Abstract: Data characterizing an assembly/structure containing a first stage and a second stage are received in a computer system. The first stage can contain a first cyclic symmetry and the second stage can contain a second cyclic symmetry. The first cyclic symmetry and the second cyclic symmetry are different from each other. Each stage may be a 360-degree stage. The received data includes a first mesh representing the first stage and a second mesh representing the second stage. Multiple simulation results are obtained using corresponding models in respective dynamic analyses of the assembly. Each model includes a set of constraints for coupling the first mesh and the second mesh. The set of constraints is associated with a group of distinct linked harmonic indices. Physical behaviors of the assembly are then calculated using one or more sets of the simulation results. Constraints are in forms of constraint equations.

Abstract: A method of manufacturing a panel using an initial die and a series of secondary dies includes sequentially defining multi-dimensional models for the series of secondary dies. The method includes simulating a geometry of an nth pre-panel, defining a multi-dimensional model of the nth secondary die based on the simulated geometry of the nth pre-panel, simulating operation of the nth secondary die on the nth pre-panel to determine geometry of an (n+1)th pre-panel, and determining a deviation between the simulated (n+1)th pre-panel and a target pre-panel geometry. If the deviation is outside tolerance, the method includes iteratively: adjusting the multi-dimensional model of the nth secondary die, simulating operation thereof to determine an adjusted simulated geometry of the (n+1)th pre-panel, and determining a deviation between the adjusted simulated geometry of the (n+1)th pre-panel and the target (n+1)th pre-panel, until the deviation is within the tolerance limit.

Abstract: A method of determining placement of nozzles within a fire suppression system comprising: determining a geometry of a room in response to a floor plan; determining a type of fire suppression agent required in response to at least one of articles in the room and hazards in the room; determining an amount of fire suppression agent required in response to at least one of the articles in the room, hazards in the room, the geometry of the room, average temperature in the room, and average pressure within the room; and determining a number of nozzles, a type of each of the nozzles, a location of each of the nozzles within the room in response to at least the amount of fire suppression agent required.

Abstract: The present disclosure provides a strip flatness prediction method considering lateral spread during rolling. The method includes: step 1: acquiring strip parameters, roll parameters and rolling process parameters; step 2: introducing a change factor of a lateral thickness difference before and after rolling and a lateral spread factor by considering lateral metal flow, and constructing a strip flatness prediction model based on the coupling of flatness, crown and lateral spread; step 3: constructing a three-dimensional (3D) finite element model (FEM) of a rolling mill and a strip, simulating strip rolling by the 3D FEM, extracting lateral displacement and thickness data of the strip during a stable rolling stage, calculating parameters of the strip flatness prediction model based on the coupling of flatness, crown and lateral spread; and step 4: predicting the flatness of the strip by the strip flatness prediction model based on the coupling of flatness, crown and lateral spread.

Abstract: A method and system for an accelerated design of a virtual product formulation based on an expert-enhanced quantitative formulation network includes sourcing qualitative expert formulation; creating a qualitative formulation network; extracting qualitative network-expansion data based on a category associated with a target product associated with the qualitative formulation network, creating a second set of network components including formulation variable nodes and formulation edge connections; integrating the second set of network components into the qualitative formulation network; transforming the qualitative formulation network integrated with the second set of network components to a quantitative formulation network; designing at least part of a virtual product formulation based on the quantitative formulation network; and generating a target formulation proposal that likely satisfies the target formulation objective based on executing the virtual product formulation as initialized.

Abstract: A geometry of a substrate surface is received at a neural network. The neural network is trained using one or more training sets. Each training set comprises a different type of substrate geometry and a collection of manufacturing process parameters. The substrate is configured to receive at least one liquid droplet. A shape of the at least one droplet after it has been deposited on the substrate is determined based on the received geometry. An output representing the determined shape of the at least one droplet is produced.

