Granted Patent B2

US 12,724,935 · App. 17/127,533 · Granted Sep 1, 2026

Inventor: Konara Mudiyanselage Kosala Bandara (Beckenham, GB)

Assignee: AUTODESK, INC.

G06F30/20G06F30/13G06N3/126G06F2111/06G06F2119/14G06N20/20

Abstract

Claims (55)

1 . A computer-implemented method for generating a design of a frame system associated with a building, the method comprising:

determining a set of potential frame locations based on a frame grid for a structural system and a computer-aided design of the structural system;

computing a plurality of dead loads associated with a plurality of floors included in the building and a plurality of live loads associated with the plurality of floors based on the computer-aided design of the structural system; computing a building load centroid based on the plurality of dead loads and the plurality of live loads;

bifurcating the set of potential frame locations based on the building load centroid to generate a plurality of frame groups;

generating a genetic algorithm within an iterative optimization application associated with a frame system definition optimization problem, the genetic algorithm being based on the plurality of frame groups, wherein the genetic algorithm determines a plurality of values for a plurality of location counts associated with the plurality of frame groups by performing one or more search-based optimization operations based on a building objective value of an objective function that quantifies one or more design objectives;

executing an iteration of the genetic algorithm on a first building objective value for the objective function that is associated with a first plurality of values for the plurality of location counts to determine a second plurality of values for the plurality of location counts;

generating the design of the frame system based on the plurality of frame groups and the second plurality of values for the plurality of location counts; and

transmitting the design of the frame system to an iterative sizing application within the iterative optimization application, the iterative sizing application being associated with a vertical and lateral load design optimization problem, wherein the iterative sizing application generates a new building objective value for execution of a subsequent iteration of the genetic algorithm.

2 . The computer-implemented method of claim 1 , wherein bifurcating the set of potential frame locations comprises:

computing a plurality of projections based on a wind direction and the set of potential frame locations to determine a first subset of potential frame locations that are associated with the wind direction; and

dividing the first subset of potential frame locations into a first frame group that is to the left of the building load centroid with respect to the wind direction and a second frame group that is to the right of the building load centroid with respect to the wind direction.

3 . The computer-implemented method of claim 1 , wherein generating the genetic algorithm comprises defining a first location count included in the plurality of location counts as an integer design variable associated with the genetic algorithm that can range from one to a size of a first frame group included in the plurality of frame groups.

4 . The computer-implemented method of claim 1 , wherein generating the genetic algorithm comprises configuring a metaheuristic to iteratively determine the plurality of values for the plurality of location counts based on the objective function and a plurality of integer ranges associated with the plurality of location counts.

5 . The computer-implemented method of claim 1 , wherein the one or more design objectives include at least one of minimizing total weight, minimizing embodied carbon, or minimizing material cost.

6 . The computer-implemented method of claim 1 , further comprising computing the first building objective value for the objective function based a second computer-aided design of the structural system that is generated based on the computer-aided design of the structural system and the first plurality of values for the plurality of location counts.

7 . The computer-implemented method of claim 1 , wherein generating the design of the frame system comprises:

determining a subset of a first frame group included in the plurality of frame groups based on the building load centroid, wherein the subset has a size equal to a first value included in the second plurality of values for the plurality of location counts; and

specifying via the design of the frame system that the subset corresponds to a first frame included in the frame system.

8 . The computer-implemented method of claim 1 , wherein determining the set of potential frame locations comprises:

determining that a first plurality of structural elements specified in the computer-aided design of the structural system is associated with a first grid line included in the frame grid; and

adding a first location associated with the first plurality of structural elements to the set of potential frame locations.

9 . The computer-implemented method of claim 8 , wherein the first plurality of structural elements includes at least two columns and at least two beams.

10 . The computer-implemented method of claim 1 , further comprising executing a plurality of iterations of the genetic algorithm, wherein a first iteration of the genetic algorithm randomly determines the plurality of values for the plurality of location counts associated with the plurality of frame groups, and each given subsequent iteration of the genetic algorithm determines a given plurality of values for the plurality of location counts by performing the one or more search-based optimization operations based on a given building objective value of the objective function, the given building objective value being computed based on a prior iteration of the genetic algorithm immediately prior to the given subsequent iteration.

