METHOD FOR FORMULATION AND MODELLING OF INTENTIONS IN PROCESS PLANT ENGINEERING

    公开(公告)号:WO2022263168A1

    公开(公告)日:2022-12-22

    申请号:PCT/EP2022/064787

    申请日:2022-05-31

    Applicant: ABB SCHWEIZ AG

    Abstract: The invention relates to a method for formulation and modelling of intentions in process plant engineering, comprising the steps: formulating (S10), by an assistance system (100), intentions of an actor (A1, A2) by guiding the actor (A1, A2) to provide the intentions (I) to the assistance system (100) in a controlled natural language using semi-formal phrases (P), wherein the intentions (I) are hierarchically structured and comprises at least a goal (IG), describing a goal to be achieved, at least an implementation (II), describing how the goal can be achieved, and at least an requirement (IR), describing requirements for the at least one implementation (II); translating (S20), by the assistance system (100), the intentions (I) into an intention model (MI) wherein the intention model (MI) describes a relationship between the intentions (I); transforming (S30), by the assistance system (100), the intention model (MI) into a graphical representation (RG) of the intention model (MI) and providing the graphical representation (RG) to the actor (A1, A2); modeling (S40), by the assistance system (100), the intention model (MI) using modelling data (DM) provided by the actor (A1, A2), wherein the graphical representation (RG) allows the actor (A1, A2) to provide the modelling data (DM) to the assistance system (100).

    SYSTEM FOR A CHEMICAL AND/OR ELECTROLYTIC SURFACE TREATMENT OF A SUBSTRATE

    公开(公告)号:WO2022258216A1

    公开(公告)日:2022-12-15

    申请号:PCT/EP2021/085251

    申请日:2021-12-10

    Applicant: SEMSYSCO GMBH

    Abstract: The present invention relates to a system of at least two distribution body elements for a chemical and/or electric surface treatment of a substrate, a modular distribution body comprising such a system and a manufacturing method for at least two distribution body elements. In the system of at least two distribution body elements, each distribution body element has a plate shape and comprises jet openings for distributing a process fluid from inside the distribution body element to the substrate to be treated and drain openings for distributing the process fluid and an electric current through the distribution body element. Each distribution body element has a connecting area configured to be connected to a connecting area of another distribution body element to form a modular distribution body comprising at least two distribution body elements.

    AEROSOL-GENERATING DEVICE WITH GESTURE CONTROL

    公开(公告)号:WO2022234012A1

    公开(公告)日:2022-11-10

    申请号:PCT/EP2022/062144

    申请日:2022-05-05

    Abstract: An aerosol-generating device, an aerosol-generating system and a method of operating an aerosol-generating device or system are provided. The aerosol-generating device comprises motion detection circuitry including at least one motion sensor and a motion sensor controller configured to process motion sensor data of the at least one motion sensor into gesture data indicative of a gesture performed on the aerosol-generating device by movement of the aerosol-generating device. The aerosol-generating device further comprises device control circuitry including one or more device processors configured to determine, based on analyzing the gesture data provided by the motion sensor controller of the motion detection circuitry, the gesture performed on the aerosol-generating device and to control the aerosol-generating device to perform at least one device function in response to the determined gesture.

    TRAINING PREDICTION MODELS FOR PREDICTING UNDESIRED EVENTS DURING EXECUTION OF A PROCESS

    公开(公告)号:WO2023088665A1

    公开(公告)日:2023-05-25

    申请号:PCT/EP2022/080267

    申请日:2022-10-28

    Applicant: ABB SCHWEIZ AG

    Abstract: A method (100) for training a prediction model (1) for predicting the likelihood that at least one predetermined undesired event will occur during execution of a process (2) using training samples (3), wherein each training sample (3) comprises data that characterizes a state of the process (2), and the method (100) comprises the steps of: obtaining (110) training samples (3) representing states of the process (2) that do not cause the undesired event, and labelling these training samples with a pre-set low likelihood of the undesired event occurring; obtaining (120), based at least in part on a process model (2a) and a set of predetermined rules (2b) that stipulate in which states of the process (2) there is an increased likelihood of the undesired event occurring, further training samples (4) representing states of the process (2) with an increased likelihood to cause the undesired event, and labelling these training samples (4) with said increased likelihood; providing (130) training samples (3, 4) to the to-be-trained prediction model (1), so as to obtain, from the prediction model (1), a prediction (5) of the likelihood for occurrence of the undesired event in a state of the process (2) represented by the respective sample (3, 4); rating (140) a difference between the prediction (5) and the label of the respective sample (3, 4) by means of a predetermined loss function (6); and optimizing (150) parameters (1a) that characterize the behavior of the prediction model (1), such that, when predictions (5) on further samples (3, 4) are made, the rating (6a) by the loss function (6) is likely to improve.

Patent Agency Ranking