Substrate inspection apparatus and method of determining fault type of screen printer

A substrate inspection apparatus, comprising:

• a memory configured to store a machine-learning-based model which has been trained to:
• derive a plurality of values indicating relevance of respective first fault types of a screen printer to an image indicating a plurality of solder pastes with anomalies detected;
• and
• generate a plurality of images indicating regions associated with one of a plurality of first fault types by using the image indicating the plurality of solder pastes with anomalies detected;
• and
• a processor electrically connected to the memory,
• wherein the processor is configured to:
• when anomalies of a plurality of second solder pastes among a plurality of first solder pastes printed on a first substrate is detected based on an image about the first substrate, generate at least one image indicating the plurality of second solder pastes by using the image about the first substrate;
• apply the at least one image to the machine-learning-based model;
• acquire, from the machine-learning-based model, a plurality of first values indicating relevance of the respective first fault types to the at least one image and a plurality of first images indicating regions associated with one of the plurality of first fault types;
• determine a plurality of second fault types, which are associated with the plurality of second solder pastes, among the plurality of first fault types based on the plurality of first values;
• and
• determine at least one third solder paste, which is associated with the respective second fault types, among the plurality of second solder pastes based on a plurality of second images, which correspond to the plurality of second fault types, among the plurality of first images.