Abstract: A method for non-destructive inspection of at least one test object on a workpiece includes the steps of: obtaining a theoretical position of each test object in relation to a testing robot; capturing an image of each test object to obtain image data; determining a real position of each test object in relation to the testing robot on the basis of the image data; and bringing a sensor carried by the testing robot in contact with each test object to obtain a respective test measurement. Where the test instrument needs to be brought in physical contact with the test object, it is crucial to know the exact position of the test object. As soon as an approximate position of the test object is known an image of the test object can be captured, and the exact position of the test object can be extracted from the respective image data.

Abstract: An apparatus for monitoring a switchgear includes: an input unit; a processing unit; and an output unit. The input unit is provides the processing unit with a monitor infra-red image of the switchgear. The processing unit implements a machine learning classifier algorithm to analyse the monitor infra-red image and determine if there is one or more anomalous hot spots in the switchgear. The machine learning classifier algorithm has been trained based on a plurality of different training infra-red images. The plurality of training infra-red images include a plurality of modified infra-red images generated from a corresponding plurality of infra-red images, each of the modified infra-red images having been modified to remove an effect of obscuration in the image. The output unit outputs information relating to the one or more anomalous hot spots.

Abstract: A method for system monitoring in a hierarchical network of distributed edge devices includes a master edge, first and second client edges connected via a first communication interface to the master edge, the method including receiving sensor data from a sensor device via a second communication interface, determining a first local model parameter representing a machine learning (ML) model of the at least first client edge based on the sensor data; storing the first local model parameter in a data storage of the at least first client edge; collecting the first local model parameter from the at least first client edge; and generating a global ML model based on the at least first local model parameter, wherein the global ML model is used for monitoring a system performance or a condition of the system.

Abstract: A system and method for enabling an efficient data processing in a distributed network of devices includes collecting first data from at least one client device sent by at least one plant device via a first communication interface; storing the first data in a data storage; profiling the first data to obtain characteristic information of the collected first data; determining a data processing strategy upon a result of the characteristic information of the first data; processing the first data according to the data processing strategy and deciding which data of the first data need to be sent to the master device via a second communication interface.

Abstract: A method for producing hydrogen using two types of electrolysis systems, the first having an active DC module and at least one first-type electrolyzer producing a first hydrogen output by using a first power from the active DC module, and the second electrolysis system having a passive DC module and at least one second-type electrolyzer producing a second hydrogen output by using a second power from the passive DC module. The method includes increasing the first hydrogen output and when it crosses a first predefined hydrogen output threshold, switching on the second electrolysis system and decreasing the first hydrogen output of the first electrolysis system to the first predefined hydrogen output threshold minus the second hydrogen output, so that an overall hydrogen output of the hydrogen production plant is a sum of the first hydrogen output and the second hydrogen output.

Abstract: A method for determining the state of health of an industrial process executed by at least one industrial plant comprising an arrangement of entities, and the state of each such entity, includes obtaining values of the entity state variables; providing the values to a model to obtain a prediction of the state of health; determining propagation paths for anomalies between said entities; determining importances of the states of health of the individual entities for the overall state of health of the process; and aggregating the individual states of health of the entities to obtain the overall state of health of the process.

Abstract: A method for training a prediction model includes obtaining training samples representing states of the process that do not cause the undesired event; obtaining based on a process model and a set of predetermined rules that stipulate states having an increased likelihood of the undesired event occurring; training samples representing states with an increased likelihood to cause the undesired event; providing samples to the to-be-trained prediction model to obtain a prediction of the likelihood for occurrence of the undesired event in a state of the process represented by the respective sample; rating a difference between the prediction and the label of the respective sample using a predetermined loss function; and optimizing parameters such that, when predictions are made, the rating by the loss function improves.

Abstract: A computer-implemented method for orchestrating execution of workloads on nodes includes determining a set of requirements for resources needed for execution of the workload; determining for each compute node an availability of the resources required; establishing multiple candidate configurations having an assignment of each compute workload to at least one pair of a compute node and a working class, wherein different working classes differ at least in the degree of retention of the compute workload in memory and/or in at least one cache of the compute node after execution; computing for each candidate configuration at least one figure of merit with respect to at least one given optimization goal; and determining a candidate configuration with the best figure of merit as the optimal configuration.

Abstract: A method for providing an efficient communication in a hierarchical network of distributed devices includes collecting first data from a first client device sent by a sensor via a second communication interface; storing the first data in a data storage; determining metadata of the first data; receiving a requirement information of the first data; generating classification information of the first data according to the metadata and the requirement information; providing the classification information to a master device and/or to a second client device according to a rule; and updating the classification information when the first data is changed.

Abstract: A method for reading a digital graphical diagram representing an electric circuit is provided. The graphical diagram includes one or more diagram pages, each representing a portion of the electric circuit. The method includes for each diagram page detecting the graphical objects included in the diagram page, for each diagram page basing on the detected graphical objects, obtaining predictive information related to the components included in the portion of electric circuit represented in the diagram page, and for each diagram page harmonizing the predictive information related to the components of the portion of electric circuit represented in the diagram page to obtain an identification list of the components of the electric circuit.

