Abstract: A method for interactive explanations in industrial artificial intelligence systems includes providing a machine learning model and a set of test data, a set of training data and a set of historical data simulating a piping and process equipment; predicting a result for the piping and process equipment based on the machine learning model using the set of test data and the set of training data, wherein the set of historical data is used by the machine learning model to predict at least one parameter of the piping and process equipment; and presenting the predicted at least one parameter on a piping and instrumentation diagram of the piping and process equipment.

Abstract: A method for recommending an operational command includes receiving an alarm from a sensor and/or an operator; obtaining the current state of the plant that includes a current process value and/or operational command; comparing the current state to a list of historic states, each comprising a plurality of historic process values and/or historic operational commands; when the current state matches a subset of at least one of the historic states, starting a simulation and running a plurality of simulations, each based on a variation of at least one of the historic operational commands; determining, for each simulation of the plurality of simulations, a quality value, based on at least one quality criterion; and recommending the variation of the operational command that resulted in the simulation with the highest quality value.

Abstract: A display device for a motor vehicle is provided. The display device includes at least one display with a display surface for displaying content via a plurality of pixels. The display device comprises a light-guiding lens with at least one entry surface and an exit surface. During operation of the display device the light emitted from the display surface enters the light-guiding lens through the at least one entry surface and is emitted by an exit surface, such that the content is shown on the exit surface. In one embodiment, the exit surface features a different shape. In another embodiment, the exit surface is a different size than the at least one display surface. In another embodiment, the display device comprises several displays with display surfaces at distances to each other, and the light-guiding lens features merely one exit surface or several exit surfaces directly adjoining each other.

Abstract: Various sensors and methods of assembling sensors are described. In some embodiments, the sensor assembly includes a first end, a body portion, and a second end. The first end can include a neck portion and a connector portion and the second end can include a flap, a first component, a neck portion, and a second component. A method is also described for sensor folding. The method can include using a circuit with an attached emitter and a detector that is separated by a portion of the circuit. The method can also include folding the portion of the circuit such that a first fold is created through the emitter and folding the portion of the circuit such that a second fold is created such that the first fold and second fold form an angle.

Abstract: The present disclosure is directed to a method of disturbance correction and to a laser scanning microscope carrying out this method. Specifically, it is directed to an image recording method according to the MINFLUX principle, in which a spatially isolated fluorescence dye molecule is illuminated at a sequence of scan positions by an intensity distribution with a local intensity minimum, and the number of fluorescence photons emitted by the fluorescence dye molecule is detected at each of the scan positions. The location of the molecule is determined with a high spatial resolution from the scan positions and the numbers of fluorescence photons. A disturbance is captured when illuminating the fluorescence dye molecule and detecting the fluorescence light, said disturbance being considered in corrective fashion when determining the location of the fluorescence dye molecule.

Abstract: A method for deciding on a machine learning model result quality based on the identification of distractive samples in the training data includes providing a first result of the model based on initial training data; determining a first performance of the first result of the model; logging input data; providing a second result of the model based on initial training data and the input data, determining a second performance of the second result of the model and thereon based identifying erroneous data within the input data and/or the training data.

Abstract: A vehicle includes a chassis, a body, and a door assembly. The body is supported by the chassis, and defines a driver compartment and a cargo compartment. The driver compartment has a cab opening and the cargo compartment has a cargo opening. The door assembly is coupled to the body and provides selective access into the driver compartment and into the cargo compartment through the cab opening and cargo opening, respectively. The door assembly includes a first door and a second door. The first door is movable between a first position extending across the cab opening and a second position extending at least partially across a portion of the cab opening. The second door is movable between a third position extending across the cargo opening and a fourth position extending at least partially across a portion of the cab opening.

Abstract: A transport vehicle, such as a vision guided vehicle, can comprise a drive portion constructed to facilitate movement of the transport vehicle and a load portion constructed to engage an object of interest. The load portion can comprise an object engagement apparatus and at least one sensor coupled to or disposed within a distal end of the object engagement apparatus, wherein the sensor can be at least a 2D sensor. The engagement apparatus can comprise forks, at least one fork having sensor coupled to or disposed within a fork tip. The 2D sensor can comprise a scanning LIDAR sensor arranged to collect information to identify a pickable pallet, for example.

Abstract: A method for explanation of machine learning results based on using a model collection includes training at least two machine learning models with at least two competing strategies for the at least one dataset; and using the least two machine learning models to yield at least two different predictions and/or at least two explanations for the at least one dataset.

Abstract: A method for enabling user feedback and summarizing return of investment for machine learning systems includes providing a training data set and an initial machine learning model; providing a result of the initial machine learning model; receiving feedback on the result of the initial machine learning model from a user enriching the training dataset based on the feedback to an enriched data set; and retraining the initial machine learning model to a retrained machine learning model based on an enriched data set.

Abstract: The invention relates to a method for solvent-free production of an electrode. By means of the method it is possible to produce an electrode which has high mechanical stability and which provides a high specific capacitance. The method also enables the production of an electrode which can be used as an anode in a lithium-ion battery, without giving rise to unstable operation with undesirable and irreversible degradation reactions. An electrode is also provided, which has the above-mentioned advantages. In addition, uses of the electrode according to the invention are proposed.

