Search

To avoid the failure of pumping units, the monitoring of operating points with a subsequent assessment of the condition of the pump may support the decision for required maintenance. For that purpose, convolutional neural networks (CNNs) are implemented to predict the operating points of pumping units. Instead of using traditional flowmeter and manometer, vibration and acoustic signals are used to estimate the head and volume flow rate. An appropriate pre-processing of raw data is applied, enabling our method to predict well on different datasets. For the datasets measured in an anechoic chamber, the best model of each subset achieves relative errors smaller than 4.9% for the prediction of head and 7.6% for the volume flow rate. For cases where only small amounts of data exist, it is furthermore demonstrated that transfer learning from one dataset to another dataset provides an improvement in performance., KSB Foundation, German Research Foundation (DFG)

The fluorinated epoxy resin, 2,2-bisphenol hexafluoropropane diglycidyl ether (DGEBHF) was synthesized through a two-step procedure, and the chemical structure was confirmed by 1H nuclear magnetic resonance (NMR), 13C NMR, and Fourier transform infrared (FTIR) spectra. Moreover, DGEBHF was thermally cured with methyl hexahydrophthalic anhydride (MHHPA). The results clearly indicated that the cured DGEBHF/MHHPA exhibited higher glass transition temperature (Tg 147°C) and thermal decomposition temperature at 5% weight loss (T5 372°C) than those (Tg 131.2°C; T5 362°C) of diglycidyl ether of bisphenol A (DGEBA)/MHHPA. In addition, the incorporation of bis-trifluoromethyl groups led to enhanced dielectric properties with lower dielectric constant (Dk 2.93) of DGEBHF/MHHPA compared with cured DGEBA resins (Dk 3.25). The cured fluorinated epoxy resin also gave lower water absorption measured in two methods relative to its nonfluorinated counterparts. © 2013 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 130: 2801–2808, 2013