GENERATING LEARNED KNOWLEDGE FROM AN EXECUTABLE DOMAIN MODEL

    公开(公告)号:EP3542971A3

    公开(公告)日:2019-12-25

    申请号:EP18214015.2

    申请日:2018-12-19

    IPC分类号: B25J9/16

    摘要: A computer-implemented method for performing autonomous operations in an operating environment includes simulating the operating environment to generate a plurality of examples. Each example comprises (a) signal data describing a scene, (b) one or more objects present in the scene, and (c) a description of characteristics associated with the objects. A machine learning model is trained using the examples to generate a data structure comprising (i) objects associated with a signal and (ii) characteristics corresponding to the objects associated with the signal. A signal sensor of an autonomous device collects an input signal describing a new scene. The machine learning model is used to generate an output data structure based on the input signal. One or more objects are identified using the output data structure. One or more actions are generated for operating the autonomous device based on the characteristics associated with the identified objects.

    SYSTEM AND METHOD FOR GENERATING PROGRAM CODE FOR AN INDUSTRIAL CONTROLLER

    公开(公告)号:EP4089525A1

    公开(公告)日:2022-11-16

    申请号:EP21173614.5

    申请日:2021-05-12

    IPC分类号: G06F8/35 G06F16/36

    摘要: The invention relates to a system and a method for generating program code (AS) for an industrial controller, the method comprising: in a first step, storing first ontology (MSO) of a modelling system and second ontology (ESO) of an industrial engineering system in an engineering knowledge graph database (EKG), in a second step, with the modelling system, developing or changing of a system model (SM) of the program code and/or an automation system with the industrial controller, in a third step, based on the first (MSO) and the second ontology (ESO), transforming the system model (SM) into a knowledge graph representation and storing the knowledge graph representation in the engineering knowledge graph database (EKG), in a fourth step, generating, from the data of the engineering knowledge graph database (EKG), the program code (AS) for the industrial controller, and, in a fifth step, storing the program code (AS) in an industrial engineering system. With this, the knowledge graph concept / system is introduced in the code generation workflow and two sets of ontologies are provided to the knowledge graph system to have a common understanding of both worlds. From the knowledge-based representation of the system model a program code in an industrial automation programming language according to IEC 61131-3 standard can be generated.