Abstract: A global computer aided engineering (CAE) model representing an electronic product that contains solder joints and an individual detailed solder joint model are received. The solder joint model can include a solder ball, one or more metal pads, a portion of printed circuit board, and a portion of semiconductor chip component. The global CAE model includes locations of the solder joints to be evaluated in a drop test simulation. The solder joint model is replicated at each location to create a local CAE model via a geometric relationship between the global CAE model and the local CAE model. Simulated physical behaviors of the product under a design condition are obtained in a co-simulation using the global CAE model in a first time scale and the local CAE model in a second time scale. Simulated physical behaviors are periodically synchronized based on kinematic and force constraints.

Abstract: Methods for training machine learning algorithms for generation of a reservoir digital twin include receiving information obtained from hydrocarbon wells. The information includes porosity logs, petrophysical data, rock typing data, pressure transient test results, vertical production logs, reservoir pressure logs, reservoir saturation logs, production performance, and injection performance. The reservoir saturation logs are normalized in accordance with time. A machine learning algorithm is trained using the reservoir pressure logs, the production performance, and the injection performance to provide variations in reservoir pressure of the hydrocarbon reservoir in accordance with time. The machine learning algorithm is trained to provide variations in reservoir saturation of the hydrocarbon reservoir in accordance with time.

Abstract: A method of determining placement of pipes within a fire suppression system including: obtaining a layout of nozzles within a room for a fire suppression system; determining a number of pipes, a length of each of the pipes, and a location of each of the pipes to connect each nozzle within the room to a fire suppression agent source in response to the layout of nozzles within the room; determining locations of junctions and elbows to interconnect the pipes; and determining whether the pipe, junctions, and elbows violate a piping constraint.

Abstract: A method of designing a fire suppression system including: determining nozzle placement for nozzles of a fire suppression system within a location; determining piping placement for pipes of the fire suppression system within the location; determining whether the nozzle placement or piping placement violate a constraint; and generating a map displaying the nozzle placement and the piping placement on a computing device.

Abstract: The invention relates to a method for simulation-based analysis and/or optimization of a motor vehicle, preferably having the following working steps: simulating (SIOI) a driving operation of the motor vehicle (I) on the basis of a model (M) with at least one manipulated variable for acquiring values of at least one simulated variable which is suitable for characterizing an overall vehicle behaviour, in particular a driving capability, of the motor vehicle (I), wherein the model has at least one partial model, in particular a torque model, and wherein the at least one partial model is based on a function and preferably characterizes the operation of at least one component, in particular of an internal combustion engine of the motor vehicle (I); and—outputting (S I03) the values of the at least one simulated variable.

Abstract: In one embodiment, a wizard can automate a setup of a welding simulation by requiring the input of data (e.g. in data entry fields labelled as required) that is used to automatically set up a welding simulation. The wizard can be part of a general purpose mechanical simulation software package, and the wizard can receive inputs from CAD software that specifies the geometrical shapes of bodies of the assembly to be welded and the filling material itself and physical properties of bodies to be welded (e.g. sizes of bodies, number of bodies, physical arrangement and geometries of bodies, melting temperatures, etc.), in addition to the material physical properties and the wizard can provide outputs to the mechanical simulation software package to provide boundary conditions for use in the mechanical simulation software that can use finite element analysis methods in simulations.

Abstract: A method and controller for operating a pumping station. The method includes receiving (1102), by at least one controller (910, 952), sensor data (712) of a first pumping station (900) corresponding to a liquid being transported from the first pumping station (900). The method includes predicting (1104) arrival of the liquid, by the at least one controller (910, 952), at a second pumping station (900). The method includes executing (1106) one or more pump models (720), by the at least one controller (910, 952), according to the sensor data (712) to determine an optimal pumping configuration. The method includes operating (1108) one more pumps of the second pumping station (900), by the at least one controller (910, 952), according to the optimal pumping configuration.

