Bayesian and ultrasonic sensor aided multi-objective optimisation for sustainable clean-in-place processes

In food and drink manufacturing, clean-in-place procedures are essential for hygienic and efficient operations but often over-clean process equipment leading to unnecessary use of energy, water, and chemicals. Previous attempts in the literature to optimise clean-in-place processes have focused on trialling cleaning over a range of parameter (e.g. temperature and chemical concentration) combinations or modelling the process using equations. However, these methods do not aim to minimise the number of experimental trials that a manufacturer must conduct and only determine the optimal cleaning parameters for the average fouling condition. In this work, Bayesian optimisation is used to minimise the number of cleaning parameter combinations that require trialling thereby reducing the disruption to a manufacturing process during the optimisation procedure. Secondly, ultrasonic sensors are used to monitor the cleaning process and enable real-time optimisation of the parameters to adapt to variations in the fouling condition. Multi-objective optimisation was used in both tasks to simultaneously minimise the economic cost, carbon footprint, and water usage of a clean-in-place process. Bayesian optimisation was able to optimise the process after trialling only nine cleaning parameter combinations (achieving between 98.7% and 100% optimisation of the objective function compared with the global optimum). Bayesian optimisation displayed a small advantage (0.0–4.7% decrease in the objective function) compared with methods used in previous literature. Real-time optimisation of the cleaning parameters using ultrasonic sensor data improved the optimisation objective function by 0.0 – 4.8% for all fouling instances tested when utilising results from ten trials conducted during the Bayesian optimisation procedure along with five additional cleaning processes under normal operation. •A clean-in-place process was optimised for cost, carbon footprint, and water use.•Bayesian optimisation used to minimise number of parameter combinations trialled.•Optimal solution found after only nine cleaning parameter combination trials.•Ultrasonic sensors used for real-time optimisation of the clean-in-place process.•This provided up to 4.8% further improvement to the multi-objective optimisation.