Forecasting multicycle hollow fiber ultrafiltration fouling using time series analysis

This study proposes the application of time series analysis and exponential smoothing (ETS) to predict multicycle membrane fouling with high accuracy and great interpretability. First, lab-scale filtration tests were performed with foulant surrogates to assess the potential of ETS models in predicting multicycle membrane fouling. Two models, ETS (A,A,A) and ETS (A,A,M), were found to be most suitable for describing the variation of trans membrane pressure. The ETS (A,A,A) model showed a slight edge over the ETS (A,A,M) model when reversible fouling was dominant. In contrast, the ETS (A,A,M) performed better when irreversible fouling was prevalent. Then, the effectiveness of ETS models in multicycle forecasting during the filtration of natural water resources was evaluated. Residual mean squared errors between 0.02 bar and 0.15 bar were obtained for horizons going from 2 up to 10 filtration cycles. Finally, ETS models were applied to predict the variation in permeability of drinking water treatment plant membrane skid. A three-month dataset was utilized to predict the next 41 days of permeability variation, yielding an average error of 3.2 %. Along with that, a web application designed to assist membrane users in utilizing ETS was developed and presented at the end. The web application can be accessed through the following link: https://fouling-ets.shinyapps.io/shiny-ets-forecasting/.

Automated summary

This study proposes the application of time series analysis and exponential smoothing (ETS) to accurately predict multicycle membrane fouling. The ETS models showed great interpretability and were found to be effective in both lab-scale filtration tests and natural water resources filtration. Additionally, the ETS models were applied to predict the permeability variation of drinking water treatment plant membrane skid, yielding satisfactory results. A web application was also developed to assist membrane users in utilizing ETS models.