A longer duration can by achieved by mid-term forecasting. But the mid-term forecasting models introduce the previous errors into the follow-up forecasting and amplified gradually, eventually invalidating the forecasting. A new mid-term forecasting with error suppression based on restricted Boltzmann machine(RBM) is proposed in this paper. The proposed model can suppress the error amplification by replacing the previous inputs with their features, which are retrieved by a deep belief network(DBN). Furthermore, a new mechanism is proposed to decide whether the forecasting result is accepted or not. The model is evaluated with several datasets. The reported experiments demonstrate the superior performance of the proposed model compared to the state-of-the-art approaches.
Journal of Porous Materials - Aiming at the poor heat conduction performance of porous MIL-101 applied in adsorption cooling process, few layer graphene (FLG) was selected as a promising thermal... 相似文献
Highly conductive transparent aluminium-doped ZnO (ZnO:A1) films were successfully deposited by CW-CO2 laser-induced evaporation. Optimisation of evaporation parameters was based on laser power, substrate temperature, O2 partial pressure in the vacuum chamber and amount of Al in the ZnO source pellet. ZnO:A1 films with an electrical resistivity as low as 6.6 × 10−2Ω·cm and an optical transmission of 80% at 500nm were obtained at laser power of 15 W, substrate temperature of about 200°C, O2 partial pressure of 6—7 × 10−4 Torr and 5wt.% Al. Conductivity of ZnO films can be increased one order via Al-doping in ZnO films. The films obtained by laser-induced evaporation have compared quite favorably with the high quality films obtained by sputtering. 相似文献
Titanium dioxide (TiO2) nanotube arrays were prepared by electrochemical anodization of titanium sheets in the glycerol 176 mL/H2O 44 mL/NH4F 0.5 wt% electrolytes modified with H2SO4 and NaAc addition. The surface morphologies, average inner diameter, and the length of the nanotube arrays changed with the solution pH in the range from 5.6 to 4.0 by adding H2SO4. A uniform surface morphology of the nanotubes with average inner diameter of ∼80 nm and a length of ∼1000 nm was obtained when the solution pH was 5.0. The growth rates of the nanotubes were remarkably enhanced by NaAc addition in the range of 0.04–0.14 M . With NaAc addition of 0.10 M , the length of the nanotube arrays reached 4.16 μm after an 8-h anodization, increasing 3.23 μm compared with no NaAc addition. The relationship between solution pH and growth of TiO2 nanotubes was analyzed by current–time curves, solution electrical conductivities, and scanning electron microscopy (SEM), and the role of NaAc was also discussed based on SEM and solution electrical conductivities. 相似文献