Abstract: A method for compensating imprecise user input in the maneuvering of a vessel detects the environment of the vessel; determines at least one distance to an object in the environment of the vessel while the vessel is operated using at least one control command originating from an operator of the vessel; the at least one distance being related to a corresponding point on the vessel; analyzes the at least one distance and determines, based on the analysis, at least one compensation for the at least one control command, and provides the at least one control command compensation for use in the operation of the vessel being performed by the operator.

Abstract: A method for assisting an operator in collision avoidance for a first vessel traveling in a present passage along a route in a body of water as well as to such a first vessel includes detecting a risk situation for the first vessel involving a possible collision with an object; determining a number of parallel collision avoidance schemes; presenting the collision avoidance schemes to the operator; selecting one of the collision avoidance schemes; performing collision avoidance according to the selected collision avoidance scheme and displaying a progress of the first vessel according to the selected collision avoidance scheme together with the non-selected collision avoidance schemes.

Abstract: A computer implemented method for monitoring the lead through teaching of a robot in a human robot collaboration environment, comprising: receiving a velocity vector of an element of the robot; receiving a force vector of the of the element of the robot; determining a safety result based on the received velocity vector and the received force vector; and triggering a safety stop based on the determined safety result.

Abstract: A method for aggregating outputs of multiple language models determines calibration information of each of the multiple LMs using at least one calibration question; obtains, from each of the multiple LMs, an original answer based on an original question; obtains, from each of the multiple LMs, an estimation answer based on an estimation question using the determined calibration information, wherein the estimation question asks for a most popular answer to the original question among the multiple LMs; and determines a predicted answer to the original question by aggregating sets of same original answers and same estimation answers.

Abstract: A converter for transferring power from a medium-voltage, MV, to a low-voltage, LV, side is provided. The converter includes at least one DC/AC cell with a MV AC terminal configured for generating an AC voltage from a MV DC voltage, and includes at least one AC/DC cell with a LV AC terminal configured for generating a DC voltage from a LV AC voltage. The converter has a magnetic core with a LV winding, and a LV terminal connected to the LV AC terminal, additionally with a magnetic core with a MV winding, and a MV terminal connected to the MV AC terminal. The converter includes an auxiliary unit with an auxiliary winding, and an auxiliary terminal connected to control circuits for operating the MV DC/AC cell. Galvanic insulation between the LV and the MV winding and the auxiliary winding is configured to withstand the Basic Insulation Level of the converter.

Abstract: A method of controlling a vessel having a plurality of thrusters, where the vessel is configured to operate in a bias mode where at least two of the thrusters provide thrust forces at least partly in opposite thrust directions, the method including estimating, by a control system, an operational condition associated with the vessel; and commanding, by the control system and based on the estimation, execution of a countermeasure associated with an activation of the bias mode, a deactivation of the bias mode or a change of a bias level of the bias mode. A control system and a vessel are also provided.

Abstract: A modular static transfer switch (STS) assembly comprises a semiconductor powertrain constructed with wide-bandgap transistors. A first input of the STS assembly is electrically coupled to a first power source and a second input of the STS assembly is electrically coupled to a second power source. An output of the STS assembly is electrically coupled to a load, wherein the load is powered using the first power source via the STS modular assembly. A galvanic isolator like relay or contactor or breaker or fuse disconnects any faulty semiconductor powertrain. The STS also comprises a controller to execute the transfer of power supplied to the load from the first power source to the second power source by electrically decoupling the first power source from the load, verifying that the first power source is disconnected from the load, and providing instructions to electrically couple the second power source to the load.

Abstract: A computer-implemented method for configuring a communication network based on a given intent comprising providing communications, the method comprising determining from the given intent by a given orchestration engine a candidate network configuration that, when implemented, causes the given intent to be realized; determining one or more changes to the security posture of the network that result from the candidate network configuration; determining based on a criterion, whether there is sufficient correspondence between the intent and the changes to the security posture; in response to determining that this correspondence is not sufficient, determining at least one amendment to the given intent such that, when a new candidate network configuration is determined based on this amendment to have a better correspondence between the amended intent and the resulting changes to the security posture of the network; and implementing the new candidate configuration in the communication network.

Abstract: A power converter system includes auxiliary resonant commutated pole converter legs, particularly ARCP half-bridge legs, connected in parallel between a common dc system and a common ac system or between two common dc systems. Commutations of the parallel-connected converter legs are initiated by simultaneous commutation commands. A control arrangement is provided to balance a current sharing between the parallel-connected ARCP converter legs by means of having an individual autonomous leg-specific boost current adjustment for each of the parallel-connected ARCP converter legs for adjusting boost currents in a direction that a differential output current is reduced. Each individual boost current adjustment is dependent on the magnitude of the leg current of the respective ARCP converter leg only.

