Karimanzira, DivasDivasKarimanziraRauschenbach, ThomasThomasRauschenbach2022-03-062022-03-062021https://publica.fraunhofer.de/handle/publica/27039810.4236/gep.2021.97004One of the major challenges that membrane manufacturers, commercial enterprises and the scientific community in the field of membrane-based filtration or reverse osmosis (RO) desalination have to deal with is system performance retardation due to membrane fouling. In this respect, the prediction of fouling or system performance in membrane-based systems is the key to determining the mid and long-term plant operating conditions and costs. Despite major research efforts in the field, effective methods for the estimation of fouling in RO desalination plants are still in infancy, for example, most of the existing methods, neither consider the characteristics of the membranes such as the spacer geometry, nor the efficiency and the day to day chemical cleanings. Furthermore, most studies focus on predicting a single fouling indicator, e.g., flux decline. Faced with the limits of mathematical or numerical approach, in this paper, machine learning methods based on Multivariate Temporal Convolutional Neural networks (MTCN), which take into account the membrane characteristics, feed water quality, RO operation data and management practice such as Cleaning In Place (CIP) will be considered to predict membrane fouling using measurable multiple indicators. The temporal convolution model offers one the capability to explore the temporal dependencies among a remarkably long historical period and has potential use for operational diagnostics, early warning and system optimal control. Data collected from a Desalination RO plant will be used to demonstrate the capabilities of the prediction system. The method achieves remarkable predictive accuracy (root mean square error) of 0.023, 0.012 and 0.007 for the relative differential pressure and permeates Total Dissolved solids (TDS) and the feed pressure, respectively.enReverse osmosismembrane foulingFouling IndicesPredicting Modelsmachine learning004670journal article