Method, computing device and computer program for detecting abnormal behavior of process equipment

A method of detecting abnormal behavior of process equipment by one or more processors of a computing device, the method comprising:

• obtaining process sensor data and prior knowledge data corresponding to the process sensor data;
• generating reconstruction process sensor data, which corresponds to the process sensor data, using a deep learning model;
• calculating a reconstruction rate error on the basis of the process sensor data and the reconstruction process sensor data;
• and
• detecting abnormal behavior on the basis of a comparison between the reconstruction rate error and a reference threshold,
• wherein the process sensor data is obtained in real time through a plurality of sensors on the basis of operation of semiconductor process equipment and comprises a plurality of pieces of sensor data related to normal behavior, and the prior knowledge data comprises relationship information between the plurality of sensors, and
• wherein the deep learning model comprises:
• a first sub-model configured to output feature information corresponding to the process sensor data;
• a second sub-model configured to extract interrelationship information between pieces of the process sensor data on the basis of the process sensor data and the prior knowledge data;
• an attention module configured to generate feature information by combining outputs of the first sub-model and the second sub-model;
• and
• a dimension restoration model configured to generate the reconstruction process sensor data by restoring the feature information.