Multi-Objective Optimization Layout Design
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for multi-objective optimization of complex technical systems often rely on non-integrated software tools, leading to incomplete exploration of design potential and inefficient iteration processes, resulting in suboptimal solutions.
Innovation Solution
A computer-implemented method for designing Pareto-optimal layouts that integrates data processing, multi-objective optimization, and surrogate modeling to systematically explore layout configurations and visualize trade-offs, using a user interface to select optimal configurations based on inferred objective responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If non-integrated software tools are used for multi-objective optimization, then tool specialization is maintained, but design potential exploration becomes incomplete and iterative efficiency decreases
Solution Approach 1:
The patent merges multiple previously separate software tools (modelling tool, simulation tool, data analytics tool, optimization tool) into a single integrated software system. This integration enables seamless data exchange and coordinated operation between modules, allowing complete exploration of design potential while maintaining iterative efficiency through unified processing workflows.
Solution Approach 2:
The integrated software system performs multiple functions that were previously distributed across separate specialized tools. The system can handle modelling, simulation, data analytics, optimization, and visualization within a single platform, eliminating the need for multiple separate tools and enabling comprehensive design exploration.
2Reliability
If non-integrated tools are used, then each tool can be specialized, but the overall design process requires many iteration loops and may not reach global maximum
Solution Approach 1:
The integrated system implements continuous feedback loops where optimization results feed back into the modelling and simulation processes. The system automatically uses simulation results to guide optimization iterations and updates the design model based on performance data, enabling efficient convergence toward global maximum without requiring numerous manual iteration loops.
Solution Approach 2:
The system performs preliminary actions by pre-processing design spaces, pre-calculating simulation parameters, and pre-optimizing iteration paths before the main design process begins. This preparation enables faster convergence to optimal solutions by avoiding redundant calculations and unnecessary iteration loops during the actual optimization process.
3Loss of information
If limited design space exploration is performed, then computational resources are saved, but knowledge about true design potential remains incomplete
Solution Approach 1:
The system applies partial action by strategically sampling only the most promising regions of the design space identified through preliminary analysis and surrogate models. Instead of exhaustively exploring the entire design space, the optimization algorithm focuses computational resources on areas with highest potential, achieving complete knowledge of design potential while minimizing unnecessary computational expenditure.
Solution Approach 2:
The system introduces intermediary components including surrogate models and design space mapping algorithms that mediate between the design parameters and simulation results. These intermediaries enable efficient exploration of design potential by creating simplified representations of complex systems, allowing comprehensive analysis with reduced computational resources.
Data Source
AI summary
The present disclosure relates to multi-objective optimization of complex technical systems. A method of designing a Pareto-optimal layout of a system includes processing input data relating to defining a layout space of layout parameters, a target space of target parameters, and constraints in the layout parameters and the target parameters, determining one or more sets of layout parameter values, each set specifying a layout configuration of the system to be modeled, receiving objective responses for the system having layout configurations specified by the one or more sets of layout parameter values, wherein each objective response corresponds to a target parameter value achieved by the system when having a layout configuration specified by one of the sets of layout parameter values, applying multi-objective optimization with respect to the target parameters to determine one or more further sets of layout parameter values, receiving objective responses for the system having layout configurations specified by the one or more further sets of layout parameter values, repeating the steps of applying multi-objective optimization and receiving respective objective responses until an abort criterion is met, and providing a user interface for Pareto-optimal design of the system to be modeled, the user interface configured for selecting a specific layout configuration on basis of visualizing objective trade-offs inferred from the objective responses for the respective sets of layout parameter values, wherein the trade-offs are inferred from the objective responses based on determining Pareto-optimal point.