A framework for tool condition monitoring of abrasive waterjet systems

The study presents an innovative method for developing a waterjet mixing tube process monitoring system, leveraging aluminium oxide abrasives for accelerated data collection. A novel method of recording data during the jet dwell cycle is proposed, which eliminates abrasive from the data collection step and allows for the mixing tube wear state to be predicted before machining takes place. Airflow sensors were shown to be capable of detecting changes in mixing tube exit diameter. The performance of machine learning models, utilizing airflow data, was compared against simpler models using wear time as a sole parameter. Both approaches were tested in their ability to predict the exit diameter and to classify the state of the tool. Although wear time-based models outperformed machine learning models in this study, their ability to adapt to process changes may be limited. Machine learning models, given a larger dataset, may be required for accurate wear detection. The research lays a promising foundation for developing a robust mixing tube monitoring system. Future work should focus on collecting more data, investigating the effect of mixing chamber and orifice wear on the airflow signal, and evaluating model performance trained with accelerated wear data, on tubes worn in a regular wear trial.