Enhanced Clean-In-Place Monitoring Using Ultraviolet Induced Fluorescence and Neural Networks

Abstract

Clean-in-place (CIP) processes are extensively used to clean industrial equipment without the need for disassembly. In food manufacturing, cleaning can account for up to 70% of water use and is also a heavy user of energy and chemicals. Due to a current lack of real-time in-process monitoring, the non-optimal control of the cleaning process parameters and durations result in excessive resource consumption and periods of non-productivity. In this paper, an optical monitoring system is designed and realized to assess the amount of fouling material remaining in process tanks, and to predict the required cleaning time. An experimental campaign of CIP tests was carried out utilizing white chocolate as fouling medium. During the experiments, an image acquisition system endowed with a digital camera and ultraviolet light source was employed to collect digital images from the process tank. Diverse image segmentation techniques were considered to develop an image processing procedure with the aim of assessing the area of surface fouling and the fouling volume throughout the cleaning process. An intelligent decision-making support system utilizing nonlinear autoregressive models with exogenous inputs (NARX) Neural Network was configured, trained and tested to predict the cleaning time based on the image processing results. Results are discussed in terms of prediction accuracy and a comparative study on computation time against different image resolutions is reported. The potential benefits of the system for resource and time efficiency in food manufacturing are highlighted.

Intelligent Industrial Cleaning: A Multi-Sensor Approach Utilising Machine Learning-Based Regression

“…With reference to CIP processes, the literature reports a number of image segmentation procedures for food fouling detection. A review reported in [14] compares Otsu, Iteration method, 1D and 2D entropy. Fuzzy c-means (FCM) clustering [32,33] is a powerful clustering algorithm that allows each data point to belong to multiple clusters with varying degrees of membership.…”

“…A time series prediction-based intelligent decision-making support system is developed in [14] utilizing nonlinear autoregressive models with exogenous inputs (NARX) Neural Network was adopted and configured, trained, and tested to predict the cleaning time based on the image processing results.…”

“…As regards fouling volume charts, the fluctuations are due to the small size of the ROI and the transient nature of the fouling, i.e., during the cleaning process, fouling may temporarily increase in the ROI as it is moves across the surfaces [14,16].…”

Sensors support machine learning

“…The University of Nottingham has been working with Loughborough University and several industrial partners, funded through Innovate UK projects, to develop an intelligent multi‐sensor technology to monitor the removal of surface fouling during cleaning of processing equipment [4, 7] .…”

Clean-in-place monitoring of different food fouling materials using ultrasonic measurements

“…(Pereira, Mendes, & Melo, 2009) (P. M. Withers, 1996) (Úbeda, Hussein, Hussein, Hinrichs, & Becker, 2016)). Optical sensors utilising ultraviolet fluorescent techniques have also been used to monitor cleaning processes (P. M. Withers, 1996) (Simeone, Deng, Watson, & Woolley, 2018) (Simeone et al, 2016) and a fibre optical device has been used to monitor biofilm fouling in a brewery water pipe (Tamachkiarow & Flemming, 2003). However, optical imaging technologies require lighting to enable imaging of the surface under investigation so they would not be suitable in pipes or processing equipment where suitable illumination would be extremely challenging (e.g.…”