Abstract: An industrial plant machine learning system includes a machine learning model, providing machine learning data, an industrial plant providing plant data and an abstraction layer, connecting the machine learning model and the industrial plant, wherein the abstraction layer is configured to provide standardized communication between the machine learning model and the industrial plant, using a machine learning markup language.

Abstract: A field of electric motors, such as electric motors and electric generators for industrial applications, and more particularly to an electric motor.

Abstract: A grounding ring includes: a first clamping member having a radially inward side and a radially outward side, the radially outward side at least in part defining a channel; and a second clamping member disposable within the channel so as to prohibit the second clamping member from moving in an axial direction with respect to the first clamping member, the second clamping member being rotatable with respect to the first clamping member within the channel about the axial direction.

Abstract: A metal enclosure for electrical switchgear, the metal enclosure is configured to be pressurized above atmospheric pressure, the metal enclosure having: metal walls sealing a volume for accommodating the electrical switchgear, the metal walls including a first metal wall arranged opposite a second metal wall, wherein at least the second metal wall is a corrugated metal plate with corrugations that extend along a first axis, a set of elongated metal elements attached to the first metal wall and to the second metal wall, the elongated metal elements are arranged through holes in the first metal wall and in the second metal wall and reach outside the metal enclosure, a set of elongated metal stiffeners attached to a rear side of the second metal wall outside the metal enclosure, each of the metal stiffeners is attached to at least two of the corrugations of the second metal wall, wherein each metal stiffener is attached to at least one of the elongated metal elements.

Abstract: A system and method for controlling multiple robots using a single HMI device includes having a Teach Pendant Unit Multiplexer (TPU-MUX) that allows multiple robots to remain connected to the single HMI device all at the same time. The system further allows the HMI device to communicate with at least one robot among the plurality of connected robots, at a time and to switch between a plurality of connected robots seamlessly.

Abstract: Described herein is a layered panel for on-site modular construction of buildings. The layered panel includes a layer formed by a prefabricated cement-bonded particle board, a supporting structure and fastening elements attaching the prefabricated cement-bonded particle board to the supporting structure. Also described herein is a method for manufacturing the layered panel, an installation for manufacturing the layered panel and a method for the construction of buildings with a plurality of the layered panels.

Abstract: A method for estimating an SoH of a battery includes discharging a Field Battery; measuring parameters of the Field Battery during discharging, and determining a Field Battery measuring discharge curve; estimating a Healthy Discharge Curve of the Field Battery using a neural network; comparing the estimated Healthy Discharge Curve of the Field Battery with the measuring discharge curve of the Field Battery; when a value of the measuring discharge curve of the Field Battery is smaller than a value of the estimated Healthy Discharge Curve of the Field Battery, determining the time difference between the distinct point of time and a predicted point of time, when the value is estimated to be reached according to the prediction of the neural network; estimating an SoH of the Field Battery based on the difference between the distinct point of time and the predicted point of time.

Abstract: A method for assisting an operator to handle a crane of a container lifting system includes using a container lifting management device that displays a progress indicator to the operator. The progress indicator shows representations of a number of sequential steps being performed by the crane in an operations cycle, obtains sensor data of the crane at a current point in time during the operations cycle, determines a current step of the operations cycle that the crane currently performs and how much of the current step the crane has completed based on the sensor data and indicates the progress at the current point in time in the representation of the current step of the progress indicator.

Abstract: A system and method for managing an on-sensor machine learning (ML) model includes monitoring performance parameters of plurality of on-sensor ML models present in an industrial plant; detecting a degradation of at least one on-sensor ML model based on the monitored ML model performance parameters of the plurality of on-sensor ML models, wherein degradation of the at least one on-sensor ML model comprises at least one of: data distribution change, training serving skew, model drift, occurrence of outlier event, and data quality issue; and updating the at least one on-sensor ML model based on the ML model upgradation parameters retrieved from one of the plurality of sources.

Abstract: A method for obtaining diagnostic data in a distributed control system, comprising obtaining issue data, wherein the issue data is indicative of a system anomaly or fault; processing the obtained issue data to determine diagnostic requirements; identifying a kernel-instrumenting bytecode data (kiBD) based on the determined diagnostic requirements; loading and activating the identified kiBD, wherein activation comprises linking the kiBD to a system hook; and obtaining diagnostic data using the activated kiBD.

Abstract: A parallel linkage mechanism includes a support member; a connection joint; a first arm interconnecting the support member and the connection joint and including a first intermediate joint and a first driving link rotatable around a first axis; a second arm interconnecting the support member and the connection joint in parallel with the first arm, the second arm including a second intermediate joint and a second driving link rotatable around a second axis, the first and second axes defining a reference plane; wherein the parallel linkage mechanism is configured to adopt a state where the first and second driving links are crossed, the connection joint is positioned on a primary side of the reference plane, and the first and second intermediate joints are positioned on an opposite secondary side of the reference plane.