Abstract: A method, an apparatus, a computer readable media, and a computer program product for detecting a gas leak of a gas tank. The method includes obtaining a gas pressure within the gas tank and a temperature of a tank body of the gas tank; determining an internal average temperature of the gas tank based on the gas pressure; determining a temperature rise of the tank body relative to an ambient temperature; and determining at least one additional characteristic quantity associated with the temperature rise of the tank body. A gas leak of the gas tank can be detected by using the internal average temperature of the gas tank, the temperature rise of the tank body, and the at least one additional characteristic quantity to obtain a predicted relationship between the internal average temperature of the gas tank and the temperature rise of the tank body.

Abstract: A method includes obtaining training data from an operation of an industrial process plant; using the training data to train a machine learning model for assisting a plant operation of the industrial process plant; determining several sub-populations in the training data, each relating to a different scenario of an operation of the industrial process plant; determining several performances of the machine learning model, each relating to a different sub-population; determining, based on the performance of each one of the sub-populations, one or more underrepresented sub-populations; and revising, based on the one or more underrepresented sub-populations, the machine learning model for increased consideration of the one or more underrepresented sub-populations when assisting the plant operation of the industrial process plant.

Abstract: A converter comprises a conversion stage and an output protection circuit. The output protection circuit comprises first and second input terminals, and first and second output terminals. The first input and output terminals are on a first voltage level, and the second input and output terminals are on a second voltage level. A switch is connected between the first input and output terminals, or between the second input and output terminals, and an interruptible freewheeling circuit is connected between the first and second output terminals. The freewheeling circuit comprises a freewheeling path including a freewheeling switch and a freewheeling diode, and a voltage clamping device parallel to at least the freewheeling switch.

Abstract: A method for enabling power origin labelling processing with increased security in an industrial context includes providing, at a device configured to generate power origin labels, a hardware-protected storage for storing signing keys that are bound to the device and that are to be used by a power origin labelling algorithm for calculating the power origin labels; providing, at the device, a trusted execution environment, TEE, for the power origin labelling algorithm to be implemented and/or executed in the TEE; and providing, at the device, a remote attestation mechanism for an external party to verify the power origin labelling algorithm and/or the device.

Abstract: A knowledge graph generation system includes an input unit and a knowledge graph generator. The input unit receives service reports, each comprising natural language; and provides the service reports to the knowledge graph generator. The knowledge graph generator implements a Large Language Model (LLM), utilizes the LLM to identify entries from the natural language in the service reports, wherein the identified entries comprise names and types of instruments, issues that need to be addressed for those instruments, and actions taken by service technicians to mitigate the issues. The identified entries form rules, each rule comprises a tuple of one instrument type, one issue, and an action step or series of action steps taken to mitigate the issue. The rules are used to generate a plurality of knowledge graph nodes. The knowledge graph generator utilizes the nodes to generate a knowledge graph.

Abstract: A method for making a power origin label trustworthy and verifiable in an industrial context includes obtaining the power origin label that carries information about one or more power origins of power used for production of a product; and adding, to the power origin label, a reference to metadata that provides evidence for the information about the one or more power origins.

Abstract: A method of identifying parameters of a motor system having an electric motor and a control system for vibration reduction, includes: sweeping a frequency of an oscillating reactive torque injected into the motor, determining a natural frequency of the motor system, which is the frequency at which the reactive torque produces maximum amplitude of a vibration-related parameter obtained based on measurements, incrementally increasing a magnitude of reactive torque oscillating at the natural frequency, injected to the motor, obtaining a magnitude of the parameter for each magnitude of the reactive torque, and determining, for each magnitude of the reactive torque, a gain and a phase response of the motor system, the gain being based on the magnitude of the reactive torque and the corresponding magnitude of the parameter, and the phase response being based on a phase angle of the reactive torque and a phase angle of the corresponding parameter.

Abstract: A robot system includes a first group of robot controllers, each including a safety change control unit and each being connected to at least one corresponding manipulator, where one robot controller is a proxy robot controller. The safety change control unit of the proxy receives a request to manually operate at least one joint of at least one of the manipulators via a first point of manual control at one of the robot controllers and forwards it to the others, each safety change control unit determines a response to the request and at least one safety change control unit receives the responses from the other safety change control units, investigates if the responses and request match and denies the request in case at least one response does not match the request.

Abstract: A fault state detection apparatus includes an input unit and a processing unit. The input unit receives condition monitoring data. The processing unit implements a trained machine learning algorithm to analyze the received condition monitoring data to determine if the received condition monitoring data is associated with a fault state. The trained machine learning algorithm was trained on the basis of a plurality of non-fault state condition monitoring data and associated ground truth information and on the basis of a plurality of fault state condition monitoring data and associated ground truth information. A subset of the plurality of fault state condition monitoring data was generated from one or more non-fault state condition monitoring data. Generation of fault state conditioning monitoring data in the subset of the plurality of fault state condition monitoring data comprises a transformation of non-fault state condition monitoring data to fault state condition monitoring data.

Abstract: A method of reducing mechanical vibrations of a motor system including an electric motor, the method including: a) receiving a vibration-related signal based on measurements by one or more sensors mounted on the electric motor, b) generating a reactive torque reference based on the vibration-related signal, and c) controlling the electric motor based on the reactive torque reference and a main torque reference to counteract the mechanical vibrations.