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.

A computer-implemented method of machine-learning is described that includes obtaining a dataset of virtual scenes. The dataset of virtual scenes belongs to a first domain. The method further includes obtaining a test dataset of real scenes. The test dataset belongs to a second domain. The method further includes determining a third domain. The third domain is closer to the second domain than the first domain in terms of data distributions. The method further includes learning a domain-adaptive neural network based on the third domain. The domain-adaptive neural network is a neural network configured for inference of spatially reconfigurable objects in a real scene. Such a method constitutes an improved method of machine learning with a dataset of scenes including spatially reconfigurable objects.

Disclosed are a method and an apparatus for string connecting photovoltaic modules. The method includes: acquiring position information of n photovoltaic modules to be connected; categorizing the n photovoltaic modules into m partitions based on the position information of the n photovoltaic modules; generating k candidate connection solutions of an i.sup.th partition in the m partitions, wherein the i.sup.th partition includes m photovoltaic modules, and each of the k candidate connection solutions uses one photovoltaic module in the m photovoltaic modules as a starting point, and obtaining at least one string of photovoltaic modules by simulating connection of the m photovoltaic modules according to a preset connection solution; and selecting a target connection solution from the k candidate connection solutions based on an estimated cable use amount corresponding to each of the k candidate connection solutions.

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.

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.

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.

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.

An engineering support system that supports engineering of a process control system, includes: a storage; and a processor connected to the storage and that: transforms design drawings into semantic models and outputs the semantic models to the storage; and generates a combined semantic model by combining the semantic models based on a degree of similarity among the semantic models and outputs the combined semantic model to the storage, wherein each of the semantic models is expressed by first information indicating elements included in the design drawings and second information indicating a relationship between the elements.

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.

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.