Prediction of Ejection State for a Pneumatic Valve-Controlled Micro-Droplet Generator by a BP Neural Network

Abstract

Pneumatic valve-controlled micro-droplet generation is a printing technique that has potential applications in many fields, especially in the field of biomedical printing. The droplet generation is controlled by a solenoid valve being briefly turned on, so that high pressure gas enters the liquid reservoir, forming a gas pressure pulse P(t), forcing the liquid out through a tiny nozzle to form a micro-droplet. Under the typical working conditions, P(t) is not consistent. Since P(t) is highly correlated with the micro-droplet ejection state, the inconsistency of P(t) results in fluctuation of ejection state. For each injection, the P(t) is acquired by a high speed pressure sensor, and the ejection state is obtained by machine vision processing. A machine learning method based on BP neural network is used to establish a prediction model with P(t) as the input and the droplet ejection state as the output. Experiments show that a BP neural network with only a single hidden layer and two neurons can accurately predict the number of droplets with an accuracy higher than 99%. Another experiment shows that a more complex double hidden layer BP neural network can improve the prediction accuracy for the position of droplets after a certain time delay. In summary, through pressure pulse P(t), the predictive model established by the machine learning method can effectively predict the micro-droplet ejection state. This technique may be used for real time monitoring and control of the pneumatic valve-controlled micro-droplet generator.