An electrohydrodynamic (EHD) printing system may include a nozzle having a nozzle opening, a discharge electrode, a voltage source, an imager, and a controller in communication with the voltage source and the imager. The nozzle may be configured to contain ink and discharge the ink through the nozzle opening. The discharge electrode may be configured to be in electrical communication with the ink in the nozzle to apply voltage to the ink and create a jet of the ink discharged from the nozzle opening. The voltage source may be configured to apply the voltage to the discharge electrode. The imager may be configured to image the jet of the ink discharged. The controller may be configured to analyze the images from the imager and output control signals to the voltage source based on an analysis of the images.

A substrate processing apparatus and method capable of responding to jetting abnormalities in real time are provided. The substrate processing apparatus includes: a first stage supporting a substrate; an inkjet head unit ejecting a substrate processing liquid onto the substrate as droplets; a gantry unit moving the inkjet head unit on the first stage; a droplet inspection unit inspecting the droplets; and a control unit performing compensation on the substrate based on results of the inspection of the droplets, wherein the inkjet head unit ejects the substrate processing liquid onto a usage area and a non-usage area of the substrate, and the droplet inspection unit inspects the droplets ejected onto the non-usage area.

A liquid droplet ejection method is provided including capturing an image of a pattern on a substrate, acquiring first image data corresponding to the pattern, and applying the first image data to a machine learning model to perform machine learning and generate liquid droplet ejection conditions based on an electrostatic method. The liquid droplet ejection method described above may further include generating the machine learning model by performing machine learning on pre-acquired first image data.