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

Abstract

<jats:p>Effectively cleaning equipment is essential for the safe production of food but requires a significant amount of time and resources such as water, energy, and chemicals. To optimize the cleaning of food production equipment, there is the need for innovative technologies to monitor the removal of fouling from equipment surfaces. In this work, optical and ultrasonic sensors are used to monitor the fouling removal of food materials with different physicochemical properties from a benchtop rig. Tailored signal and image processing procedures are developed to monitor the cleaning process, and a neural network regression model is developed to predict the amount of fouling remaining on the surface. The results show that the three dissimilar food fouling materials investigated were removed from the test section via different cleaning mechanisms, and the neural network models were able to predict the area and volume of fouling present during cleaning with accuracies as high as 98% and 97%, respectively. This work demonstrates that sensors and machine learning methods can be effectively combined to monitor cleaning processes.</jats:p>

Machine Learning Algorithms Used in PSE Environments: A Didactic Approach and Critical Perspective

“…213 PSE applications turn around process monitoring and control, as well as product properties prediction. Simeone et al 214 present the design of an intelligent cleaning system using a monitoring process approach coupled to sensor strategies and image processing. Chakraborty et al 215 implement an hybrid modeling using ANN and regression trees for a process monitoring strategy.…”

Spatial ultrasonic cleaning process control based on its current state evaluation

“…More flexible is the formation of assessment based on machine learning, which was used in [5] and [6]. In these works, the condition of the treatment facility (in both cases, part of the pipe) was assessed by applying a neural network to the received ultrasound responses.…”

Convolutional feature extraction for process monitoring using ultrasonic sensors

“…Nevertheless, this is still a coarse method of monitoring waveform changes, which are indirectly measured rather than directly identified. Signal features similar to those previously listed can also be extracted in the frequency domain, commonly after using the discrete wavelet transform (Cau et al, 2005, Simeone et al, 2020. However, US transducers used for material characterisation typically have narrow frequency bands.…”