Abstract: A method of inspecting a programmable logic controller (PLC) control logic using a graphic neural network (GNN) generally includes three operations: a data preprocessing operation for a GNN, an operation of predicting whether tags are connected, and an operation of verifying suitability of edge connections between tags. As a result, a graph is generated from a PLC control logic and input to a link prediction model to find an incorrect connection in the PLC control logic. Subsequently, a result graph output through the link prediction is input to a trained model to verify edge connection suitability between tags. Then, it may be finally verified whether tags are connected in the PLC control logic.

Abstract: The present disclosure discloses a master pattern generation method which is a major pattern in a repeated cycle by analyzing programmable logic controller (PLC) logic, and a method for training a model that may analyze an error of a cycle using the generated master pattern. The master pattern generation method and the training method for a cycle analysis model according to the present disclosure are different from the related art in that the methods are a technology of processing a machine control language (low-level language) that is difficult for humans to analyze and converting the machine control language into an analyzable language (high-level language), i.e., a machine language processing (MLP)-based technology that analyzes the executed machine language (a language that controls a machine) with a computer and cats be understood by humans.