Because of the transesterification reaction between poly(butylene terephthalate) (PBT) and polycarbonate (PC), the crystallization behavior and thermal-resistant properties of the blend have been known to be decreased. Therefore it is of importance to control the transesterification degree in PBT/PC blends. In this article, the effect of silicone phosphate on the transesterification reaction between PBT and PC was studied using differential scanning calorimetry (DSC), nuclear magnetic resonance (NMR), and infrared spectroscopy (IR). It was found that the crystallization temperature of PBT/PC/silicone phosphate was 18.0 C higher than that of pure system, and the difference of the crystallization temperature between the first and secondary cooling cycles in DSC was 15.8 C lower than that of the pure system. IR results showed that both random and block copolymer existed in the stabilized system, and both IR and NMR results proved the decrease of the copolymer content by the introduction of silicone phosphate. Compared with that of the pure system, the Vicat soft temperature of the stabilized system was increased by 17.2 C. All the results showed that silicone phosphate was an effective inhibitor for the controlling of the transesterification reaction in PBT/PC blends.
Key words: artificial neural network (ANN), near-infrared spectroscopy, degree of approximation, nondestructive analysis, analgini powder. ABSTRACT This paper demonstrates the usefulness of near-infrared (NIR) spectra and artificial neural network (ANN) in nondestructive quantitative analysis of Pharmaceuticals. Real data sets from near-infrared reflectance spectra of analgini powder pharmaceutical were used to build up an artificial neural network to predict unknown samples. The parameters affecting the network were discussed. A new 69 Downloaded by [University of California, San Francisco] at 02:49 15 March 2015 70 REN ET AL.network evaluation criterion, the degree of approximation, was employed. The overfitting was discussed. Owing to the good nonlinear multivariate calibration nature of ANN, the predicted result was reliable and precise. The relative error of unknown samples was less than 2.5 %.
Ultra-short-term power load forecasting is beneficial to improve the
economic efficiency of power systems and ensure the safe and stable
operation of power grids. As the volatility and randomness of loads in
power systems, make it difficult to achieve accurate and reliable power
load forecasting, a sequence-to-sequence based learning framework is
proposed to learn feature information in different dimensions
synchronously. A CNN_BiLSTM network is built in the encoder to extract
the correlated timing features embedded in external factors affecting
power loads. The parallel BiLSTM network is built in the decoder to mine
the power load timing information in different regions separately. The
multi-headed attention mechanism is introduced to fuse the BiLSTM hidden
layer state information in different components to further highlight the
key information representation. The load forecastion results in
different regions are output through the fully connected layer. The
model proposed in this paper has the advantage of high forecastion
accuracy through the example analysis of real power load data.
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.