Abstract: A method for operational optimization of an industrial plant includes receiving, at a computing system, values of operational parameters of the industrial plant, the operational parameters including at least hydrogen production by the at least one hydrogen producer, hydrogen consumption by the at least one hydrogen consumer, energy production of the industrial plant, energy consumption of the industrial plant, availability of electrical energy via the at least one source of electrical energy, and pricing of electrical energy. A time-series for values is forecasted. One or more optimum operational setpoints for optimizing operational control of the industrial plant are determined in terms of at least one of energy consumption and operation costs of the industrial plant, wherein the one or more optimum operational setpoints are determined based on at least one degree of freedom for the industrial plant.

Abstract: A computer-implemented method for reverse engineering control logic of a module for a modular industrial plant includes: obtaining module-related data including runtime data relating to prior use of the module during a timeperiod in which at least one piece of equipment of the module transitions from a first equipment state to a second equipment state, the runtime data including tags indicating the equipment state of the equipment at a plurality of timepoints during the timeperiod; and inferring from the module-related data one or more equipment state transition conditions causing the equipment to transition from the first equipment state to the second equipment state.

Abstract: A guide roller or roller unit on a transport unit of a transport device in the form of a long stator linear motor suitable for hygiene applications, includes a first axial end face of a roller of the transport unit which is closed by an end wall and the opposite second end face is open, such that a bearing recess is formed in the interior of the roller, which is axially limited on one side by the end wall, wherein a shaft journal projects through the open second axial end face into the bearing recess and a bearing arrangement is arranged in the bearing recess on the shaft journal, and in the region of the second end face an annular region forming between the centrally arranged shaft journal and the inner circumferential surface of the bearing recess is closed off by a sealing unit.

Abstract: A method for testing a two-phase cooling device is provided. The cooling device has a housing surrounding a cavity and a cooling medium within the cavity. The method includes controlling a temperature of ambient air of the cooling device such that the cooling medium within the cavity transitions from its liquid state to its solid state and/or from its solid state to its liquid state, while monitoring a first temperature of the cooling device, determining whether the monitored first temperature fulfills a predetermined criterion, and determining that the cooling device is overfilled with the cooling medium if the predetermined criterion is fulfilled.

Abstract: A computer-implemented method for automating the development of industrial machine learning applications includes one or more sub-methods that, depending on the industrial machine learning problem, may be executed iteratively. These sub-methods include at least one of a method to automate the data cleaning in training and later application of machine learning models, a method to label time series (in particular signal data) with help of other timestamp records, feature engineering with the help of process mining, and automated hyper-parameter tuning for data segmentation and classification.

Abstract: An unloading system for automatically unloading an object includes a robot arm having a gripper and a control unit. The control unit is configured to drive the robot arm to place the gripper at a side surface of the object and to allow the gripper to exert a lateral force to the object to drive the object to slide onto a loading surface.

Abstract: A method for estimating a level of confidence of a response that a AI/ML model delivers in response to a query, includes obtaining a representation of the query in a space; determining a closeness of the representation to one or more reference representations of reference inputs that are known to belong to a domain of validity (DOV) of the AI/ML model, determining the level of confidence based at least in part on this closeness; and in response to the level of confidence being lower than a predetermined threshold: obtaining feedback whether the response provided by the AI/ML model is correct; and when this feedback indicates that the response is correct, determining that the representation of the query belongs to the DOV, wherein the query relates to a property of an industrial asset in an industrial plant, and/or of an industrial process executed on this industrial plant.

Abstract: A method for automating error diagnosis of an industrial drive product includes obtaining, by a generative artificial intelligence (AI) agent, a notification that is associated with an error occurred; retrieving pieces of information from one or more data sources that are associated with the industrial drive product; determining a relevance in relation to the error; for pieces of information of the plurality of pieces of information that are determined to have a relevance above a predetermined relevance threshold, augmenting, by the generative AI agent, the pieces of information; and generating, by the generative AI agent, a proposal for handling the error based on the augmented pieces of information.

Abstract: A method for training and using a ML model on customer engineering data with increased customer privacy preservation in an industrial context includes, in a training phase, obtaining the customer engineering data from customer project data associated with a customer; training the ML model on the customer engineering data by using federated ML; and applying customer privacy preservation mechanisms on information inferred by the ML model. When using the ML model for inference: verifying, by using an Entailment Checking method, that the information inferred by the ML model and determined by the ML model to be associated with the customer were obtained from the customer project data.