Monitoring Process Water Quality Using Near Infrared Spectroscopy and Partial Least Squares Regression with Prediction Uncertainty Estimation. Issue 3 (March 2017)

• Record Type: Journal Article
• Authors: Skou, Peter B.; Berg, Thilo A.; Aunsbjerg, Stina D.; Thaysen, Dorrit; Rasmussen, Morten A.; van den Berg, Frans
• Is Part Of: Applied spectroscopy. Volume 71:Issue 3(2017)
• Page Start: 410
• Page End: 421
• Publication Date: 2017-03
• Subjects: Multivariate calibration -- near-infrared spectroscopy -- NIRS -- real-time monitoring -- uncertainty estimation -- water quality; Spectrum analysis -- Periodicals; 543.505
• DOI: 10.1177/0003702816654165
• Languages: English
• ISSNs: 0003-7028

Abstract

Reuse of process water in dairy ingredient production—and food processing in general—opens the possibility for sustainable water regimes. Membrane filtration processes are an attractive source of process water recovery since the technology is already utilized in the dairy industry and its use is expected to grow considerably. At Arla Foods Ingredients (AFI), permeate from a reverse osmosis polisher filtration unit is sought to be reused as process water, replacing the intake of potable water. However, as for all dairy and food producers, the process water quality must be monitored continuously to ensure food safety. In the present investigation we found urea to be the main organic compound, which potentially could represent a microbiological risk. Near infrared spectroscopy (NIRS) in combination with multivariate modeling has a long-standing reputation as a real-time measurement technology in quality assurance. Urea was quantified Using NIRS and partial least squares regression (PLS) in the concentration range 50–200 ppm (RMSEP = 12 ppm, R 2 = 0.88) in laboratory settings with potential for on-line application. A drawback of using NIRS together with PLS is that uncertainty estimates are seldom reported but essential to establishing real-time risk assessment. In a multivariate regression setting, sample-specific prediction errors are needed, which complicates the uncertainty estimation. We give a straightforward strategy for implementing an already developed, but seldom used, method for estimating sample-specific prediction uncertainty. We also suggest an improvement. Comparing independent reference analyses with the sample-specific prediction error estimates showed that the method worked on industrial samples when the model was appropriate and unbiased, and was simple to implement.