Abstract: A medium voltage circuit breaker switching pole includes: a fixed contact of a vacuum interrupter; a movable contact of the interrupter; and a threaded drive element. The movable contact moves along a longitudinal axis of the interrupter. A center axis of the drive element is parallel to the longitudinal axis of the interrupter. When in an open configuration the fixed contact and movable contact are separated from one another. When in a closed configuration the fixed contact and movable contact are in contact with one another. Rotation of the drive element about its center axis in a first direction is transitions the switching pole from the open configuration to the closed configuration. Rotation of the drive element about its center axis in a second direction counter to the first direction transitions the switching pole from the closed configuration to the open configuration.

Abstract: A system and method for nuisance-trip decision management in an electric power system using data analytics comprising, a protection system, PS, and at least one electrical protection circuit, EPC. The PS comprising, a plurality of sensors configured to measure data; a memory configured to store an updated data of nuisance-trip events and a plurality of nuisance-trip parameters detected or generated on the electric power system over a period; a processor configured to perform hybrid machine learning (HML) based on the measured data from the plurality of sensors for a nuisance-trip condition and communicate with a neighboring PS; a protection microcontroller configured to allow or avoid tripping at least one electronic tripping circuit provided in the at least one EPC by communicating with the processor and the neighboring PS.

Abstract: A system and method for heavy-current charging cables for charging an electric vehicles includes a central heavy-current wire extending in a longitudinal direction, a plurality of heavy-current power wires comprising a power conductor and a power wire insulation surrounding said power conductor, the heavy-current power wires extending parallel to the central wire, a liquid tight inner hose extending in the longitudinal direction and surrounding the heavy-current central wire and the heavy-current power wires thereby defining a first hollow area comprising liquid coolant to flow between the heavy-current central wire and the heavy-current power wires along the longitudinal direction, and a liquid tight outer hose extending in the longitudinal direction and surrounding the inner hose thereby defining a second hollow area comprising liquid coolant to flow between the inner hose and the outer hose along the longitudinal direction.

Abstract: A connector for electric vehicle supply equipment includes: a housing that includes one or more electrical coupling members that are connectable between the electric vehicle supply equipment and a mating inlet of an electric vehicle to supply electric power to the vehicle. The housing includes a sensor for detecting light within the housing and outputting a signal in response to a detection of light within the housing to interrupt or disable the supply of electric power to the vehicle through the connector.

Abstract: Described herein is a switch pole for a low voltage switching device including an insulating casing defining an internal space with a contact area and an arc-extinguishing area of the switch pole, a fixed contact assembly and a movable contact assembly positioned in the contact area and including, respectively, one or more fixed contacts and one or more movable contacts, which can be mutually coupled or uncoupled, and an arc chamber positioned in the arc-extinguishing area that includes a plurality of parallel arc-breaking plates. The insulating casing includes an insulating wall partially separating the contact area from the arc-extinguishing area and a channel connects the contact area to the arc-extinguishing area. The switch pole further includes an additional arc-breaking element anchored to the insulating wall, passing through the channel of the insulating wall and arranged in electrical connection with a terminal arc-breaking plate of the arc chamber.

Abstract: A field of electric drive devices and electric machines, such as electric motors and electric generators for industrial applications and more particularly to a method and an arrangement for controlling vibration of a variable frequency drive controlled electric machine. In the method for controlling vibration of a variable frequency drive controlled electric machine, the resonance frequency/frequencies and the stiffness are determined in a ramp up/ramp down test; amount of damping is determined in an impulse test; a mechanical transfer function is determined in a steady drive test; a vibration control model is determined utilizing said resonance frequency/frequencies, said stiffness, the amount of damping and the mechanical transfer function; and vibration is controlled utilizing the vibration control model.

Abstract: Embodiments of present disclosure relate to an apparatus and a method for separating objects. The apparatus comprises: a separating mechanism configured to separate objects arranged in a stack; a robot configured to hold the separating mechanism; and a controller configured to: cause the robot to move the separating mechanism to a first height; cause the robot to move the separating mechanism towards the stack; in response to a distance between the separating mechanism and the stack reaching a distance threshold, cause the robot to stop moving the separating mechanism; and cause the separating mechanism to separate the objects.

Abstract: A packing cell for packing products in boxes includes a picking system for picking products and stacking them according to a stacking pattern, a support unit for the stacking process, with a rotatable horizontal shaft for placing a support platform in a predetermined angular position for the stacking process, and a box handling robot to transfer empty boxes towards the support unit and full boxes away from the support unit. A method includes placing the support platform in a predetermined angular position adjacent a product picking system, picking and stacking a number of products according to a stacking pattern on the support unit, and removing from the support unit, with a box handling robot, a box containing the stacked products.

Abstract: A voltage sensor is disclosed for high and medium voltage use, wherein a voltage divider is arranged in a housing with external creepage distance enlarging ribs. To implement structures for creepage path enlargement to a sensor housing in a very effective and easy way, the voltage divider is arranged in a housing or in housing modules which is or are covered at least partly by at least one shrinking tube of insulating material such that the shrinking creepage enlarging structures are implemented at least at outer surface of the shrinking tube.

Abstract: A strike pin assembly for a fuse assembly in which the strike pin assembly is maintained in a locked position by a holding force of a filament and an interference provided by a plurality of retention bodies. Upon a breakage of the filament, such as, for example, in response to heat generated by operation of a fuse element, a trigger can be displaced via a first biasing force in a distal direction such that the trigger is positioned at a location that does not impede an inward displacement of a plurality of retention bodies from a recess of a firing pin. Upon the inward displacement of the retention bodies, a second biasing force can displace the firing pin in the distal direction such that a portion of the firing pin can protrude out from an adapter of the strike pin assembly.