Abstract: An approach for maintaining pipeline infrastructure based on graphical images is disclosed. The approach receives a plurality of parameters in a pipeline infrastructure by using a plurality of sensors. The approach generates a digital twin of the determined one or more susceptible and/or vulnerable points/areas/joints in the pipeline infrastructure. The approach simulates the determined susceptible areas/points/joints in the pipeline infrastructure for determining one or more damages and/or defects. The approach predicts one or more proactive maintenance actions based on the determined damage and/or defect in the pipeline infrastructure to prevent the users from being near the susceptible area/joints/portions and prioritizing the proactive maintenance actions based on the level and extent of damage and/or defect.

Abstract: Embodiments of the invention are shown in the figures, where a method is presented for designing a component, including designing or receiving a model of the component; determining at least one mode shape of at least a portion of the model; redesigning the model based on the determined at least one mode shape to obtain a redesigned model of the component; and manufacturing the component in accordance with the redesigned model.

Abstract: A computer-implemented method of generating an operation procedure for a simulation of a system, in particular a mechatronic system is disclosed. A source node has at least one source parameter (Ps) and a first simulation system with at least one first simulation node is determined, wherein the first simulation node includes at least one input parameter (Pi) and at least one output parameter (Pa). The first simulation node includes a simulation function for determining the output parameter (Pa) based on the input parameter (Pi) of the first node. When the input parameter (Pi) is available based on the source parameter (Ps), a global operation graph is built describing a link between the source node and the first simulation node for describing an operating procedure of the simulation of the system.

Abstract: Processes for optimizing the geometry of a blade for use in a propeller are disclosed. In one exemplary process, an optimization routine that generates new blade geometries based on structural parameters and calculates performance parameters of each blade geometry, including aerodynamic performance parameters, farfield acoustic parameters, and/or electrical power requirements to operate a propeller having the blade geometry, is performed. The optimization routine receives design parameters and weightings from a user and can use one or more surrogate algorithms to map a design space of the weighted values of the design parameters to find their local minima. The optimization routine then determines an optimized blade geometry using a gradient-based algorithm to generate new blade geometries to explore the minima until the weighted values of the design parameters converge at an optimized blade geometry representing the global minima of the design space.

Abstract: A device receives an infrastructure design document that represents a network infrastructure design. The device causes the infrastructure design document to be displayed via a first interface of a geographic information system (GIS) tool that is to be used during an inspection of a site, where the inspection includes inspecting structural components that are to support equipment of a network. The device receives, from a user device, feedback data that is based on the inspection. The device causes the feedback data to be integrated into the GIS tool. The device receives, from another user device, instructions that are to be used to update the infrastructure design document. The device updates the infrastructure design document based on the set of instructions and performs actions that allow the infrastructure design document to be used when implementing the network infrastructure design.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing thermal modeling. In one aspect, a method includes receiving monitoring data comprising temperature data measured inside a site, mode data, and state data, receiving weather data descriptive of weather at the site, and aligning the received temperature data, mode data, and state data with the received weather data. The method also includes determining an internal heat gain representing an amount of heat generated at the site irrespective of the heating or cooling system, determining at least one of a thermal product for the site or a thermal potential for the heating or cooling system, generating, based on the internal gain and the thermal product or the thermal potential, a thermal model for the site, and providing, as output, the generated thermal model.

Abstract: The present disclosure is directed to a system for reparameterizing of a neural network to optimize structural designs. The system can obtain data descriptive of a design space for a physical design problem. The design space is parameterized by a first set of parameters. The system can reparameterize the design space with a machine-learned model that comprises a second set of parameters. For a plurality of iterations, the system can provide an input to the machine-learned model to produce a proposed solution. The system can apply one or more design constraints to the solution to create a constrained solution. The system can generate a physical outcome associated with the constrained solution using a physical model. The system can evaluate the physical outcome using an objective function and update at least one of the second set of parameters. After the plurality of iterations, the system can output a solution.