Virtual sensor for time series prediction of hydrogen safety parameter in DEGUSSA sintering furnace

Abstract

Hydrogen is increasingly investigated as an alternative energy source to petroleum products in industrial application, internal combustion engines (transportation) and electrical power plant. The safety issues related to hydrogen gas are further exasperated by expensive instrumentation required to measure the temperature, flow rates and production pressure. This paper investigates the use of model based virtual sensors in connection with DEGUSSA Sintering furnace with hydrogen gas as process atmosphere for UO2 pellet sintering processes. The virtual sensors are used to predict relevant hydrogen safety parameters, such as hydrogen output temperature, hydrogen pressure and hydrogen flow rate as a function of different input conditions parameters. The virtual sensors are developed by means of the application of various Artificial Intelligent techniques. To train and appraise the neural network models as virtual sensors, the Degussa sintering system is instrumented with necessary sensors to gather experimental data which together with neural networks and adaptive neuro-fuzzy inference systems were used as predictive tools to estimate hydrogen safety parameters. It was shown that using the neurofuzzy inference system, hydrogen safety parameters were predicted with the average RMSE 0.0387, 0.0283, 0.1301 and MAE 0.0241, 0.0115, 0.0355 sequentially for temperature, pressure, and flow rate of hydrogen.

Spatio‐temporal analysis for extreme temperature indices over the Levant region

“…For this study, the thresholds of an outlier were defined within the range of ±4 standard deviations (Athar, 2014;Zhang et al, 2005). After that, the comparison with neighboring stations (spatial coherency) was also used to determine whether an outlier was the result of natural factors or systematic errors (Sutarya and Mahendra, 2014).…”