11 . One or more non-transitory computer readable media including instructions that, when executed by one or more processors, cause the one or more processors to generate a design of a frame system associated with a building by performing the steps of:

determining a set of potential frame locations based on a frame grid for a structural system and a computer-aided design of the structural system;

computing a plurality of dead loads associated with a plurality of floors included in the building and a plurality of live loads associated with the plurality of floors based on the computer-aided design of the structural system; computing a building load centroid based on the plurality of dead loads and the plurality of live loads;

bifurcating the set of potential frame locations based on the building load centroid to generate a plurality of frame groups;

generating a genetic algorithm within an iterative optimization application associated with a frame system definition optimization problem, the genetic algorithm being based on the plurality of frame groups, wherein the genetic algorithm determines a plurality of values for a plurality of location counts associated with the plurality of frame groups by performing one or more search-based optimization operations based on a building objective value of an objective function that quantifies one or more design objectives;

executing an iteration of the genetic algorithm on a first building objective value for the objective function that is associated with a first plurality of values for the plurality of location counts to determine a second plurality of values for the plurality of location counts;

generating the design of the frame system based on the plurality of frame groups and the second plurality of values for the plurality of location counts; and

transmitting the design of the frame system to an iterative sizing application within the iterative optimization application, the iterative sizing application being associated with a vertical and lateral load design optimization problem, wherein the iterative sizing application generates a new building objective value for execution of a subsequent iteration of the genetic algorithm.

12 . The one or more non-transitory computer readable media of claim 11 , wherein bifurcating the set of potential frame locations comprises dividing the set of potential frame locations into a first frame group that is to the left of the building load centroid with respect to a first direction and a second frame group that is to the right of the building load centroid with respect to the first direction.

13 . The one or more non-transitory computer readable media of claim 11 , wherein generating the genetic algorithm comprises defining a first location count included in the plurality of location counts as an integer design variable associated with the genetic algorithm that can range from one to a size of a first frame group included in the plurality of frame groups.

14 . The one or more non-transitory computer readable media of claim 11 , wherein generating the genetic algorithm comprises configuring a metaheuristic to iteratively determine the plurality of values for the plurality of location counts based on the objective function and a plurality of integer ranges associated with the plurality of location counts.

15 . The one or more non-transitory computer readable media of claim 11 , wherein the one or more design objectives include at least one of minimizing total weight, minimizing embodied carbon, or minimizing material cost.

16 . The one or more non-transitory computer readable media of claim 11 , further comprising computing the first building objective value for the objective function based a second computer-aided design of the structural system that is generated based on the computer-aided design of the structural system and the first plurality of values for the plurality of location counts.

17 . The one or more non-transitory computer readable media of claim 11 , wherein generating the design of the frame system comprises:

determining a first subset of a first frame group included in the plurality of frame groups based on a frame selection rule, wherein the first subset has a first size equal to a first value included in the second plurality of values for the plurality of location counts;

determining a second subset of a second frame group included in the plurality of frame groups based on the frame selection rule, wherein the second subset has a second size equal to a second value included in the second plurality of values for the plurality of location counts; and

specifying via the design of the frame system that the first subset and the second subset correspond to a plurality of frames included in the frame system.

18 . The one or more non-transitory computer readable media of claim 11 ,

wherein determining the set of potential frame locations comprises:

determining that a first plurality of structural elements specified in the computer-aided design of the structural system is associated with a first grid line included in the frame grid and a first wind direction; and

adding a first location associated with the first plurality of structural elements to the set of potential frame locations.

19 . A system comprising:

one or more memories storing instructions; and

one or more processors coupled to the one or more memories that, when executing the instructions, perform the steps of:

determining a set of potential frame locations based on a frame grid for a structural system of a building and a computer-aided design of the structural system;

computing a plurality of dead loads associated with a plurality of floors included in the building and a plurality of live loads associated with the plurality of floors based on the computer-aided design of the structural system;

computing a building load centroid based on the plurality of dead loads and the plurality of live loads;

bifurcating the set of potential frame locations based on the building load centroid to generate a plurality of frame groups;

generating a genetic algorithm within an iterative optimization application associated with a frame system definition optimization problem, the genetic algorithm being based on the plurality of frame groups, wherein the genetic algorithm determines a plurality of values for a plurality of location counts associated with the plurality of frame groups by performing one or more search-based optimization operations based on a building objective value of an objective function that quantifies one or more design objectives;

executing an iteration of the genetic algorithm on a first building objective value for the objective function that is associated with a first plurality of values for the plurality of location counts to determine a second plurality of values for the plurality of location counts;

generating a design of a frame system based on the plurality of frame groups and the second plurality of values for the plurality of location counts; and

transmitting the design of the frame system to an iterative sizing application within the iterative optimization application, the iterative sizing application being associated with a vertical and lateral load design optimization problem, wherein the iterative sizing application generates a new building objective value for execution of a subsequent iteration of the genetic algorithm.

Assignments (1)

Continuity (1)

References Cited (144)