دانلود مقاله ISI انگلیسی شماره 138619
ترجمه فارسی عنوان مقاله

پیش بینی پراکندگی پودر در یک محیط پیچیده با استفاده از شبکه های عصبی مصنوعی

عنوان انگلیسی
Forecasting powder dispersion in a complex environment using Artificial Neural Networks
کد مقاله سال انتشار تعداد صفحات مقاله انگلیسی
138619 2017 19 صفحه PDF
منبع

Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)

Journal : Process Safety and Environmental Protection, Volume 110, August 2017, Pages 71-76

ترجمه کلمات کلیدی
مدل سازی پراکندگی اتمسفری، شبکه عصبی مصنوعی، پیش بینی گرد و غبار،
کلمات کلیدی انگلیسی
Atmospheric dispersion modeling; Artificial Neural Networks; Dust forecasting;
پیش نمایش مقاله
پیش نمایش مقاله  پیش بینی پراکندگی پودر در یک محیط پیچیده با استفاده از شبکه های عصبی مصنوعی

چکیده انگلیسی

Atmospheric dispersion prediction skill is required for any industry processing hazardous material. This is a sensitive task since many parameters are involved: source term, atmospheric conditions, and local configuration. Behavior of dust dispersion is difficult because of the diameter scattering, agglomeration, sedimentation, range of densities... Furthermore, production sites may be located inside a complex environment such as urban areas, where accuracy of classical dispersion models is low. This paper aims to evaluate the efficiency of an Artificial Neural Networks (ANN) model to predict dust dispersion in an urban area without prior knowledge of the source term. The experimental database consists of 290 daily mean concentration measurements on a site located 500 m away from the emission source. The inputs are selected from meteorological data from a MeteoSwiss station located 4.5 km south. The training phase is done through early stopping application. ANN model selection is performed on the best coefficient of determination value. Model performance is evaluated using classical air quality criteria and shows good results. Nevertheless, ANN model tends to underestimate high concentrations while overestimating low concentrations. Results are included within acceptable range. Improvements can be achieved by adding information of the source term as an input for the ANN model.