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: An apparatus for extracting common command information from programmable logic controller (PLC) ladder information according to the present invention may include: a logic information extracting portion configured to extract control logic information from XML information converted from PLC ladder information; and a common command converting portion configured to convert the control logic information extracted by the logic information extracting portion into common command information, wherein the logic information extracting portion is configured to extract, from the XML information, the control logic information in the form of a block obtained by grouping units that respectively represent contacts and lines constituting the PLC ladder information according to an AND condition and an OR condition.

Abstract: A method, of training an anomaly detecting model using a plurality of pieces of graph data, includes: (a) inputting one piece of graph data that has not yet been input, among the plurality of pieces of graph data, to a graph neural network (GNN) AutoEncoder calculating a probability of each edge as input data; (b) calculating a difference value (hereinafter, “edge difference value”) between an edge probability value of reconstructed data output by the GNN AutoEncoder and an edge value of the input data; (c) calculating an average value (hereinafter, “positive edge loss”) of a positive edge and an average value (hereinafter, “negative edge loss”) of a negative edge using the edge difference value, and calculating an edge prediction loss value of the reconstructed data by summing the positive edge loss and the negative edge loss; (d) retraining the GNN AutoEncoder until the edge prediction loss value is minimized.

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: Disclosed is a method of analyzing a programmable logic controller (PLC) logic to detect whether an anomaly that deviates from a standard pattern occurs in a repeated cycle. After modeling and patterning an operation pattern of automation equipment and processes with a graph, an anomaly detecting model capable of detecting whether a pattern is abnormal may be constructed as a graph AutoEncoder model. By detecting the change in the process pattern, it is possible to early detect the anomaly of the equipment and processes.

Abstract: A method of alarming an abnormal state of a line of an automated manufacturing system using a programmable logic controller (PLC) signal pattern is provided.

Abstract: Disclosed are a PLC (Programmable Logic Controller) symbol structure for a PLC code for automatically generating an input/output model, and a simulation apparatus and a simulation method for testing the PLC code using the same. In one embodiment, a computer-readable recording medium records a PLC code including a plurality of PLC symbols, wherein each of the PLC symbols includes a plurality of levels identified by an identifier, and a computer automatically generates an input/output model using the structure of each of the PLC symbols, thereby performing a simulation for testing the PLC code. The PLC symbol structure according to one embodiment systematically contains information required for automatically generating the input/output model, making it possible to automatically generate the input/output model for testing the PLC code in an easier manner without knowledge of simulation and modeling, and reducing the time consumed and the labor required for generating the input/output model.

Abstract: A multiple programmable logic controller (PLC) simulation system is provided.

Abstract: A multiple programmable logic controller (PLC) simulation system is provided.

Abstract: An apparatus and method for distinguishing between tack-welding and welding are provided. The apparatus for distinguishing between tack-welding and welding includes: a current sensor configured to detect arc current of a welder; and a distinguish control unit configured to distinguish whether a welding operation performed by the welder is tack-welding or welding based on the arc current detected by the current sensor for a predefined period of time. Accordingly, the amount of work performed by a welding worker can be fairly and accurately evaluated.

Abstract: Provided are a system and a method for monitoring welding operations. The system includes a welding machine, a current sensor sensing an operation time of the welding machine and a welding current, a welding information database storing information of the operation time of the welding machine and the welding current for each welding operator and storing information of a consumed charge amount of the welding machine, which is preset for each welding operation process, a data analyzer checking a charge amount consumed for the operation time by using the sensed operation time of the welding machine and the welding current and determining whether the welding operator achieves a task goal of a corresponding process by comparing the checked consumed charge amount with the preset consumed charge amount for a process performed by the welding machine, and a display unit outputting a result of the determining, performed by the data analyzer, whether the welding operator achieves a task goal of a corresponding process.

Abstract: Disclosed are a PLC (Programmable Logic Controller) symbol structure for a PLC code for automatically generating an input/output model, and a simulation apparatus and a simulation method for testing the PLC code using the same. In one embodiment, a computer-readable recording medium records a PLC code including a plurality of PLC symbols, wherein each of the PLC symbols includes a plurality of levels identified by an identifier, and a computer automatically generates an input/output model using the structure of each of the PLC symbols, thereby performing a simulation for testing the PLC code. The PLC symbol structure according to one embodiment systematically contains information required for automatically generating the input/output model, making it possible to automatically generate the input/output model for testing the PLC code in an easier manner without knowledge of simulation and modeling, and reducing the time consumed and the labor required for generating the input/output model.