Long-Term Statistical Process Monitoring of an Ultrafiltration Water Treatment Process

TL;DR

This paper evaluates long-term fault detection in an ultrafiltration water treatment process using statistical and machine learning methods.

Contribution

The study introduces a long-term evaluation of multivariate monitoring for water treatment, emphasizing parameter tuning for autonomous performance.

Findings

Adaptive lasso detrending was selected as the best method for long-term monitoring.

Multivariate monitoring outperformed univariate methods and daily pressure decay tests over a year.

Careful tuning of three critical parameters is essential for successful long-term monitoring.

Abstract

As water treatment
technology has improved, the amount of available
process data has substantially increased, making real-time, data-driven
fault detection a reality. One shortcoming of the fault detection
literature is that methods are usually evaluated by comparing their
performance on hand-picked, short-term case studies, which yields
no insight into long-term performance. In this work, we first evaluate
multiple statistical and machine learning approaches for detrending
process data. Then, we evaluate the performance of a PCA-based fault
detection approach, applied to the detrended data, to monitor influent
water quality, filtrate quality, and membrane fouling of an ultrafiltration
membrane system for indirect potable reuse. Based on two short case
studies, the adaptive lasso detrending method is selected, and the
performance of the multivariate approach is evaluated over more than
a year. The method is tested for different sets of three critical
tuning parameters, and we find that for long-term, autonomous monitoring
to be successful, these parameters should be carefully evaluated.
However, in comparison with industry standards of simpler, univariate
monitoring or daily pressure decay tests, multivariate monitoring
produces substantial benefits in long-term testing.

Figures