ارسل ملاحظاتك

ارسل ملاحظاتك لنا







Prediction of Reverse Osmosis (RO) Membrane Properties Using One Year Real Operational Data

المصدر: المجلة الجامعة
الناشر: جامعة الزاوية - مركز البحوث والدراسات العليا
المؤلف الرئيسي: Sassi, Kamal M. (Author)
مؤلفين آخرين: Yagub, Mustafa T. (Co-Author) , Atibeni, Rajab. A. (Co-Author)
المجلد/العدد: مج18, ع2
محكمة: نعم
الدولة: ليبيا
التاريخ الميلادي: 2016
الشهر: مايو
الصفحات: 61 - 78
رقم MD: 1263614
نوع المحتوى: بحوث ومقالات
اللغة: الإنجليزية
قواعد المعلومات: EduSearch, EcoLink, IslamicInfo, AraBase, HumanIndex
مواضيع:
كلمات المؤلف المفتاحية:
Fouling | Neural Network Techniques | Membrane Permeability | Reverse Osmosis | Spiral Wound Module | Seasonal Changes
رابط المحتوى:
صورة الغلاف QR قانون
حفظ في:
المستخلص: Modelling played an important role in simulation, optimisation, and control of reverse osmosis (RO) desalination processes. Water and salt permeability of the membrane are one of important membrane properties that affect optimal design and operation of RO processes. Therefore, estimation of membrane water and salt permeability is significant. In this work, neural networks (NNs) based correlation has been developed based on the actual RO fouling data over one year of operation and used for estimating the membrane permeability decline factors. It is found that the NNs based correlations can predict the experimental water and salt permeability very closely. Due to advancement in the microcomputer, plant automation becomes reliable means of plant maintenance. NNs based correlations (models) can be updated in terms of new sets of weights and biases for the same architecture or for a new architecture reliably with new plant data.

عناصر مشابهة