Abstract: An apparatus for generating an enhanced signal from an input signal, wherein the enhanced signal has spectral values for an enhancement spectral region, the spectral values for the enhancement spectral regions not being contained in the input signal, includes a mapper for mapping a source spectral region of the input signal to a target region in the enhancement spectral region, the source spectral region including a noise-filling region; and a noise filler configured for generating first noise values for the noise-filling region in the source spectral region of the input signal and for generating second noise values for a noise region in the target region, wherein the second noise values are decorrelated from the first noise values or for generating second noise values for a noise region in the target region, wherein the second noise values are decorrelated from first noise values in the source region.

Abstract: The invention relates to a compressor arrangement comprising a compressor (2) for compressing a process gas (13) from a suction region (21) towards a pressure region (22), a mechanical seal arrangement (3) for sealing against an atmosphere (6) on a shaft (5) of the compressor (2), wherein the mechanical seal arrangement comprises a mechanical seal (4) having a stationary slide ring (41) with a first sliding surface (41a) and a rotating slide ring (42) with a second sliding surface (42a), which define a sealing gap (42a) between the sliding surfaces (41a, 42a), and a barrier fluid supply (7) with a barrier fluid line (70) which extends from the pressure region (22) of the compressor (2) to the mechanical seal (4) and through which process gas is branched off from the pressure region, the stationary slide ring (41) having a through opening (8), which extends from a rear side (41b) of the stationary slide ring (41) to an orifice at the first sliding surface (41a) of the stationary slide ring to supply process ga

Abstract: Various sensors and methods of assembling sensors are described. In some embodiments, the sensor assembly includes a first end, a body portion, and a second end. The first end can include a neck portion and a connector portion and the second end can include a flap, a first component, a neck portion, and a second component. A method is also described for sensor folding. The method can include using a circuit with an attached emitter and a detector that is separated by a portion of the circuit. The method can also include folding the portion of the circuit such that a first fold is created through the emitter and folding the portion of the circuit such that a second fold is created such that the first fold and second fold form an angle.

Abstract: A method improves antenna matching for a node, in particular a sensor apparatus and/or actuator apparatus, of a communications network. The node is capable of radio communication and has a radio module equipped with an antenna and a transmit path and/or receive path for radio signals to be emitted and/or received. The node has a power supply apparatus, which is preferably energy self-sufficient, in particular a battery. The antenna has an impedance and in the receive situation and/or in the transmit situation in the case of adjustable matchings, preferably by use of adjustable matching networks, the signal to noise ratio associated with each matching is estimated, and a matching is selected from the different matchings for the receive mode and/or the transmit mode.

Abstract: The invention relates to a process for manufacturing a multilayered porous transport layer, the process comprising (a) providing a first feedstock comprising first metal particles and a first polymer binder; and providing a second feedstock comprising second metal particles and a second polymer binder; the first and the second feedstock having a metal powder content of 40 to 70% by volume; and the first feedstock having (i) metal particles with a smaller average particles size, (ii) a higher metal powder content, or (iii) both, metal particles with a smaller average particles size and a higher metal powder content compared to the second feedstock; (b) coextruding the first and the second feedstock to form a film-shaped green body comprising a first layer and a second layer, the second layer being materially connected to the first layer above the melting temperature and or glass transition temperature of the first polymer binder and the second polymer binder; (c) optionally smoothening the film-shaped gr

Abstract: A power tool including a shroud for restricting the path of debris generated by a rotatable cutting disc and defining a shroud outlet opening through which the debris can be sucked by a vacuum device. The debris enters a sub-volume along a first axis and exits the sub-volume along a second axis in a different plane. A conduit having a curved wall defines the sub-volume such that debris travelling therethough undergoes a change in direction and exits the sub-volume along a direction substantially parallel with the second axis.

Abstract: A transport vehicle, such as a vision guided vehicle, can comprise a drive portion constructed to facilitate movement of the transport vehicle and a load portion constructed to engage an object of interest. The load portion can comprise an object engagement apparatus and at least one sensor coupled to or disposed within a distal end of the object engagement apparatus, wherein the sensor can be at least a 2D sensor. The engagement apparatus can comprise forks, at least one fork having sensor coupled to or disposed within a fork tip. The 2D sensor can comprise a scanning LIDAR sensor arranged to collect information to identify a pickable pallet, for example.

Abstract: A computer implemented system, method, or computer readable medium for providing a interactive digital tool that permits users to investigate and evaluate financial, trade, and business-related risks. The system, method, or computer readable medium can be configured to include a software engine that identifies risk subgraphs or other subgraph features in accordance with automated traversal based on a set of rules.

Abstract: A research, analysis, regulatory compliance and media platform that connects customers to finished research and analysis produced by subject matter experts is described. The platform facilitates research, investigations, and analysis by creating a single environment in which a group of distributed analysts conduct research and investigations, store and retrieve documents and other sources, collaborate, and publish findings. Consumers are able to query a published knowledge graph, surface high value relationships, and access insights captured by analyst through a customer web portal or external production environment. The platform allows analysts and customers to research and map the commercial, financial, and facilitation networks of sanctioned or other actors that may be associated with illicit activity. Customers can access visual graphs depicting relationships between sanctioned and non-sanctioned actors in order to evaluate their possible exposure to financial crime or sanctions-related risks.