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.

A shape change prediction method for a press formed part for predicting a shape change of the press formed part with a lapse of time units after springback at a moment of a release from a die includes: a shape/residual stress immediately after springback acquisition step of acquiring a shape and a residual stress of the press formed part immediately after the springback by a springback analysis of the press formed part; a residual stress relaxation/reduction setting step of setting a value of a residual stress relaxed and reduced from the acquired residual stress to the press formed part immediately after the springback; and a shape analysis step of determining a shape, in which moments of force are balanced, for the press formed part to which the value of the relaxed and reduced residual stress is set.

A simulation device for analyzing behavior of a granular material that includes a plurality of particles includes a first parameter acquisition unit that acquires a first parameter including a parameter relating to the granular material, a second parameter calculation unit that calculates a second parameter, when a particle group including the plurality of particles is coarsely viewed as a single coarse-view particle, the second parameter relating to the coarse-view particle, and a coarse-view particle behavior analysis unit that analyzes a behavior of the coarse-view particle based on the first parameter and the second parameter. The second parameter calculation unit calculates the second parameter by solving a characteristic equation that uses a relationship between an elastic energy of the particle group and an elastic energy of the coarse-view particle.

A method of automatically generating AutoCAD drawings includes: receiving, by a receiving unit, a data sheet generated only with input data necessary for drawing a column from strength calculation data for the column provided by a strength calculation program; loading, by a loading unit, the input data; and generating AutoCAD drawings of the column by activating an automatic AutoCAD drawing generation interface by a user's selection after the input data is loaded, the automatic AutoCAD drawing generation interface being activatable only after the input data is loaded.

A tubular joint includes a tubular substrate extending along an axis. The substrate has a first inner diameter. A first tubular brace member is additively manufactured on the substrate and is connected thereto at a proximal end of the first tubular brace member. A second tubular brace member is additively manufactured on the substrate and is connected thereto at a proximal end of the second tubular brace member. At respective distal ends of the brace members, the first tubular brace member and the second tubular brace member have a circular cross-sectional shape having a distal wall thickness and a second inner diameter that is smaller than the first inner diameter. At the proximal ends the of brace members, the first tubular brace member and the second tubular brace member have respective proximal wall thicknesses that are greater than the distal wall thickness.

Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design of physical structures using generative design processes. A method includes: obtaining a design space and design criteria for a modeled object including a design constraint on an acceptable likelihood of failure, wherein a statistical model that relates a structural performance metric to specific likelihoods of failure for material(s) is used to translate between the acceptable likelihood of failure and a value for the structural performance metric; iteratively modifying a generatively designed shape of the modeled object in the design space in accordance with the design criteria including the design constraint to stay under the acceptable likelihood of failure for the physical structure, wherein the numerical simulation includes computing the structural performance metric, which is evaluated against the design constraint; and providing the generatively designed shape of the modeled object for use in manufacturing a physical structure.

A method for designing an optical scanning mirror is provided. The method may include receiving, by a communication interface, a set of design parameters of the scanning mirror. The method may also include simulating scanning mirror oscillation, by at least one processor, based on the set of design parameters using a computer model. In certain aspects, the computer model may include a lookup table that correlates electrostatic force applied to a sample scanning mirror and angular displacement in the sample scanning mirror caused by the electrostatic force. The method may further include generating, by the at least one processor, mirror oscillation data as an output of the computer model for designing the scanning mirror. The mirror oscillation data may include a correlation of drive frequency, angular displacement, and time.

A pressure-resistant hull for a submersible, includes unit hulls, reinforcing ribs, connecting channels, and closure heads. A plurality of unit hulls are provided, and are sequentially strung together spiralling upward or spiralling downward, the closure heads being arranged on the unit hulls at the first position and the last position respectively, an observation window being provided on each unit hull respectively, adjacent two unit hulls in a horizontal direction being respectively connected by means of a reinforcing rib, and at least two connecting channels being provided between adjacent two rings of the unit hulls in the vertical direction. The design method includes using a spiral joining structure to facilitate organic adjustment of the number of unit hulls, thus having better utilization of space and aiding to greatly expand the space. The sensitivity of the limit load to defects is low, increasing axial rigidity, improving the overall pressure-resistive ability.

The present invention discloses an optimization method for a screen surface dynamic load of a vibrating screen. The method includes the following steps: step 1. selecting design variables, and establishing an experimental matrix; step 2. performing a response curved surface experiment; step 3. establishing two double-objective optimization models and solving the same to obtain two groups of Pareto solution sets, wherein the solution sets respectively represent screening efficiency optimization paths of the vibrating screen under the conditions of a high screen surface dynamic load and a low screen surface dynamic load; and step 4. calculating an optimization space for a screen surface dynamic load under a high screening efficiency. According to the method of the present invention, the screen surface dynamic load can be directly reduced, and the service life of the screen surface and the whole vibrating screen is prolonged.

A computing device includes: a tomographic image acquisition unit that acquires a plurality of tomographic images representing shapes of reinforcing fibers and shapes of resin in a plurality of cross sections obtained when an article containing the reinforcing fibers and the resin is divided in parallel; and a computing unit that calculates a rigidity parameter of each of a plurality of small regions obtained by dividing the article, based on the plurality of acquired tomographic images.