کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
4926217 | 1363174 | 2017 | 49 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
A comparative study and prediction of the liquid desiccant dehumidifiers using intelligent models
ترجمه فارسی عنوان
یک مطالعه مقایسه ای و پیش بینی مخلوط کننده های مایع خشک کن با استفاده از مدل های هوشمند
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی انرژی
انرژی های تجدید پذیر، توسعه پایدار و محیط زیست
چکیده انگلیسی
Dehumidifier in liquid desiccant systems is affected by different influential parameters and precise prediction of its characteristics is vital for a better overall performance. In this communication, the well-known artificial intelligence based methods such as Least Square Support Vector Machine (LSSVM), Adaptive Neuro Fuzzy Inference System (ANFIS), and Artificial Neural Network (ANN) are developed for prediction of the dehumidification effectiveness (ε) as well as the process outlet temperature and humidity (Tout and Ïout). Based on a comparative study, brighter conformity was obtained between the predicted and experimental data for the ANN models presented in the current study. The coefficients of determination and mean square errors for the ANN models during the testing phase were respective values of 0.9993 and 2.9740e-05 for the ε, 0.9997 and 0.0039 for the Ïout, and 0.9988 and 0.0192 for the Tout. A sensitivity analysis was conducted and showed higher influence of concentration and temperature of desiccant solution at the absorber inlet on the dehumidification effectiveness and process outlet state conditions, respectively. Further to the above, a mathematical technique on the basis of Leverage algorithm was implemented to assess the quality of the collected data, diagnose the doubtful data samples, and indicate the applicability range of the developed ANN models.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Renewable Energy - Volume 114, Part B, December 2017, Pages 1023-1035
Journal: Renewable Energy - Volume 114, Part B, December 2017, Pages 1023-1035
نویسندگان
Alireza Zendehboudi, Afshin Tatar, Xianting Li,