Real-time leakage predictions of pneumatic controlled actuator during cycle test using machine learning

The pressure decaying test is traditionally used to detect leakage in pneumatic actuators; however, it is time-consuming as it is performed between cycles of actuation. To date, there is a notable lack of real-time, data-driven machine learning methods to detect such leakages. Such leakage prediction is important to determine the lifecycle of the actuator and the exerting force to seal the vacuum chamber. This study aims to employ machine learning techniques to predict the categories of normal and leaked pressure loss ratio (PLR) in real-time during different number of pneumatic actuators cycles. The data was collected using a two-way factorial design with center points for the cycle test setting parameters. Seven parameters were recorded and undergo the training and test phase. Additionally, multiple model architecture was employed, each performing binary classification for each class to predict the PLR. Correlation analysis shows that pressure reading of each "open" and "close" inlets have better correlation for predicting the leakage with 0.216 and 0.183 respectively. The top performing model for each class is K-Nearest Neighbors (KNN) and Multilayer Perceptron (MLP). For the model 1, the KNN model achieved the highest accuracy of 93.86%, with an AUC of 0.94 in ROC analysis. Meanwhile, for the Model 2, utilizing MLP model attained an accuracy of 89.36% and an 84.87% mean-harmonic score. This study demonstrates that real-time machine learning can effectively predict leakage in pneumatic actuators, with the potential for further improvement through the inclusion of more data and increased setting points in the cycle test.